Proceedings of the Second International Conference on Soft Computing for Problem Solving (SocProS 2012), December 28-30, 2012

Most of the diabetic patients need to take insulin before every meal. The doctors have to decide insulin doses for every patient according to the patient’s previous records of doses and sugar levels measured at regular intervals. This paper proposes a hidden Markov model to predict the insulin chart for a patient and uses simulated annealing search algorithm to efficiently implement the model. The one-month chart maintained by the patient has been used to train the model, and the prediction for next fifteen days is done on the basis of the trained data. We discussed the results with the university medical doctor; he was very pleased to see to the result obtained.

Stiction is one of the most common problems in the spring-diaphragm type control valves, which are widely used in the process industry. In this paper, a procedure for single curve piecewise fitting stiction detection method and quantifying valve stiction in control loops based on ant colony optimization has been proposed. The single curve piecewise fitting method of detecting valve stiction is based on the qualitative analysis of the control signals. The basic idea of this method is to fit two different functions, triangular wave and sinusoidal wave, to the controller output data. The calculation of stiction index (SI) is introduced based on the proposed method to facilitate the automatic detection of stiction. A better fit to a triangular wave indicates valve stiction, while a better fit to a sinusoidal wave indicates nonstiction. This method is time saving and easiest method for detecting the stiction. Ant colony optimization (ACO), an intelligent swarm algorithm, proves effective in various fields. The ACO algorithm is inspired from the natural trail following behaviour of ants. The parameters of the Stenman model estimated using ant colony optimization, from the input–output data by minimizing the error between the actual stiction model output and the simulated stiction model output. Using ant colony optimization, Stenman model with known nonlinear structure and unknown parameters can be estimated.

The design of miniaturized and efficient patch antennas has been a main topic of research in the past two decades. The fractal patch antennas have provided a good solution to this problem. But, in fractal antennas, finding the location of optimum feed point is a very difficult task. In this chapter, a novel method of using GRNN-GA hybrid model is presented to find the optimum feed location. The results of this hybrid model are compared with the simulation results of IE3D which are in good agreement.

In order to increase the probability of finding optimal solution, GAs must maintain a balance between the exploration and exploitation. Maintaining population diversity not only prevents premature convergence but also provides a better coverage of the search space. Diversity measures are traditionally used to analyze evolutionary algorithms rather than guiding them. This chapter discusses the applicability of updation phase of binary trie coding scheme [BTCS] in introducing as well as maintaining population diversity. Here, the robustness of BTCS is compared with informed hybrid adaptive genetic algorithm (IHAGA), which works by adaptively changing the probabilities of crossover and mutation based on the fitness results of the respective offsprings in the next generation.

Vehicle routing problem with time window constraints (VRPTW) is an extension of the original vehicle routing problem (VRP). It is a well-known NP-hard problem which has several real-life applications. Meta-heuristics have been often tried to solve VRTPW problem. In this paper, an attempt has been made to develop a suitable version of Ant colony optimization heuristic to efficiently solve VRPTW problem. Experimentation with the developed version of Ant colony optimization has shown that it succeeds in general in obtaining results obtained with earlier version and often even better than the results that are better than the corresponding results available in literature which have been obtained using even previously developed hybridized versions of ACO. In many cases, the obtained results are comparable with the best results available in literature.

In this paper, we propose an energy saving model for sensor network by finding the optimal path for data transmission using ant colony optimization (ACO) algorithm. The proposed model involves (1) developing a relational model based on the correlation among sensors both in spatial and in temporal dimensions using DBSCAN clustering, (2) identifying a set of sensors which represents the network state, and (3) finding the best path for transmission of data using ACO algorithm. Experimental results show that the proposed model reduces the energy consumption by reducing the amount of data acquiring and query processing using the representative sensors and ensures that the transmission is done on the best path which minimizes the probability of retransmission of data.

The main aim of this chapter is to obtain optimal gains for a PID controller using multi-objective genetic algorithm used in a coupled-tank liquid-level control system. Liquid level control system is a nonlinear system and finds a wide application in petrochemical, food processing, and water treatment industries, and the quality of control directly affects the quality of products and safety. This chapter employs the use of multi-objective genetic algorithm for the optimization of the PID gains for better plant operations in contrast to conventional tuning methods and GA. The simulations indicate that better performance is obtained in case of multi-objective genetic algorithm-optimized PID controller.

In this paper, an interval type-2 fuzzy logic controller (IT2FLC) is proposed for thyristor-controlled series capacitor (TCSC) to improve power system damping. It has been tested on the single-machine infinite-bus (SMIB) system. The proposed controller performance is compared with particle swarm optimization (PSO) and type-1 fuzzy logic controller (T1FLC)-based TCSC. In this problem, the PSO algorithm is applied to find out the optimal values of parameters of lead-lag compensator-based TCSC controller. The comparative performance is analyzed based on the simulation results obtained for rotor speed deviation and power angle deviation plot, and it has been found that for damping oscillations of SMIB system, the proposed IT2FLC is quite effective. The proposed controller is also robust subjected to different operating conditions and parameter variation of the power system.

In this paper, we give a solution for the segmentation problem using membrane computing techniques. There is an important difference with respect to the solution presented in Christinal et al. [6], we use multiple membranes. Hence, the parallel behavior of the algorithm with respect to the previous works has been improved.

Hardware/software partitioning is a common method used to reduce the design complexity of a reconfigurable system. Also, it is a major critical issue in hardware/software co-design flow and high influence on the system performance. This paper presents a novel method to solve the hardware/software partitioning problems in dynamic partial reconfiguration of system-on-chip (SoC) and observes the common traits of the superior contributions using genetic algorithm (GA). This method is stochastic in nature and has been successfully applied to solve many non-trivial polynomial hard problems. It is based on the appropriate formulation of a general system model, being therefore independent of either the particular co-design problem or the specific partitioning procedure. These algorithms can perform decomposition and scheduling of the target application among available computational resources at runtime. The former have been entirely proposed by the authors in previous works, while the later have been properly extended to deal with system-level issues. The performance of all approaches is compared using benchmark data provided by MCNC standard cell placement benchmark netlists. This paper has shown the solution methodology in the basis of quality and convergence rate. Consequently, it is extremely important to choose the most suitable technique for the particular co-design problem that is being confronted.

School bus routing involves transporting students from predefined locations to school using a fleet of buses with varying capacity. This paper describes a real-life problem of the school bus routing. The overall goal of this study is to develop a route plan for the school bus service so that it is able to serve the students in an efficient and economical manner with maximum utilization of the capacity of buses using hybrid genetic algorithm.

Quantum-inspired evolutionary algorithms (QEAs) have been successfully used for solving search and optimization problems. QEAs employ quantum rotation gates as variation operator. The selection of rotation angles in the quantum gate has been mostly performed intuitively. This paper presents tuning of the parameters by designing experiments using well-known Taguchi’s method with massively multimodal deceptive problem as the benchmark.

In this chapter, a novel dimensionality reduction method, based on fuzzy rough sets, is presented, which simultaneously selects attributes and extracts features using the concept of feature significance. The method is based on maximizing both relevance and significance of the reduced feature set, whereby redundancy therein is removed. The chapter also presents classical and neighborhood rough sets for computing relevance and significance of the feature set and compares their performance with that of fuzzy rough sets based on the predictive accuracy of nearest neighbor rule, support vector machine, and decision tree. The effectiveness of the proposed fuzzy rough set-based dimensionality reduction method, along with a comparison with existing attribute selection and feature extraction methods, is demonstrated on real-life data sets.

This article presents a fuzzy programming (FP) method for modeling and solving bilevel stochastic decision-making problems involving fuzzy random variables (FRVs) associated with the parameters of the objectives at different hierarchical decision-making units as well as system constraints. In model formulation process, an expectation model is generated first on the basis of the fuzzy random variables involved with the objectives at each level. The problem is then converted into a FP model by considering the fuzzily described chance constraints with the aid of applying chance constrained methodology in a fuzzy context. After that, the model is decomposed on the basis of tolerance ranges of fuzzy numbers associated with the parameters of the problem. To construct the fuzzy goals of the decomposed objectives of both decision-making levels under the extended feasible region defined by the decomposed system constraints, the individual optimal values of each objective at each level are calculated in isolation. Then, the membership functions are formulated to measure the degree of satisfaction of each decomposed objectives in both the levels. In the solution process, the membership functions are converted into membership goals by assigning unity as the aspiration level to each of them. Finally, a fuzzy goal programming model is developed to achieving the highest membership degree to the extent possible by minimizing the under deviational variables of the membership goals of the objectives of the decision makers (DMs) in a hierarchical decision-making environment. To expound the application potentiality of the approach, a numerical example is solved.

The travelling salesman problem (TSP) is one of the most sought out NP-hard, routing problems in the literature. TSP is important with respect to some real-life applications, especially when tour is generated in real time. The objective of this paper is to apply the intelligent water drops algorithm to solve graph-based TSP (GB-TSP). The intelligent water drops (IWD) algorithm is a new meta-heuristic approach belonging to a class of swarm intelligence-based algorithm. It is inspired from observing natural water drops that flow in rivers. The idea of path finding of rivers is used to find the near-optimal solution of the travelling salesman problem (TSP).

The intelligent water drops (IWD) algorithm was introduced by Hamed Shah Hosseini in 2007, which has been used to solve some of the discrete optimization problems. This chapter introduces a simplified version of the basic IWD algorithm and uses it to find the global minimum of some of the complex mathematical functions. The parameter settings have a very important role in the efficiency of the algorithm. The results demonstrated that the simplified IWD algorithm gave better results as compared to other techniques in less number of iterations.

In this paper, we proposed a new ranking method for intuitionistic fuzzy numbers (IFNs) by using centroid and circumcenter of membership function and non-membership function of the intuitionistic fuzzy number. The method utilizes the midpoint of the circumcenter of membership and non-membership function of intuitionistic fuzzy number to define the ranking function for IFN satisfying the general axioms of ranking functions. The developed method has been illustrated by some examples and is compared with some existing ranking method to show its suitability.

In the paper, we give a new method for solution of multi-objective linear programming problem in intuitionistic fuzzy environment. The method uses computation of the upper bound of a non-membership function in such way that the upper bound of the non-membership function is always less than the upper bound of the membership function of intuitionistic fuzzy number. Further, we also construct membership and non-membership function to maximize membership function and minimize non-membership function so that we can get a more efficient solution of a probabilistic problem by intuitionistic fuzzy approach. The developed method has been illustrated on a problem, and the result has been compared with existing solutions to show its superiority.

In an attempt to study the success factors for the competitiveness of machine tool manufacturing (MTM) industry an in-depth study of 10 manufacturers located in India was carried out. Performance measures, especially which are related to supply chain (SC) activities, are also the part of competitive priorities [

16

,

17

]. It can be seen that systematic identification and prioritization of SC performance indicators would help managers to integrate them into corporate strategy. An ANP approach is used to analyze the dynamic, large, and complex attribute decision. To perform the related computations, a programming platform of

$$\text {MATLAB}^\text {TM }$$

MATLAB

TM

software suite was operated. Research findings unveiled that flexibility and quality dimensions are of foremost significance in the development of sector under study, followed by delivery indicators. However, the companies believed that cost constituents need to be focused to achieve overall SC competitiveness.

A Gaussian prime is a Gaussian integer that cannot be expressed in the form of the product of other Gaussian integers. The concept of Gaussian integer was introduced by Gauss [

4

] who proved its unique factorization domain. In this paper, we propose a modified RSA variant using the domain of Gaussian integers providing more security as compared to the old one.

Many modeling studies that aimed at providing an accurate relationship between the software project effort (or cost) and the involved cost drivers have been conducted for effective management of software projects. However, the derived models are only applicable for a specific project and its variables. In this chapter, we present the use of back-propagation neural network (NN) to model the software development (SD) effort of 18 SD NASA projects based on six cost drivers. The performance of the NN model was also compared with a multi-regression model and other models available in the literature.

In the present investigation, we introduce a class of

$$\alpha $$

α

-convex multivalent functions defined by generalized Ruscheweyh derivatives introduced by Goyal and Goyal (J. Indian Acad. Math. 27(2):439–456, 2005) which involves a generalized fractional differential operator. The necessary and sufficient condition for functions to belong to this class is obtained. We study properties of this class and derive a theorem about image of a function from this class through generalized Komatu integral operator. Also, the integral representation for the functions of this class has been obtained.

Here, we consider a network, whose arc lengths are intervals or triangular fuzzy numbers. A new comparison technique based on the expected value of intervals and triangular fuzzy numbers is introduced. These expected values depend on a parameter which reflects the optimism/pessimism level of the decision-maker. Moreover, they can be used for negative intervals or triangular fuzzy numbers.

The main aim of this paper is to prove some fixed point theorems in fuzzy metric spaces through rational inequality. Our results extend and generalize the results of many other authors existing in the literature. Some applications are also given in support of our results.

Process fault detection concerns itself with monitoring process variables and identifying when a fault has occurred in the process workflow. Sophisticated learning algorithms may be used to select the relevant process state variables out of a massive search space and can be used to build more efficient and robust fault detection models. In this study, we present a recently proposed swarm intelligence-based hybrid intelligent water drop (IWD) optimization algorithm in combination with support vector machines and an information gain heuristic for selecting a subset of relevant fault indicators. In the process, we demonstrate the successful application and effectiveness of this swarm intelligence-based method to variable selection and fault identification. Moreover, performance testing on standard machine learning benchmark datasets also indicates its viability as a strong candidate for complex classification and prediction tasks.

Fuzzy logic controls and neuro-fuzzy controls are accustomed to increase the performance of air conditioning system. In this paper, we are trying to provide the new design air conditioning system by exploitation two logics, namely fuzzy logic and neuro-fuzzy management. This paper proposes a set of rule and uses 2 inputs specifically temperature and humidness and 4 outputs specifically compressor speed, fan speed, fin direction and mode of operation. These outputs are rule-based output. At last, compare simulation results of each system exploitation fuzzy logic and neuro-fuzzy management and notice the higher output.

Optimizing the operations of a multi-reservoir systems are complex because of their larger dimension and convexity of the problem. The advancement of soft computing techniques not only overcomes the drawbacks of conventional techniques but also solves the complex problems in a simple manner. However, if the problem is too complex with hardbound variables, the simple evolutionary algorithm results in slower convergence and sub-optimal solutions. In evolutionary algorithms, the search for global optimum starts from the randomly generated initial population. Thus, initializing the algorithm with a better initial population not only results in faster convergence but also results in global optimal solution. Hence in the present study, chaotic algorithm is used to generate the initial population and coupled with genetic algorithm (GA) to optimize the hydropower production from a multi-reservoir system in India. On comparing the results with simple GA, it is found that the chaotic genetic algorithm (CGA) has produced slightly more hydropower than simple GA in fewer generations and also converged quickly.

In this paper, a new reliable algorithm based on homotopy perturbation method using Laplace transform, named homotopy perturbation transform method (HPTM), is proposed to solve nonlinear fractional Harry Dym equation. The numerical solutions obtained by the HPTM show that the approach is easy to implement and computationally very attractive.

This paper describes fused floating point add–subtract operations and which is applied to the implementation of fast fourier transform (FFT) processors. The fused operations of an add–subtract unit which can be used both radix-2 and radix-4 butterflies are implemented efficiently with the two fused floating point operations. When placed and routed using a high-performance standard cell technology, the fused FFT butterflies are about may be work fast and gives user-defined facility to modify the butterfly’s structure. Also the numerical results of the fused implementations are more accurate, as they use rounding modes is defined as per user requirement.

In this paper, a user-friendly algorithm based on new homotopy perturbation transform method (HPTM) is proposed to obtain approximate solution of a time-space fractional cubic nonlinear Schrödinger equation. The numerical solutions obtained by the HPTM indicate that the technique is easy to implement and computationally very attractive.

A graph

G

is super strongly perfect graph if every induced subgraph

H

of

G

possesses a minimal dominating set that meets all the maximal cliques of

H

. In this paper, we have characterized the super strongly perfect graphs on trees. We have presented the results on trees in terms of domination and codomination numbers

$${\upgamma }$$

γ

and

$$\overline{\upgamma }$$

γ

¯

. Also, we have given the relationship between diameter, domination, and codomination numbers in trees.

In this paper, a numerical algorithm based on new homotopy analysis sumudu transform method (HASTM) is proposed to solve a nonlinear boundary value problem arising in the study of thin flow of a third-grade fluid down an inclined plane. The homotopy analysis sumudu transform is a combined form of sumudu transform and homotopy analysis method. The proposed technique finds the solution without any discretization or restrictive assumptions and avoids the round-off errors. The numerical results show that the proposed approach is very efficient and simple and can be applied to other nonlinear problems.

The present work analyzes the buckling and vibration behavior of non-homogeneous orthotropic rectangular plates of variable thickness and subjected to constant in-plane force along two opposite simply supported edges on the basis of classical plate theory. The other two edges may be clamped, simply supported, and free. For non-homogeneity of the plate material, it is assumed that Young’s moduli and density vary exponentially along one direction. The governing partial differential equation of motion of such plates has been reduced to an ordinary differential equation using the sine function for mode shapes between the simply supported edges. This has been solved numerically employing DQM. The effect of various parameters has been studied on the natural frequencies for the first three modes of vibration. Critical buckling loads by allowing frequencies to approach zero have been computed. Comparison has been made with the known results.

The dual part of a SBM model in data envelopment analysis (DEA) aims to calculate the optimal virtual costs and prices (also known as weights) of inputs and outputs for the concerned decision-making units (DMUs). In conventional dual SBM model, the weights are found as crisp quantities. However, in real-world problems, the weights of inputs and outputs in DEA may have fuzzy essence. In this paper, we propose a dual SBM model with fuzzy weights for input and output data. The proposed model is then reduced to a crisp linear programming problem by using ranking function of a fuzzy number (FN). This model gives the fuzzy efficiencies and the fuzzy weights of inputs and outputs of the concerned DMUs as triangular fuzzy numbers (TFNs). The proposed model is illustrated with a numerical example.

Ball bearing plays a very crucial part of any rotating machineries, and the fault diagnosis in rotating system can be detected at early states when the fault is still small. In this paper, a ball bearing fault is detected by using continuous wavelet transform (CWT) with modern algebraic function. The reflected vibration signals from ball bearing having single point defect on its inner race, outer race, ball fault, and combination of these faults have been considered for analysis. The features extracted from a non-stationary multi-component ball bearing signal are very difficult. In this paper, a CWT with selected stretching parameters is used to analyze a signal in time–frequency domain and extract the features from non-stationary multi-component signals. The algebraic function norms are calculated from the matrix which can be generated with the help of wavelet transforms. The norms lookup table is used as a reference for fault diagnosis. The experimental results show that this method is simple and robust.

Many real-life problems arising in science, business, engineering, etc. can be modeled as nonlinear constrained optimization problems. To solve these problems, population-based stochastic search methods have been frequently used in literature. In this paper, a population-based constraint-handling technique C-SOMGA is used to solve six engineering optimization problems. To show the efficiency of this algorithm, the results are compared with the previously quoted results.

The technocrats put their efforts regularly to minimize the total cost/budget of transportation problem. However, the proper effort has not been put for minimizing the total cost of trans-shipment problem. A goal programming approach has been developed to obtain the minimum budget for trans-shipment problem. The trans-shipment problem is regarded as the extended transportation problem and hence be solved by the transportation techniques. In the present algorithm, trans-shipment problem is transferred to suitable transportation problem and further modified as a proper goal programming problem. The priorities of goal programming explore the wider impact for decision maker. Therefore, the solution obtained is more suitable for decision makers. Hence, it is widely acceptable for any organization. At the end, a numerical example is solved in support of the procedure.

Goal programming (GP) has been proven a valuable mathematical programming form in a number of venues. GP model serves a valuable purpose of cross-checking answers from other methodologies. Different software packages are used to solve these GP models. Likewise, multiple regression models can also be used to more accurately combine multiple criteria measures that can be used in GP model parameters. Those parameters can include the relative weighting and the goal constraint parameters. A comparative study on the solutions using TORA, LINDO, and least square method has been made in this paper. The objective of this paper is to find out a method that gives most accurate result to a nonlinear multiple regression model.

The purpose of the present investigation is to derive several Fekete–Szegö-type coefficient inequalities for certain subclasses of normalized analytic function

$$f(z)$$

defined in the open unit disk. Various applications of our main results involving (for example) the operators defined using generalized fractional differential operator are also considered. Thus, as one of these applications of our result, we obtain the Fekete–Szegö-type inequality for a class of normalized analytic functions, which is defined here by means of the convolution and the fractional differential operators.

The present chapter pertains to a bi-objective scheduling on parallel machines involving total tardiness and number of tardy jobs (NT). The processing time of jobs are uncertain in nature and are represented by triangular fuzzy membership function. The objective of the chapter is to find the optimal sequence of jobs processing on parallel identical machines so as to minimize the secondary criteria of NT with the condition that the primary criteria of total tardiness remains optimized. The bi-objective problem with total tardiness and NT as primary and secondary criteria, respectively, for any number of parallel machines is NP-hard. Following the theoretical treatment, a numerical illustration has also been given to demonstrate the potential efficiency of the proposed algorithm as a valuable analytical tool for the researchers.

Holding costs are determined from the investment in physical stocks and storage facilities for items during a cycle. In most of the research papers, holding cost rate per unit time for perishable inventory is assumed as constant. However, this is not necessarily the case when items in stock are decaying. In this work, paying better attention on the holding cost, we present a deteriorating inventory model in which the unit holding cost is continuously based on the deterioration of the inventory with the time the item is in stock. The deterioration rate is assumed as a Weibull distribution function. Declining market demand is considered in this paper. Shortages are allowed and partial backlogged. The partial backlogging rate is a continuous exponentially decreasing function of waiting time in purchasing the item during stock out period. Conditions for uniquely existence of global minimum value of the average total cost per unit time are carried out. Numerical illustration and sensitivity analysis are presented.

Owing to its strategic implications, reverse logistics has received much attention in recent years. Growing green concerns and advancement of reverse logistics concepts make it all the more relevant who can be achieved through the End-of-Life (EoL) treatment. In the proposed model, we develop a production inventory model with the reverse flow of the material. Here we determined the value of product life cycle with EoL scenario where the reverse logistics operations deal with the collection, sorting, cleaning, dissembling, and remanufacturing of the buyback products. The purpose of this paper is to develop an effective and efficient management of product remanufacturing. As a result, in this article, we establish a mathematical formulation of the model to determine the optimal payment period and replenishment cycle. Illustrative examples, which explain the application of the theoretical results as well as their numerical verifications, are also given. Finally, the sensitivity analysis is reported.

We develop an inventory model with time-dependent demand rate and deterioration, allowing shortages. The production rate is assumed to be finite and proportional to the demand rate. The shortages are partially backlogged with time-dependent rate. Inflation is also taken in this model. Inflation plays a very significant role in inventory policy. We developed the model in both fuzzy and crisp sense. The model is solved logically to obtain the optimal solution of the problem. It is then illustrated with the help of numerical examples. Sensitivity of the optimal solution with respect to changes in the values of the system parameters is also studied.

In this article, an inventory model is developed to deal with the impreciseness present in the market demand and the various cost parameters. The presented model is developed in crisp and fuzzy environments. Signed distance method is used for defuzzification. In most of the classical models, constant demand rate is considered. But in practice purchasing deeds of the customers is affected by the selling price and inventory level. In this study, we have considered demand rate as a function of stock-level and selling price. Two parameters Weibull distribution deterioration is considered. It is assumed that shortages are allowed and are partially backordered with the time dependent backlogging rate. A numerical experiment is provided to illustrate the problem. Sensitivity analysis of the optimal solution with respect to the changes in the value of the system parameters is also discussed.

Mobile ad hoc network is prone to denial of service attack. Jellyfish is a new denial of service attack and is categorized as JF Reorder Attack, JF Periodic Dropping Attack, JF Delay Variance Attack. In JF Periodic Dropping Attack, intruder node intrudes into forwarding group and starts dropping packets periodically. Due to JF Periodic Dropping attack, the delay in the network increases and throughput decreases. In this paper a comparative performance analysis of three reactive routing protocols i.e. AODV, DSR and TORA used in mobile ad hoc network under JF Periodic Dropping attack is done. This work is specially done for multimedia transmission i.e. video and voice. If we have a mobile ad hoc network in which probability of occurrence of JF Periodic Dropping attack is high and also if it requires time efficient network multimedia service for information exchange then TORA protocol is to be chosen. If it requires high multimedia throughput and consistent service in the network then AODV protocol is recommended. An algorithm has been proposed depending upon the analysis done particularly for multimedia transmission in MANET which will help in choosing the best suited protocol for the required network parameters under JF Periodic Dropping attack.

With the introduction of Critical chain by Goldratt in 1997, there has been a lot of research in the field of resource constraint project scheduling problems (RCPSP) and Buffer Sizing techniques. This paper suggests a Buffer management technique which aims at reducing the make span time yet maintaining the stability of the project. In the theory of CCPM it is suggested to reduce the duration of all the activities by half to remove the excess safety time in each activity. The trimmed duration is collected and made available at the end of the project in the form of project buffer which could be used if the project gets delayed. Another buffer called the feeding buffer is added whenever a noncritical chain joins a critical chain. This increases the project duration if the slack of the last activity in the feeding chain is smaller than the feeding buffer. In such cases, this paper suggests the division of the project buffer into parts, fitting each part at the junction of critical and noncritical chains so that the delay occurred because of addition of feeding buffer can be utilized and the duration of project buffer is shortened. The use of the proposed technique has reduced the project duration by a significant value.

Technological changes have occurred at an exponential rate in recent years leading to the generation of large amount of data in various sectors. Several database and data warehouse is built to store and manage the data. As we know the data which are relevant to us should be extracted from the database for our task. Earlier different mining approaches are proposed in which items are collected at same minimum support value. In this paper we propose a fuzzy data mining algorithm which generates the fuzzy association rules from time series data having different minimum support values. The temperature varying dataset is used to generate fuzzy rules. The proposed algorithm also predicts the variation of temperature. Experiments are also performed to get the desired result.

The aim of this paper is to gain insights into how process dynamics can affect control configuration decision based on relative gain array (RGA) analysis in the face of model uncertainty. Analytical expressions for worst-case bounds of uncertainty in steady-state and dynamic RGA are derived for two inputs two outputs (TITO) plant models. A simulation example which has been used in several prior studies is considered here to demonstrate the results. The obtained bounds of uncertainty in RGA provide valuable information pertaining to the necessity of robustness and accuracy in the model of decentralized multivariable systems.

With evasion of digital convergence [

1

], computing has by and large pervaded into our environment. WWW has enhanced day-to-day life by utilizing information such as Location awareness, User-context awareness; touch API, mutation observer [

2

], and many more. The future [

3

] trends in ubiquitous computing [

4

] provide a great scope for innovation and value-added services. With approach of “computing being embedded,” the future sees its usage more pervasive and appealing. Web is evolving and so are supporting technologies (in terms of hardware technologies). Many real-life examples including augmented-reality, wearable technologies, gesture-based recognition systems, etc., are already in place illustrating its high-end usage. Such diverse future targeting billions of people and devices need streamlined approach. Some steps have already been taken care by World Wide Web consortium (W3C) to provide standards relating to API usage. In this paper, we highlight various aspects of web-ubiquitous computing and how they can be dealt w.r.t to their implementation.

In remote sensing noise is some kind of ambiguous data that occurs due to some inadequacy in the sensing, digitization or data recording process. This paper examines the effect of noise clustering algorithm of image classification. In remotely sensed data the easiest and usual assumption is that each pixel represents a homogeneous area on the ground. However in real world, it is found to be heterogeneous in nature. For this reason, it has been proposed that fuzziness should be accommodated in the classification procedure and preserves the extracted information. Classification of satellite images are complex process and accuracy of the output is dependent on classifier parameters. This paper examines the effect of various parameters like weighted exponent ‘

m

’ as well as resolution parameter ‘

$$\partial $$

∂

’ for noise clustering (NC) classifier. The prime focus in this work is to select suitable parameters for classification of remotely sensed data which improves the accuracy of classification output to study the behaviour of associated learning parameters for optimization estimation using noise clustering classifier. A concept of “Noise Cluster” is introduced such that noisy data points may be assigned to the noise class. In this research work it has been tried to generate, a fraction outputs of noise clustering based classifier. The remote sensing data used has been from AWiFS, LISS-III and LISS-IV sensors of IRS-P6 satellite. This study proposes the entropy, as a special criterion for visualising and evaluating the uncertainty and it has been used as an absolute uncertainty indicator from output data. From the resultant aspect, while monitoring entropy of fraction images for different values, optimum weighting exponent ‘

m

’ and resolution parameter ‘

$$\partial $$

∂

’ has been obtained for AWIFS, LIIS-III and LISS-IV images and that is ‘

m

’

$$\,=\,$$

=

2.9 and ‘

$$\partial $$

∂

’

$$\,=\,$$

=

$$10^{6}$$

10

6

, providing highest degree of membership value with minimum entropy value as shown in Table

1

.

Location management is an important and complex issue in mobile computing. Location management problem can be solved by partitioning the network into location areas such that the total cost, i.e., sum of handoff (update) cost and paging cost is minimum. Finding the optimal number of location areas and the corresponding configuration of the partitioned network is NP-complete problem. In this paper, we present two swarm intelligence algorithms namely genetic algorithm (GA) and artificial bee colony (ABC) to obtain minimum cost in the location management problem. We compare the performance of the swarm intelligence algorithms and the results show that ABC give better optimal solution to locate the optimal solution.

This paper will extensively dictate the whole basic details of fingerprint and its techniques. Moreover one of the most important and widely used techniques that is minutiae point extraction technique is also covered in detail. The minutiae points are extracted with the help of cross-number algorithm. Cross-number algorithm also helps for the rejection of false minutiae point’s extraction

Pulp and paper industry plays an important role in Indian as well world economy. These are large scale process industries working round the clock. The focus of the present paper is on optimization problems encountered in pulp and paper industries. Different areas where optimization has been applied are identified and methods available for dealing with such problems are discussed.

In the developing economy like India Micro, Small and Medium Enterprises (MSMEs) play a very important role as they are the engines of growth in development, upliftment, and transition of economy to the next level. The MSME’s in India have played a critical role in generation of employment, providing goods and services at affordable costs by offering innovative solutions in very unstructured and unorganized manner. With the increase in the growing competition and its complexity it is essential for today’s business enterprises to work in structured manner by changing its functioning environment dynamically by integrating internal information resourses to the platform of ERP systems which will assist in optimizing potential of utilizing resources efficiently and determining growth. Moreover, with the exponential growth of Internet technology and the emergence of e-business, MSME’s can unify the external information resources with internal functional areas within an organization. Use of e-commerce solutions will help enterprises to expand their business through broader product exposure, better customer service, accurate order entry processes and faster product fulfillment. It is expected that in MSME’s implementation of an ERP system can facilitate an e-business effort of an organization to optimize its overall functioning. In order to serve as a platform for e-business, it is essential that an ERP system must also be able to be extended to support a range of external constituents for a firm. This paper focuses on that how the challenges faced by MSME’s can be overcome by implementing ERP system in an organisation with the efficient integration of e-commerce to optimize its functioning. Further, the paper will highlight the add-on benefits to the companies for using integrated e-commerce platforms with ERP systems. The paper is based on the in-depth study of publically available information collected from the published articles, journals, reports, websites, blogs, and academic literatures in context with the economy of India.

Disassembly operations are inevitable elements of product recovery with the disassembly line as the best choice to carry out the same. The product recovery operations are fully based on disassembly line balancing and because of this, disassembly lines have become the chaise of automated disassembly of returned product. It is difficult to find the optimal balance of a disassembly line because of its N-P hard nature. In this paper a new heuristic is proposed to assign the parts to the disassembly workstations under AND/OR precedence constraints. The heuristic solutions are known as intrinsically optimal/suboptimal solutions of the N-P hard problems. The solution obtained by proposed heuristic has been compared with other heuristic solutions. The heuristic tries to minimize the number of workstations and the cycle time of the line while addressing the different criteria. The methodology of the proposed heuristics has been illustrated with the help of examples and it has been observed that the heuristic generates significantly better result.

This paper introduces and incorporates the concept of rework in modelling of a merge production system under random conditions. Merge and split production stages are common in assembly lines. Merging of components can be performed correctly or otherwise. If not done properly, a merging operation can be redone, i.e. the merging operation can be reworked. This paper explains the modelling of a two stage merge production system subject to rework using semi-regenerative stochastic processes. The modelling has been done to obtain various busy period durations over finite time duration for transient state analysis. Also, the modelling and analysis has been carried out without any particular assumption on the distributions of processing times. All the processing times involved have been assumed to be arbitrarily distributed.

In this paper, a fast and robust Shape from Shading (SfS) algorithm by iterative marching with corrections criterion under oblique light source is presented. Usually, SfS algorithms are based on the assumption that image radiance is a function of normal surface alone. SfS algorithms solve first-order nonlinear Hamilton Jacobi equation called image irradiance equation. Both Fast Marching Method (FMM) and Marching with Correctness Criterion (MCC) basically work for the frontal light illumination direction, in which the image irradiance equation is an Eikonal equation. The problem task is to recover the surface from the image—which amounts to finding a solution to the Eikonal equation. FMM copes better the image irradiance iteratively under oblique light sources with the cost of computational complexity

$$O(N log N)$$

. One prominent solution is the Marching with MCC of Mauch which solves the Eikonal equation with computational complexity

$$O(N)$$

. Here, we present a new iterative variant of the MCC which copes better with images taken under oblique light sources. The proposed approach is evaluated on two synthetic real images and compared with the iterative variant of FMM. The experimental results show that the proposed approach, iterative variant of MCC is more efficient than the iterative variant of FMM.

Tracking of an object in a scene, especially through visual appearance is weighing much relevance in the context of recent research trend. In this work, we are extending the one of the approaches through which visual features are erected to reveal the motion of the object in a captured video. One such strategy is a mean shift due to its unfussiness and sturdiness with respect to tracking functionality. Here we made an attempt to judiciously exploit the tracking potentiality of mean shift to provide elite solution for various applications such as object tracking. Subsequently, in view of proposing more robust strategy with large pixel grouping is possible through mean shift. The mean shift approach has utilized the neighborhood minima of a similarity measure through bhattacharyya coefficient (BC) between the kernel density estimate of the target model and candidate. However, similar capability is quite possible through color coherence vectors (CCV). The CCV are derived in addition to color histogram of target model and target candidate. Further, joint histogram of color model and CCV is added. Thus, the resultant histograms are empirically less sensitive to variance of background which is not ensured through traditional mean shift alone. Experimental results proved to be better and seen changes in tracking especially in similar color background. This work explores the contribution and paves the way for different applications to track object in varied dataset.

Assessment of student performance is one of the important tasks in the teaching and learning process. It has great impact on the student approach to learning and their outcomes. Evaluation of student learning in different activities is the process of determining the level of performance of students in relation to individual activities. A rubric is a systematic scoring guideline to evaluate student performance (assignment, quiz, paper presentation, open and closed book test etc.) through the application of detailed description of performance standards. After giving the specific task the student should be explained about the criteria and evaluation points. This allows the students to be aware of the performance and they will try to improve the performance. In this paper the main focus is on student centered learning activities which are mainly based on multiple intelligences. This paper presents an integrated fuzzy set approach Lotfi et al. [2] to assess the outcomes of student-centered learning. It uses fuzzy set principles to represent the imprecise concepts for subjective judgment and applies a fuzzy set method to determine the assessment criteria and their corresponding weights.

In this paper, a method of representing shape of medicinal plant leaves in terms of interval-valued type symbolic features is proposed. Axis of least inertia of a shape and the fuzzy equilateral triangle membership function is exploited to extract features for shape representation. Multiple class representatives are used to handle intra class variations in each species and the concept of clustering is used to choose multiple class representatives. A simple nearest neighbor classifier is used to perform the task of classification. Experiments are conducted on the standard flavia leaf dataset to demonstrate the efficacy of the proposed representation scheme in classifying medicinal plant leaves. Results of the experiments have shown that the method is effective and has achieved significant improvement in classification accuracy when compared to the contemporary work related to leaf classification.

The main advantage of image compression is the rapid transmission of data. The conventional compression techniques exploit redundancy in images that can be encoded. The main idea is to remove redundancies when the image is to be stored and replace it back when the image is reconstructed. But the compression ratio of this technique is quite insignificant, and hence is not a suitable candidate for an efficient encoding technique. Other methods involve removing high frequency Fourier coefficients and retaining low frequency ones. This method uses discrete cosine transforms(DCT) and is used extensively in different flavors pertaining to the JPEG standards. Fractal compression provides resolution-independent encoding based on the contractive function concept. This concept is implemented using attractors (seed) that are encoded/copied using affine transformations of the plane. This transformation allows operations such as, skew, rotate, scale, and translate an input image which is in turn is extremely difficult or impossible to perform in JPEG images without having the problem of pixelization. Further, while decoding the fractal image, there exist no natural size, and thus the decoded image can be scaled to any output size without losing on the detail. A few years back fractal image was a purely a mathematical concept but with availability of cheap computing power like graphical processor units (GPUs) from Nvidia Corporation its realization is now possible graphically. The fractal compression is implemented using MatLab programming interface that runs on GPU clusters. The GPUs consist of many cores that together give a very high computing speed of over 24 GFLOPS. The advantage of fractal compression can have varied usage in satellite surveillance and reconnaissance, medical imaging, meteorology, oceanography, flight simulators, extra-terrestrial planets terrain mapping, aircraft body frame design and testing, film, gaming and animation media, and besides many other allied areas.

Gait biometrics is one of the non-cooperative biometrics traits particularly in the situation of video surveillance. In the proposed method human knowledge is combined with gait information to get the better recognition performance. Here, individual contributions of different human components, namely head, arm, trunk, thigh, front-leg, back-leg and feet are numerically analyzed. The performance of the proposed method is evaluated by experimentally with CASIA dataset B and C. The effectiveness and impact of seven human gait components is analyzed by using Average Silhouette Image (ASI) under wide range of circumstances.

Steganography is different from Cryptography, Steganography is the process of hiding the information so that no one will try to decrypt the information, where as in Cryptography it is obvious that the message is encrypted, so that any one will try decrypting the message. In this paper, we are suggesting new methods to improve the security in data hiding, perhaps by combining steganography and cryptography. In this work, we propose a new encryption method that provides the cipher text as the same size of the plain text. We also presented an extensive classification of various steganographic methods that have used in the field of Data Security. We analyze both security and performance aspects of the proposed methods by PSNR values and proved that in the cryptographic point of view. The proposed method is feasible in such a way that it makes to intricate the steganalyst to retrieve the original information from the Stego-image even if he detect the presence of digital steganography. An embedded message in this method is perceptually indiscernible under normal observation and thus our proposed method achieves the imperceptibility. The volume of data or message to be embedded in this method is comparatively large and proved in Experimental Results hence the high capacity is also achieved.

An effective unsupervised method (TDAC) is proposed for identification of biologically relevant co-expressed patterns. Effectiveness of TDAC is established in comparison to its other competing algorithms over four publicly available benchmark gene expression datasets in terms of both internal and external validity measures.

The gene classification problem is still active area of research because of the attributes of the genome data, high dimensionality and small sample size. Furthermore, the underlying data distribution is also unknown, so nonparametric methods must be used to solve such problems. Learning techniques are efficient in solving complex biological problems due to characteristics such as robustness, fault tolerances, adaptive learning and massively parallel analysis capabilities, and for a biological system it may be employed as tool for data-driven discovery. In this paper, some concepts related to cognition by examples are discussed. A classification technique is proposed in which DNA sequence is analyzed on the basis of sequence characteristics near breakpoint that occur in leukemia. The training dataset is built for supervised classifier and on the basis of that back propagation learning classifier is employed on hypothetical data. Our intension is to employ such techniques for further analysis and research in this domain. The future scope and investigation is also suggested.

Images have always been very important in human life because humans are very much adapted in understanding images. Feature points or pixels play very important role in image analysis. These feature points include edge pixels. Edges on the image are strong intensity variations which show the difference between an object and the background. Edge detection is one of the most important operations in image analysis as it helps to reduce the amount of data by filtering out the less relevant information and if edge can be identified, basic properties of object such as area, perimeter, shape, etc can be measured. In this paper, a Sobel-Fuzzy technique using auto-thresholding is proposed by fuzzifying the results of first derivatives of Sobel in

x, y

and

xy

directions. The technique automatically finds the six threshold values using local thresholding. Comparative study has been done on the basis of visual perception and edgel counts. The experimental results show the proposed Sobel-Fuzzy approach is more efficient in comparison to Roberts, Prewitt, Sobel, and LoG and produces better results.

This paper presents new approach Hesitant k-nearest neighbor (HK-nn)-based document classification and numerical results analysis. The proposed classification HK-nn approach is based on hesitant distance. In this paper, we have used hesitant distance calculations for document classification results. The following steps are used for classification: data collection, data pre-processing, data selection, presentation, analysis, classification process and results. The experimental results are evaluated using MATLAB 7.14. The Experimental results show proposed approach that is efficient and accurate compared to other classification approach.

Classification is usually the final and one of the most important steps in most of the tasks involving machine learning, computer vision, etc., for e.g., face detection, optical character recognition, etc. This paper gives a novel technique for estimating the performance of Naïve Bayes Classifier in noisy data. It also talks about removing those attributes that cause the classifier to be biased toward a particular class.

The aim of this study is to compare two supervised artificial neural network models for diagnosing a child with learning disability. Once diagnosed, then a fuzzy expert system is applied to correctly classify the type of learning disability in a child. The endeavor is to support the special education community in their quest to be with the mainstream. The initial part of the paper gives a comprehensive study of the different mechanisms of diagnosing learning disability. Models are designed by implementing two soft computing techniques called Single-Layer Perceptron and Learning Vector Quantization. These models classify a child as learning disabled or nonlearning disabled. Once diagnosed with learning disability, fuzzy-based approach is used further to classify them into types of learning disability that is Dyslexia, Dysgraphia, and Dyscalculia. The models are trained using the parameters of curriculum-based test. The paper proposes a methodology of not only detecting learning disability but also the type of learning disability.

The classification of functional magnetic imaging resonance (fMRI) data involves many challenges due to the problem of high dimensionality, noise, and limited training samples. In particular, mental states classification, decoding brain activation, and finding the variable of interest by using fMRI data was one of the focused research topics among machine learning researchers during past few decades. In the context of classification, algorithms have biases, i.e., an algorithm perform better in one dataset may become worse in other dataset. To overcome the limitations of individual techniques, hybridization or fusion of these machine learning techniques proposed in recent years which have shown promising result and open up new direction of research. This paper reviews the hybrid machine learning techniques used in cognitive classification by giving proper attention to their performance and limitations. As a result, various domain specific techniques are identified in addition to many open research challenges.

Today cloud computing is well-known for touching all periphery of technology with its on-demand and elastic capability. Ever since it has come into picture, security has remained a major concern. VM model is already known to be vulnerable to various issues. We introduce Tus-Man protocol which will act in addition to existing system to make computing secure enough for both service provider as well as service consumers. In this protocol, we suggest a tunnel-based protocol to make data transfer not only secure but also safe enough against any malicious attack.

The collection of poems is ever increasing on the Internet. Therefore, classification of poems is an important task along with their labels. The work in this paper is aimed to find the best classification algorithms among the K-nearest neighbor (KNN), Naïve Bayesian (NB) and Support Vector Machine (SVM) with reduced features. Information Gain Ratio is used for feature selection. The results show that SVM has maximum accuracy (93.25 %) using 20 % top ranked features.

Data stream classification is challenging process as it involves consideration of many practical aspects associated with efficient processing and temporal of the stream. Two such aspects which are well studied and addressed by many present data stream classification techniques are infinite length and concept drift. Another very important characteristic of data streams, namely, concept-evolution is rarely being addressed in literature. Concept-evolution occurs as a result of new classes evolving in the stream. Handling concept evolution involves detecting novel classes and training the model with the same. It is a significant technique to mine the data where an important class is under-represented in the training set. This paper is an attempt to study and discuss the technique to handle this issue. We implement one of such state-of-art techniques and also modify for better performance.

Random forest is an ensemble supervised machine learning technique. The principle of ensemble suggests that to yield better accuracy, the base classifiers in the ensemble should be diverse and accurate. Random forest uses decision tree as base classifier. In this paper, we have done theoretical and empirical comparison of different split measures for induction of decision tree in Random forest and tested if there is any effect on the accuracy of Random forest.

Text classification is used to organize documents in a predefined set of classes. It is very useful in Web content management, search engines; email filtering, etc. Text classification is a difficult task due to high- dimensional feature vector comprising noisy and irrelevant features. Various feature reduction methods have been proposed for eliminating irrelevant features as well as for reducing the dimension of feature vector. Relevant and reduced feature vector is used by machine learning model for better classification results. This paper presents various text classification approaches using machine learning techniques, and feature selection techniques for reducing the high-dimensional feature vector.

In this paper, we deal with weka-based classification methods for offline handwritten Gurmukhi character recognition. This paper presents an experimental assessment of the effectiveness of various weka-based classifiers. Here, we have used two efficient feature extraction techniques, namely, parabola curve fitting based features, and power curve fitting based features. For recognition, we have used 18 different classifiers for our experiment. In this work, we have collected 3,500 samples of isolated offline handwritten Gurmukhi characters from 100 different writers. We have taken 60 % data as training data and 40 % data as testing data. This paper presents a novel framework for offline handwritten Gurmukhi character recognition using weka classification methods and provides innovative benchmark for future research. We have achieved a maximum recognition accuracy of about 82.92 % with parabola curve fitting based features and the multilayer perceptron model classifier. In this work, we have used C programming language and weka classification software tool. At this point, we have also reported comparative study weka classification methods for offline handwritten Gurmukhi character recognition.

This paper proposes an efficient geometric-based indexing scheme for fingerprints. Unlike other geometric-based indexing schemes, the proposed indexing scheme reduces both memory and computational costs. It has been tested on IITK database containing 2,120 fingerprints of 530 subjects. Correct Recognition Rate is found to be 86.79 % at top 10 best matches. Experiments prove its superiority against well-known geometric-based indexing schemes.

A simple and a common human gait can provide an interesting behavioral biometric feature for robust human identification. The human gait data can be obtained without the subject’s knowledge through remote video imaging of people walking. In this paper we apply a computer vision-based technique to identify a person at various walking speeds, varying from 2 km/hr to 10 km/hr. We attempt to construct a speed invariance human gait classifier. Gait signatures are derived from the sequence of silhouette frames at different gait speeds. The OU-ISIR Treadmill Gait Databases has been used. We apply a dynamic edge orientation histogram on silhouette images at different speeds, as feature vector for classification. This orientation histogram offers the advantage of accumulating translation and orientation invariant gait signatures. This leads to a choice of the best features for gait classification. A statistical technique based on Naïve Bayesian approach has been applied to classify the same person at different gait speeds. The classifier performance has been evaluated by estimating the maximum likelihood of occurrences of the subject.

Structured Query Language (SQL) injection is one of the most devastating vulnerabilities to impact a business, as it can lead to the exposure of sensitive information stored in an application’s database. SQL injection can compromise usernames, passwords, addresses, phone numbers, and credit card details. It is the vulnerability that results when an attacker achieves the ability to influence SQL queries that an application passes to a back-end database. The attacker can often leverage the syntax and capabilities of SQL, as well as the power and flexibility of supporting database functionality and operating system functionality available to the database to compromise the web application. In this article we demonstrate two non-web-based SQL injection attacks one of which can be carried out by executing a stored procedure with escalating privileges. We present XML-based authentication approach which can handle this problem in some way.

The internet has taken its place beside the telephone and the television as on important part of people’s lives. Consumers rely on the internet to shop, bank and invest online shoppers use credit card to their purchases. In electronic commerce, credit card has become the most important means of payment due to fast development in information technology around the world. Credit card will be most consentient way to do online shopping, paying bills, online movie ticket booking, fees pay etc., In case of fraud associated with it is also increasing. Credit card fraud come in several ways, Many techniques use for find out the credit card fraud detection. Hidden markov model (HMM) is the statistical tools for Engineering and scientists to solve various problems. In this project, we model the sequence of operations in credit card transaction processing using a HMM and show how it can be used for the detection of frauds.

Nowadays, e-mail is widely used for communication over Internet. A large amount of Internet traffic is of e-mail data. A lot of companies and organizations use e-mail services to promote their products and services. It is very important to filter out spam messages to save users’ precious time. Machine learning methods plays vital role in spam detection, but it faces the problem of high dimensionality of feature vector. So feature reduction methods are very important for better results from machine learning approaches. In this paper, Principal Component Analysis (PCA), Singular Value Decomposition (SVD), and Information Gain (IG) methods are used for feature reduction. Further, e-mail messages are classified as spam or ham message using seven different classifiers namely Naïve Baysian, AdaBoost, Random Forest, Support Vector Machine, J48, Bagging, and JRip. Comparative study of these techniques is done on TREC 2007 Spam e-mail Corpus with different feature size.

The contribution of stream ciphers to cryptography is immense. For fast encryption, stream ciphers are preferred to block ciphers due to their XORing operation, which is easier and faster to implement. In this paper we present a matrix-based stream cipher, in which a

m

$$\times $$

×

n

binary matrix single handedly performs the work of

m

parallel LFSRs. This can be treated as an equivalent way of generating LFSR-based stream ciphers through sparse matrix-vector multiplication (SpMV). Interestingly the output of the matrix multiplication can otherwise be used as a parallel bit/byte generator, useful for encrypting video streams.

Security and scalability are important issues for secure group communication in a grid environment. Secure communication involves confidentiality and authenticity of the user and the message between group members. To transmit data in a secure way, a secure and authenticated key transfer protocol should be applied. Key transfer protocol needs an entity responsible for user authentication and secures session keys. Recently, many researchers have proposed secure group communication methods based upon various cryptographic techniques. In this paper, we propose a secure key transfer protocol that uses the concepts of soft dipole representation of the image and steganography to establish secure communication between group of authenticated users. Steganography hides the existence of group keys in images. This protocol is more secure as compare to previously proposed encryption based group communication protocols. This protocol uses a centralized entity key management center (KMC). KMC generates the group key using soft dipoles of the images of the group members and broadcast it securely to all the communicating group members.

Discovering the hierarchy of organizational structure can unveil significant patterns that can help in network analysis. In this paper, we used Enron email data which is well-known benchmarked data set for this sort of research domain. We derive a hierarchical structure of organization by calculating the individual score of each person based on their frequency of communication via email using page rank algorithm. After that, a communication graph is plotted that shows power of each individual among themselves. Experimental results showed that this approach was very helpful in identifying primal persons and their persistent links with others over the period of months.

One major issue of cloud computing is developing Service Level Agreement (SLA)-oriented cloud management system, because situations like resource failures may lead to the violation of SLA by the provider. Several research works has been carried out regarding cloud management system were the impact of SLA is not properly addressed in the perspective of resource failure. In order to achieve SLA in such circumstance, a novel-layered architecture of SLA-oriented Cloud Management System (SLAOCMS) is proposed for service provisioning and management which highlight the importance of various components and its impacts on the performance of SLA- based jobs. There are two components such as Task Scheduler and Load Balancer which are introduced in SLA Management Framework to achieve SLA during resource failure. So, an SLA Aware Task Scheduling Algorithm (SATSA) and SLA Aware Task Load Balancing Algorithm (SATLB) are proposed in the above components to improve the performance of SLAOCMS by successfully achieving the SLA’s of all the user jobs. The results of traditional and proposed algorithms are compared in the scenario of resource failure with respect to violations of SLA-based jobs. Moreover, SLA negotiation framework is introduced in application layer for supporting personalized service access through the negotiation between the service consumer and service provider.

After the advancement of the internet technology, user can get any information on tourism. Tourism is the world’s largest and fastest growing industry. It contains so many things like accommodation, food, events, transportation package, etc. So information must be reliable because tourism product is intangible in nature. Customer cannot physically evaluate the service until he/she physically experienced but there are some areas where a greater measure of intelligence is required. The Semantic Web did a lot of work to enhance the Web by enriching its content with semantic data. E-Tourism is a good candidate for such enrichment, since it is an information-based business. In this paper, we are constructing E-Tourism ontology to provide intelligent tourism service. The algorithm is designed to integrate data from different reliable sources and structure properly in tourism knowledge base for efficiently searching the data.

The Hidden Web is a part of the Web that consists mainly of the information inside databases, i.e., anything behind an interactive electronic form (search interfaces), which cannot be accessed by the conventional Web crawlers [

1

,

2

,

8

]. However, there have been well-defined, effective, and efficient methods for accessing Deep Web contents. One of these methods for accessing the Hidden Web employs an approach similar to ‘traditional’ crawling but aims at extracting the data behind the search interfaces or forms residing in databases. The paper brings insight into the various steps, a crawler must perform to access the contents in the Hidden Web. We structure the problem area and analyze what aspects have already been covered by previous research and what needs to be done.

Cloud computing is based on five attributes: multiplexing, massive scalability, elasticity, pay as you go, and self provisioning of resources. In this paper, we describe various cloud computing platforms, models, and propose a new combined and improved framework for Infrastructure as a Service (IAAS) and Platform as a Service (PAAS). As we know, that PAAS Framework has certain desirable characteristics that are important in developing robust, scalable, and hopefully portable applications like separation of data management from the user interface, reliance on Cloud Computing standards, an Integrated Development Environment, Life cycle management tools but it also has some drawbacks like the PAAS platform such as in Google Application engine, a large number of web servers catering to the platform are always running. This paper proposes an architecture which combines IAAS and PAAS framework and remove the drawbacks of IAAS and PAAS and describes how to simulate the cloud computing key techniques such as data storage technology (Google file system), data management technology, Big Table as well as programming model, and task scheduling framework using CLOUDSIM simulation tool.

The behavioral web users’ access patterns help website administrator/web site owners to take major decisions in categorizing web pages of the web site as highly demanding pages and medium demanding pages. Human beings act as a spider surfing the web pages of the website in search of required information. Most of the traditional mining algorithms concentrate only on frequency/support of item sets (web pages set denoted as ps in a given web site), which may not bring considerably more amount of profit. The utility mining model focuses on only high utilities item sets (ps). General utility mining model was proposed to overcome weakness of the frequency and utility mining models. General utility mining does not encompass website topology. This limitation is overcome by a novel model called human behavioral patterns’ web pages categorizer (HBP-WPC) which considers structural statistics of the web page in addition to support and utility. The topology of the web site along with log file statistics plays a vital role in categorizing web pages of the web site. The web pages of the website along with log file statistics forms a population. Suitable auto optimization metric is defined which provides guidelines for website designers/owners to restructure the website based on behavioral patterns of web users.

In web, users with different interest and goal enter queries to the search engine. Search engines provide all these users with the same search results irrespective of their context and interest. Therefore, the user has to browse through many results most of which are irrelevant to his goal. Personalization of search results involves understanding the user’s preferences based on his interaction and then re-ranking the search results to provide more relevant searches. We present a method for search engine to personalize search results leading to better search experience. In this method, a user profile is generated using reference ontology. The user profile is updated dynamically with interest scores whenever, he clicks on a webpage. With the help of these interest scores in the user profile, the search results are re-ranked to give personalized results. Our experimental results show that personalized search results are effective and efficient.

The usage of smartphones has increased hastily over the past few years. The number of smartphones being sold is much more than the number of PC’s due to the smartphone’s mobile nature and good connectivity. However, they are still constrained by limited processing power, memory, and Battery. In this paper, we propose a framework for making the applications of these smartphones autonomous enough, to offload their compute intensive parts automatically from the smartphone to the virtual image of the smartphones on the cloud, thus using the unlimited resources of the cloud and enhancing the performance of the smartphones. By using this framework the application developers will be able to increase the capabilities of the smartphones making them even more feature rich.

Over the past few years, the usage and boost of handheld devices such as Personal Digital Assistants (PDAs) and smartphones have increased rapidly and estimates show that they will even exceed the number of Personal Computers (PCs) by 2013. Smartphones enable a rich, new, and ubiquitous user experience, but have limited hardware resources on computation and battery. In this paper, the focus has been made on enhancing the capabilities of smartphones by using cloud computing and virtualization techniques to shift the workload from merely a smartphone to a resource-rich computational cloud environment.

Olfactory perception is the sense of smell that allows an organism to detect chemical in its environment. The first step in odor transduction is mediated by binding odorants to olfactory receptors (ORs) which belong to the heptahelical G-protein-coupled receptor (GPCR) super-family. Mammalian ORs are disposed in clusters on virtually all chromosomes. They are encoded by the largest multigene family (

$$\sim $$

1000 members) in the genome of mammals and

Caenorhabditis elegans

, whereas

Drosophila

contains only 60 genes. Each OR specifically recognizes a set of odorous molecules that share common molecular features. However, local mutations affect the DNA sequences of these receptors. Hence, to study the changes among affected and non-affected, we use unsupervised learning (clustering). In this paper, a scaled fuzzy graph model for clustering has been used to study the changes before and after the local mutation on DNA sequences of ORs. At the fractional dimensional level, our experimental study confirms its accuracy.

In this paper a linear Hopfield model is used to solve the problem of combined economic emission dispatch (CEED). The objective function of CEED problem comprises of power mismatch, total fuel cost and total emission subjected to equality/inequality constraints. In proposed methodology, inclusion of power mismatch in objective function exhibits the ability of attaining power mismatch to any desirable extent and may be employed for large-scale highly constrained nonlinear and complex systems. A systematic procedure for the selection of weighting factor adopted. The proposed method employs a linear input-output model for neurons. The efficacy and viability of the proposed method is tested on three test systems and results are compared with those obtained using other methods. It is observed that the proposed algorithm is accurate, simple, efficient, and fast.

Recent research shows that the partitioning of VLSI-based system plays a very important role in embedded system designing. There are several partitioning problems that can be solved at all levels of VLSI system design. Moreover, rapid growth of VLSI circuit size and its complexity attract the researcher to design various efficient partitioning algorithms using soft computing approaches. In VLSI

netlist

is used to optimize the parameters like mincut, power consumption, delay, cost, and area of the partitions. Hence, the Genetic Algorithm is a soft computational meta-heuristic method that has been applied to optimize these parameters over the past two decades. Here in this paper, we have summarized important schemes that have been adopted in Genetic Algorithm for optimizing one particular parameter, called

mincut

, to solve the partitioning problem.

Digital multimedia data in the form of speech, text and fax is being used extensively. Segregation of such multimedia data is required in various applications. While communication of such multimedia data, the speech, text and fax data are encoded with CVSD coding, Murray code and Huffman code respectively. The analysis and classification of such encoded multimedia from unorganized and unstructured data is an important problem for information management and retrieval. In this paper we proposed an ANN based approach to classify text, speech and fax data. The normalized frequency of binary features of varying length and PCA criterion is considered to select effective features. We use selected features in Back-propagation learning of MLP network for multimedia data classification. The proposed method classifies data efficiently with good accuracy. The classification score achieved for encoded plain data is of the order of 91, 93 and 90 % for speech, text and fax respectively. Also for 30 % distorted data, the classification score obtained is of the order of 78, 80 and 72 % for speech, text and fax respectively.

Current communication systems are very efficient and being used conveniently for secure exchange of vital information. These communication systems may be misused by adversaries and antisocial elements by capturing our vital information. Mostly, the information is being transmitted in the form of plain English text apart from securing it by encryption. To avoid losses due to leakage of vital information, one should not transmit his vital information in plain form. For monitoring of huge traffic, we require an efficient plain English text identifier. The identification of short messages in which words are written in short by ignoring some letters as in mobile messages is also required to monitor. We propose an efficient plain English text identifier based on Fuzzy measures utilizing percentage frequencies of most frequent letters and least frequent letters as features and triangular Fuzzy membership function. Presented method identifies plain English text correctly even, the given text is decimated/discontinuous and its length is very short, and seems very useful.

Mammography and X-ray imaging of the breast are considered as the mainstay of breast cancer screening. In the past several years, there has been tremendous interest in image processing and analysis techniques in mammography. The fractal is an irregular geometric object with an infinite nesting of structure of different sizes. Fractals can be used to make models of any objects. The most important properties of fractals are self-similarity, chaos, and non-integer fractal dimension. The fractal dimension analysis has been applied to study the wide range of objects in biology and medicine and has been used to detect small tumors, microcalcification in mammograms, tumors in brain, and to diagnose blood cells and human cerebellum. Fractal theory also provides an appropriate platform to build oncological-related software program because the ducts within human breast tissue have fractal properties. Fractal analysis of mammogram was used for the breast parenchymal density assessment. The fractal dimension of the surface is determined by utilizing the Box-counting method. The Mammograms were collected from HCG Hospital, Bangalore. In this study, a method was developed in the Visual Basic for extracting the suspicious region from the mammogram based on texture. The fractal value obtained through Box-counting method for benign and malignant breast cancer is combined into a set. An algorithm was used to calculate the fractal value for the extracted image of the mammogram using Box-counting method.

Traffic images captured using CCTV camera can be used to compute traffic load. This document presents a survey of the research works related to image processing, traffic load, and the technologies used to re-solve this issue. Results of the implementation of two approaches: morphology-based segmentation and edge detection using sobel operator, which are close to traffic load computation have been shown. Segmentation is the process of partitioning a digital image into its constituent parts or objects or regions. These regions share common characteristics based on color, intensity, texture, etc. The first step in image analysis is to segment an image based on discontinuity detection technique (Edge-based) or similarity detection technique (Region-based). Morphological operators are tools that affect the shape and boundaries of regions in the image. Starting with dilation and erosion, the typical morphological operation involves an image and a structure element. The edge detection consists of creating a binary image from a grayscale image where the pixels in the binary image are turned off or on depending on whether they belong to region boundaries or not. Image processing is considered as an attractive and flexible technique for automatic analysis of road traffic scenes for the measurement and data collection of road traffic parameters. Combined background differencing and edge detection and segmentation techniques are used to detect vehicles and measure various traffic parameters. Real-time measurement and analysis of road traffic flow parameters such as volume, speed and queue are increasingly required for traffic control and management.

Artificial Neural Networks (ANN) are gaining significant importance in the medical field, especially in the area of ophthalmology. Though the performance of ANN is theoretically stated, the practical applications of ANN are not fully explored. In this work, the suitability of Back Propagation Neural Network (BPN) for ophthalmologic applications is highlighted in the context of retinal blood vessel segmentation. The neural technique is tested with Diabetic Retinopathy (DR) images. The performance of the BPN is compared with the k-Nearest Neighbor (k-NN) classifier which is a statistical classifier. Experimental results verify the superior nature of the BPN over the k-NN approach

The work presents a method to automatically generate a training dataset for the purpose of summarizing text documents with the help of feature extraction technique. The goal of this approach is to design a dataset which will help to perform the task of summarization very much like a human. A document summary is a text that is produced from one or more texts that conveys important information in the original texts. The proposed system consists of methods such as pre-processing, feature extraction, and generation of training dataset. For implementing the system, 50 test documents from DUC2002 is used. Each document is cleaned by pre-processing techniques such as sentence segmentation, tokenization, removing stop word, and word stemming. Eight important features are extracted for each sentence, and are converted as attributes for the training dataset. A high quality, proper training dataset is needed for achieving good quality in document summarization, and the proposed system aims in generating a well-defined training dataset that is sufficiently large enough and noise free for performing text summarization. The training dataset utilizes a set of features which are common that can be used for all subtasks of data mining. Primary subjective evaluation shows that our training is effective, efficient, and the performance of the system is promising.

In online communication, most of the time plain English characters are transmitted, while a few are encrypted. Thus there is a need for an automatic recognizer of plain English text (based on the characteristics of the English Language) without using a dictionary. It works for continuous text without word break-up (text without blank spaces between words). We propose a very efficient artificial neural network-based technique by selecting relevant or important features using Joint Mutual Information for online recognition of English plain text which can recognize English text from English like or random data.

Genomic studies have become one of the useful aspects of Bioinformatics since it provides important information about an organism’s genome once it has been sequenced. Gene finding and promoter predictions are common strategies used in modern Bioinformatics which helps in the provision of an organism’s genomic information. Many works has been carried out on promoter prediction by various scientists and therefore many prediction tools are available. However, there is a high demand for novel prediction tools due to low level of prediction accuracy and sensitivity which are the important features of a good prediction tool. In this paper, we have developed the new algorithm Novel Approach to Promoter Prediction (NAPPR) to predict eukaryotic promoter region using the python programming, which can meet today’s demand to some extent. We have developed the parameters for Singlet (4

$$^{1}$$

1

) to nanoplets (4

$$^{9}$$

9

) in analyzing short range interactions between the four nucleotide bases in DNA sequences. Using this parameters NAPPR tool was developed to predict promoters with high level of Accuracy, Sensitivity and Specificity after comparing it with other known prediction tools. An Accuracy of 74 % and Specificity of 78 % was achieved after testing it on test sequences from the EPD database. The length of DNA sequence used as input has no limit and can therefore be used to predict promoters even in the whole human genome. At the end, it was found out that NAPPR can predict eukaryotic promoter with high level of accuracy and sensitivity.

There has been continuously arising demand for more computational power and is increasing day by day. A lot of new and adaptable technologies are coming forth to meet the user requirements, e.g., include clusters, grids, clouds and so on each having advantages and disadvantages providing computation, resources, or services. The problem arising is that for large computation many participating entities in the decision system are required and thereby more power is consumed. This paper focuses on minimizing the computation power required by the task (computation task or problem statement) especially in homogeneous systems here we are calling it as a Decision System which require some form of data (may be structured) along with the problem statement and thus proving to be a green computing environment (reducing use of hazardous things and maximizing the energy efficiency).

In this paper, a speech enhancement technique proposed by Soon and Koh is examined and improved by exploiting different window functions for preprocessing of speech signals. In this method, instead of using two-dimensional (2-D) discrete Fourier transform (DFT), discrete cosine transform (DCT) is employed with a hybrid filter based on one-dimensional (1-D) Wiener filter with the 2-D Wiener filter. A comparative study of performance of different window functions such as Hanning, Hamming, Blackman, Kaiser, Cosh, and Exponential windows has been made. When compared, Cosh window gives the best performance than all other known window functions.

There is much interest in characterizing the variations in feldspar structures because of the abundance and importance of feldspars in petrologic processes and also due to their general significance in mineralogical studies of exsolution and polymorphism, especially order-disorder. With the appearance of new analytical and rapid methods of X-ray crystallographic study and computational techniques, the significance of feldspars in igneous and metamorphic rocks has increased tremendously. In this paper methods for estimation of structrural state of alkali feldspars is reviewed and discussed.

Iris is one of the most trustworthy biometric traits due to its stability and randomness. In this paper, the Iris Recognition System is developed with the intention of verifying both the uniqueness and performance of the human iris, as it is a briskly escalating way of biometric authentication of an individual. The proposed algorithm consists of an automatic segmentation system that is based on the Hough transform, and can localize the circular iris and pupil region, occluding eyelids and eyelashes, and reflections. The extracted iris region is then normalized into a rectangular block. Further, the texture features of normalized image are extracted using LBP (Local Binary Patterns). Finally, the Euclidean distance is employed for the matching process. In this thesis, the proposed system is tested with the co-operative database such as CASIA. With CASIA database, the recognition rate of proposed method is almost 91 %, which shows the iris recognition system is reliable and accurate biometric technology.

The main problem of face recognition is large variability of the recorded images due to pose, illumination conditions, facial expressions, use of cosmetics, different hairstyle, presence of glasses, beard, etc., especially the case of twins’ faces. Images of the same individual taken at different times, different places, different postures, different lighting, may sometimes exhibit more variability due to the aforementioned factors, than images of different individuals due to gender, age, and individual variations. So a robust recognition system is implemented to recognize an individual even from a large amount of databases within a few minutes. So in order to handle this problem we have used SVM for face recognition. Using this technique an accurate face recognition system is developed and tested and the performance found is efficient. The procedure is tested on ORL face database. Results have proved that SVM approach not only gives higher classification accuracy but also proved to be efficient in dealing with the large dataset as well as efficient in recognition time. Results have proved that not only the training performance, the recognition performance but also the recognition rate raises to 100 % using SVM.

This paper discusses an approach for river mapping and flood evaluation to aid multi-temporal time series analysis of satellite images utilizing pixel spectral information for image classification and region-based segmentation to extract water covered region. Analysis of Moderate Resolution Imaging Spectroradiometer (MODIS) satellite images is applied in two stages: before flood and during flood. For these images the extraction of water region utilizes spectral information for image classification and spatial information for image segmentation. Multi-temporal MODIS images from “normal” (non-flood) and flood time-periods are processed in two steps. In the first step, image classifiers such as artificial neural networks and gene expression programming to separate the image pixels into water and non-water groups based on their spectral features. The classified image is then segmented using spatial features of the water pixels to remove the misclassified water region. From the results obtained, we evaluate the performance of the method and conclude that the use of image classification and region-based segmentation is an accurate and reliable for the extraction of water-covered region.

In this paper we have used principal component analysis (PCA) tool by adding mathematical rigor to provide explicit solution for gender recognition by extracting feature vector. We will implement face recognition system using PCA algorithm along with the application of kernel support vector machine for error minimization. In addition by using face-rec database. This is an Eigen face approach motivated by information theory using an images database of 545 images of male and female for improved efficiency. sometimes PCA mixes data points which lead to classification error. We are improving principal component analysis (PCA) by taking vector corresponding to

$$k$$

k

minimum error unlike conventional PCA.

In this paper, we are analyzing the SOM-HNN for storage and recalling of fingerprint images. The feature extraction of these images is performed with FFT, DWT, and SOM. These feature vectors are stored as associative memory in Hopfield Neural Network with Hebbian learning and Pseudoinverse learning rules. The objective of this study is to determine the optimal weight matrix for efficient recalling of the memorized pattern for the presented noisy or distorted and incomplete prototype patterns from the Hopfield network using Simulated Annealing. This process minimizes the effect of false minima in the recalling process.

Registration is an advanced technique which maps two images spatially and can produce an informative image. Intensity-based similarity measures are increasingly used for medical image registration that helps clinicians for faster and more effective diagnosis. Recently, mutual information (MI)-based image registration techniques have become popular for multimodal brain images. In this chapter, normalized mutual information (NMI) method has been employed for brain MR image registration. Here, the intensity patterns are encoded through similarity measure technique. NMI is an entropy-based measure that is invariant to the overlapped regions of the two images. To take care of the deformations, transformation of the floating image is performed using B-spline method. NMI-based image registration is performed for similarity measure between the reference and floating image. Optimal evaluation of joint probability distribution of the two images is performed using parzen window interpolation method. The hierarchical approach to nonrigid registration based on NMI is presented in which the images are locally registered and nonrigidly interpolated. The proposed method for nonrigid registration is validated with both clinical and artificial brain MR images. The obtained results show that the images could be successfully registered with 95 % of correctness.

Wireless automation sensor communication network (WASCN) is the promising tool for energy conservation [

1

] according to the research work of this paper. This paper considers the two aspects of analyzing an appliance, i.e., at manufacturer level and user condition level of that appliance. At manufacturer level, the manufacturer company of the particular appliance will itself provide the concerned data of appliance and its effect on the environment, whereas at user level, these data may depend on the infrastructure or the environment of that particular appliance where it is being used. Now to analyze the 2nd impact we have environment and infrastructure manager (EIM). EIM will deploy WASCN [

2

] between various appliances to measure the effects of the appliance according to user, infrastructure as well as the environment in which it is being used. These data recorded by the EIM will be shared to analyze the effect of a particular appliance in various particular conditions which in turn will help the customers or an industry to choose the environment friendly products considering the cost too.

Clustering techniques in wireless sensor networks (WSNs) compare to random selection techniques is less costly due to the saving of time in journeys, reduction in number of transmissions and receptions at each node, identification, contacts, etc., which are valuable for increasing the overall network life, scalability of WSNs. Clustering sensor nodes is an effective and efficient technique for achieving the requirement. The maximizing lifetime of network by minimizing energy consumption poses a challenge in design of protocols. Therefore, proper organization of clustering and orientation of nodes within the cluster becomes one of the important issues to extend the lifetime of the whole sensor network through Cluster Head (CH). We investigate the problem of energy consumption in CH rotation in WSNs. In this paper, CH selection algorithm has been proposed from an unequal cluster. The total energy and expected number of packet retransmissions in delivering a packet from the sensor node to other nodes have been mathematically derived. In this paper, we applied the approach for producing energy-aware unequal clusters with optimal selection of CH and discussed several aspects of the network mathematically and statistically. The simulation results demonstrate that our approach of re-clustering in terms of energy consumption and lifetime parameters.

The present era in communication is the era of VANET which simply represents the communication between fast moving vehicles. The VANET is expanding day by day from planes to higher altitude, from metropolitan to towns etc. At higher altitude the performance of VANET becomes prime area of consideration. Because power consumption is more due to average QoS (Quality of Service). Everyday days new functions like gaming, internet, audios, videos, credit card functions etc. are being introduced leading to fast CPU clock speed hence more battery consumption. Since energy conservation is main focus now days therefore in this paper we studied and compared various battery models for residual battery capacity taking Bellman Ford ad hoc routing protocol in to consideration along with various VANET parameters like nodes, speed, altitude, area etc. in real traffic scenario. The battery models Duracell AA(MX-1500), Duracell AAA(MN-2400), Duracell AAA(MX-2400), Duracell C-MN(MN-1400) are compared in hilly scenario using Qualnet as a simulation tool taking nearly equal real scenarios after a frequent study of that region. The performance of various battery models for residual battery capacity is compared so that right battery model shall be chosen in hilly VANET. Varying parameters of VANET shows that in the real traffic scenarios battery models AA (MX-1500) and C-MN (MN-1400) performs more efficiently for energy conservation.

This paper proposes a scheme to utilize the unaltered direct outcome of brain’s activity viz. EEG signals for emotion detection that is a prerequisite for the development of an emotionally intelligent system. The aim of this work is to classify the emotional states experimentally elicited in different subjects, by extracting their features for the alpha, beta, and theta frequency bands of the acquired EEG data using PSD, EMD, wavelet transforms, statistical parameters, and Hjorth parameters and then classifying the same using LSVM, LDA, and kNN as classifiers for the purpose of categorizing the elicited emotions into the emotional states of neutral, happy, sad, and disgust. The experimental results being a comparative analysis of the different classifier performances equip us with the best accurate means of emotion recognition from the EEG signals. For all the eight subjects, neutral emotional state is classified with an average classification accuracy of 81.65 %, highest among the other three emotions. The negative emotions including sad and disgust have better average classification accuracy of 76.20 and 74.96 % as opposed to the positive emotion i.e., happy emotional state, the average classification accuracy of which turns out to be 73.42 %.

Multi-walled carbon nanotube (MWCNT) bundle potentially provided attractive solution in current nanoscale VLSI interconnects. This research paper introduces an equivalent single conductor (ESC) model for bundled MWCNT that contains a number of MWCNTs with different number of shells. A driver-interconnect-load (DIL) system employing CMOS driver is used to calculate the propagation delay. Using DIL system, propagation delay is compared for bundled CNT structures containing different number of MWCNTs. At global interconnect lengths, delay is significantly reduced for the bundled CNT containing more number of MWCNTs with lesser number of shells. It is observed that compared to the bundles containing lesser number of MWCNTs, the overall delay is improved by 9.89 % for the bundle that has more number of MWCNTs.

This paper investigates a new geometry of circular microstrip patch antenna using rectangular slot which can be used for WLAN and Wi-Max application. This geometry obtained bandwidth enhancement upto 9.58 % in comparison with conventional design and there is also improvement in other radiation parameters like gain, efficiency and return loss. For entire bandwidth the radiation pattern is stable and uniform.

Federal Communications Commission (FCC) revealed that a bandwidth of 7.5 GHz from 3.1 to 10.6 GHz is for Ultra Wideband (UWB) wireless communication. UWB is a rapidly advancing technology for high data rate wireless communication. The main challenge in UWB antenna design is achieving the very broad impedance bandwidth with compactness in size. The proposed antenna has the capability of operating between 1.1 and 11.8 GHz. In this paper, a rectangular patch antenna is designed with truncated corners at the ground as well as at the patch. A

$$\prod $$

∏

-shaped slot is cut out from the patch to get the complete UWB. After that two equal size of slits on sides of the

$$\prod $$

∏

shape are cut out from the patch which dispends the WLAN. The proposed antenna uses Rogers RT/duroid substrate with a thickness of 1.6 mm and relative permittivity of 2.2. The aperture coupled feed is used for excitation. The proposed antenna is simulated using HFSS 11 software.

This paper presents a method to minimize the effect on resonance frequency due to fabrication error of microstrip patch antenna. When a patch antenna is fabricated, dimension of the patch may be slightly differentfrom its calculated value due to error in the fabrication operations, which causes into variation of its resonance frequency. To overcome this problem this paper presents a new technique to minimize the effect on resonance frequency due to fabrication error of MS antenna by operating dielectric constant. Effective dielectric constant of substrate is changed in such a way that the resonant frequency is set back to the calculated value.

The central issue of the study is to model the movement of stock price for Indian Information Technology (IT) companies. It has been observed that IT industry has some promising role in Indian economy. We apply the artificial neural networks (ANNs) for modeling purpose. ANNs are flexible computing frameworks and its universal approximations applied to a wide range with desired accuracy. In the study, multilayer perceptron (MLP) models, which are basically feed-forward artificial neural network models, are used for forecasting the stock values of an Indian IT company. On the basis of various features of the network models, an optimal model is being proposed for the purpose of forecasting. Performance measures like

$$\text {R}^{2}$$

R

2

, standard error of estimates, mean absolute error, mean absolute percentage error indicate that the model is adequate with respect to acceptable accuracy.

This paper presents a comparative analysis of speed controllers for three-phase induction-motor scalar speed control. The control strategy consists in keeping constant the voltage and frequency ratio of the induction-motor supply source. First, a conventional control loop including a PI controller is realized. Then a fuzzy-control system is built on a MATLAB platform, which uses speed and difference in speed variation to change both the fundamental voltage amplitude and frequency of a sinusoidal pulse width modulated inverter. An alternative optimized method using Genetic Algorithm is also proposed. The controller performance, in relation to reference speed and step change of speed variations with constant load-torque, is evaluated by simulating it on a MATLAB platform. A comparative analysis of these with conventional proportional-integral controller is also presented.

Code copy and reuse are the most common way of programming practice. Code duplication occurs in every software program. A function, a module, or a file is duplicated for various reasons. The copied part of the source code with or without modification is called a code clone. Several tools have been designed to detect duplicated code fragments. These simple code clones assists to identify the design level similarities. Recurring patterns of simple clones indicate the presence of design level similarities called higher level clones. In this work we describe a new technique using fingerprinting to find higher level clones in software. Initially the simple clones are found, and then using LSH, we compare the fingerprints to find recurring patterns of method level, file level, and directory level clones. Finally, experiments and results shows that the proposed method finds all higher level clones in the software.

Spatial data mining i.e., discovery of implicit knowledge in spatial databases, is very crucial for effective use of spatial data. Clustering is an important task, mostly used in preprocessing phase of data analysis. It is widely recognized that combining multiple models typically provides superior results compared to using a single, well-tuned model. The idea of combining object partitions without accessing the original objects’ features leads us to knowledge reuse termed as cluster ensembles. The most important advantage is that ensembles provide a platform where vertical slices of data can be fused. This approach provides an easy and effective solution for the most haunted issue of preserving privacy and dimensionality curse in data mining applications. We have designed four approaches to implement spatial cluster ensembles and have used these for merging vertical slices of attribute data. In our approach, we have brought out that by using a guided approach in combining the outputs of the various clusterers, we can reduce the intensive distance matrix computations and also generate robust clusters. We have proposed hybrid and layered cluster merging approach for fusion of spatial clusterings and used it in our three-phase clustering combination technique. The major challenge in fusion of ensembles is creation and manipulation of voting matrix or proximity matrix of order

$$\text {n}^{2}$$

n

2

, where n is the number of data points. This is very expensive both in time and space factors, with respect to spatial data sets. We have eliminated the computation of such expensive voting matrix. Compatible clusterers are identified for the partially fused clusterers, so that this acquired knowledge will be used for further fusion. The apparent advantage is that we can prune the data sets after every (m

$$-$$

-

1)/2 layers. Privacy preserving has become a very important aspect as data sharing between organizations is also difficult. We have tried to provide a solution for this problem. We have obtained clusters from the partial datasets and then without access to the original data, we have used the clusters to help us in merging similar clusters obtained from other partial datasets. Our ensemble fusion models are tested extensively with both intrinsic and extrinsic metrics.

This paper presents online estimation of unstable and integrating time delay process model parameters using a smart relay. The describing function (DF) approximation of relay not only results in simpler analytical expressions but also enables one to estimate the model parameters with significant accuracy. Measurement noise is an important issue during estimation of process model parameters. The smart relay is capable of emulating the dynamics of a conventional relay and also of rejecting the ill effects of measurement noise. Simulation results show the usefulness of the identification technique.

The apt estimate of the software cost in advance is one of the most challenging, difficult and mandatory task for every project manager. Software development is a critical activity which requires various considerable resources and time. A prior assessment of software cost directly depends on the expanse of these resources and time, which in turn depends in the software attributes and its characteristics. Since there are many precarious and dynamic attributes attached to every software project, the accuracy in prediction of the cost will rely on the prudential treatment of these attributes. This paper deals with the methods of selection, quantification and comparison of different attributes related to different projects. We have tried to find the similarity difference between project attributes and then consequently used this difference measurement for creating the initial cost proposals of any software project that has some degree of correspondence with the formerly completed projects whose total cost is fairly established and well known.

With growing science and technology in manufacturing industry, an electronic database as grown in a diverse manner. In order to maintain, organizing and analyzing application-driven databases, a systematic approach of data analysis is essential. The most succeeded approach for handling these problems is through advanced database technologies and data mining approach. Building the database with advance technology and incorporating data mining aspect to mine the hidden knowledge for a specific application is the recent and advanced data mining application in the computer application domain. Here in this article, association rule analysis of data mining concepts is investigated on engineering materials database built with UML data modeling technology to extract application-driven knowledge useful for decision making in different design domain applications.

As the wealth of online information is increasing tremendously, the need for question-answering systems is evident. Current search engines return ranked lists of documents to the users query, but they do not deliver the precise answer to the queries. The goal of a question-answering system is to retrieve answers to questions rather than full documents or best-matching passages, as most information retrieval systems currently do. Patients/Medical students have many queries related to the medical terms, diseases, and its symptoms. They are inquisitive to find these answers using search engines. But due to keyword search used by search engines it becomes quite difficult for them to find the correct answers for the search item. This paper proposes the architecture of question-answering system for medical domain and discusses the rule-based question processing and answers retrieval. Rule formation for retrieval of Answers has also been discussed in the paper.

A single-string-based evolutionary algorithm that adaptively learns to control the mutation probability

$$(p_m)$$

(

p

m

)

and mutation intensity

$$(\Delta _m)$$

(

Δ

m

)

has been developed and used to investigate the ground-state configurations and energetics of 3D clusters of a finite number (

N

) of ‘point-like’ charged particles. The particles are confined by a harmonic potential that is either isotropic or anisotropic. The energy per particle

$$(E_N/N)$$

(

E

N

/

N

)

and its first and second differences are analyzed as functions of confinement anisotropy, to understand the nature of structural transition in these systems.

Cluster analysis is a technique that divides a given data set into a set of clusters in such a way that two objects from the same cluster are as similar as possible and the objects from different clusters are as dissimilar as possible. A robust rough-fuzzy

$$c$$

c

-means clustering algorithm is applied here to identify clusters having similar objects. Each cluster of the robust rough-fuzzy clustering algorithm is represented by a set of three parameters, namely, cluster prototype, a possibilistic fuzzy lower approximation, and a probabilistic fuzzy boundary. The possibilistic lower approximation helps in discovering clusters of various shapes. The cluster prototype depends on the weighting average of the possibilistic lower approximation and probabilistic boundary. The reported algorithm is robust in the sense that it can find overlapping and vaguely defined clusters with arbitrary shapes in noisy environment. The effectiveness of the clustering algorithm, along with a comparison with other clustering algorithms, is demonstrated on synthetic as well as coding and non-coding RNA expression data sets using some cluster validity indices.

Clustering is a very important data mining task. Clustering of streaming data is very challenging because streaming data cannot be scanned multiple times and also new concepts may keep evolving in data over time. Inherent uncertainty involved in real world data stream further magnifies the challenge of working with streaming data. Rough set is a soft computing technique which can be used to deal with uncertainty involved in cluster analysis. In this paper, we propose a novel rough set based clustering method for streaming data. It describes a cluster as a pair of lower approximation and an upper approximation. Lower approximation comprises of the data objects that can be assigned with certainty to the respective cluster, whereas upper approximation contains those data objects whose belongingness to the various clusters in not crisp along with the elements of lower approximation. Uncertainty in assigning a data object to a cluster is captured by allowing overlapping in upper approximation. Proposed method generates soft-cluster. Keeping in view the challenges of streaming data, the proposed method is incremental and adaptive to evolving concept. Experimental results on synthetic and real world data sets show that our proposed approach outperforms Leader clustering algorithm in terms of classification accuracy. Proposed method generates more natural clusters as compare to k-means clustering and it is robust to outliers. Performance of proposed method is also analyzed in terms of correctness and accuracy of rough clustering.

Clustering of sensor nodes is an energy efficient approach to extend lifetime of wireless sensor networks. It organizes the sensor nodes in independent clusters. Clustering of sensor nodes avoids the long distance communication of nodes and hence prolongs the network functioning time. The number of cluster heads is an important aspect for energy efficient clustering of nodes because total intra-cluster communication distance and total distance of cluster heads to base station depends upon number of cluster heads. In this paper, we have used genetic algorithms for optimizing the number of cluster heads while taking trade-off between total intra-cluster distance and total distance of cluster heads to base station. Experimental results show that proposed scheme can efficiently optimize the number of cluster heads for clustering of nodes in wireless sensor networks.

Cluster Analysis is a popular data analysis in data mining technique. Clusters play a vital role for users to organize, summarize and navigate the data effectively. Swarm Intelligence (SI) is a relatively new subfield of artificial intelligence which studies the emergent collective intelligence of groups of simple agents. It is based on social behavior that can be observed in nature, such as ant colonies, flocks of birds, fish schools and bee hives. SI technique is integrated with clustering algorithms. This paper proposes new approaches for using Cuckoo Search Algorithm (CSA) to cluster data. It is shown how CSA can be used to find the optimally clustering N object into K clusters. The CSA is tested on various data sets, and its performance is compared with those of K-Means, Fuzzy C-Means, Fuzzy PSO and Genetic K-Means clustering. The simulation results show that the new method carries out better results than the K-Means, Fuzzy C-Means, Fuzzy PSO and Genetic K-Means.

Search Results Clustering (SRC) is a well-known approach to address the lexical ambiguity issue that all search engines suffer from. This paper develops an Expectation Maximization (EM)-based adaptive term pruning method for enhancing search result analysis. Knowledge preserving capabilities of this approach are demonstrated on the AMBIENT dataset using Snowball clustering method.

This paper presents a novel method to locate and segment the microcalcification clusters in mammogram images, using the principle of fractal dimension. This proposed technique detects the edges using the intensities of the regions/objects in the image, the Fractal dimension of the image, which is image-dependent in such a way that leads to the segmentation of microcalcification clusters in the image. Hence this fractal dimension based detection of microcalcifations is proved to produce excellent results and the location of the detected microcalcifications clusters complies with the specifications of dataset of the mini-MIAS database accurately, which substantiate the merit of the proposed technique.

This paper proposes an efficient biometrics system based on palmprint. Palmprint ROI is transformed using proposed local edge pattern (LEP). Corner like features are extracted from the enhanced palmprint images as they are stable and highly discriminative. It has also proposed a distance measure that uses some geometrical and statistical constraints to track corner feature points between two palmprint ROI’s. The performance of the proposed system is tested on publicly available PolyU database consisting of 7,752 and CASIA database consisting of 5,239 hand images. The feature extraction as well as matching capabilities of the proposed system are optimized and it is found to perform with CRR of

$$99.97\,\%$$

99.97

%

with ERR of

$$0.66\,\%$$

0.66

%

for PolyU and CRR of

$$100\,\%$$

100

%

with ERR of

$$0.24\,\%$$

0.24

%

on CASIA databases respectively.

Differential evolution (DE) is a vector population-based stochastic search optimization algorithm. DE converges faster, finds the global optimum independent to initial parameters, and uses few control parameters. The exploration and exploitation are the two important diversity characteristics of population-based stochastic search optimization algorithms. Exploration and exploitation are compliment to each other, i.e., a better exploration results in worse exploitation and vice versa. The objective of an efficient algorithm is to maintain the proper balance between exploration and exploitation. This paper focuses on a comparative study based on diversity measures for DE and its prominent variants, namely JADE, jDE, OBDE, and SaDE.

This paper presents new approach analytical results of document clustering for vectors. The proposed analytical results of document clustering for vectors approach is based on mean clusters. In this paper we have used six iterations

$$\text {I}_{1}$$

I

1

to

$$\text {I}_{6}$$

I

6

for document clustering results. The steps Document collection, Text Pre-processing, Feature Selection, Indexing, Clustering Process and Results Analysis are used. Twenty news group data sets are used in the experiments. The experimental results are evaluated using the numerical computing MATLAB 7.14 software. The experimental results show the proposed approach out performs.

Fingerprint recognition is one of the most commonly used biometric technology. Even if fingerprint temporarily changes (cuts, bruises) it reappears after the finger heals. Criminals started to be aware of this and try to fool the identification systems applying methods from ingenious to very cruel. It is possible to remove, alter, or even fake fingerprints (made of glue, latex, silicone), by burning the fingertip skin (fire, acid, other corrosive material), by using plastic surgery (changing the skin completely, causing change in pattern—portions of skin are removed from a finger and grafted back in different positions, like rotation or “Z” cuts, transplantations of an area from other parts of the body like other fingers, palms, toes, and soles). This paper presents a new algorithm for altered fingerprints detection based on fingerprint orientation field reliability. The map of the orientation field reliability has peaks in the singular point locations. These peaks are used to analyze altered fingerprints because, due to alteration, more peaks as singular points appear with lower amplitudes.

A large part of any firm’s investment goes in advertising and therefore planning of an appropriate media for advertisement is the need of today so as to achieve the best returns in terms of wider reach over potential market. In this paper, we deal with a media planning problem for multiple products of a firm in a market which is segmented geographically into various regional segments with diverse language and cultural base. As such each of these regional segments responds to regional advertising as well as national advertising which reaches them with a fixed spectrum. The objective is to plan an advertising media (national and regional media) for multiple products in such a way that maximizes the total reach which is measured through each media exclusively as well as through their combined impact. The problem is formulated as a multi-objective programming problem and solved through goal programming technique. A real life case is provided to illustrate the applicability of the proposed model.

This article develops a two warehouse deterministic inventory model for deteriorating items with trapezoidal type demand under conditionally permissible delay in payments. A rented warehouse is used when the ordering quantity exceeds the limited capacity of the owned warehouse, and it is assumed that deterioration rates of items in the two warehouses may be different. In contrast to the traditional deterministic two-warehouse inventory model with shortages at the end of each replenishment cycle, an alternative model in which each cycle begins with shortages and ends without shortages is proposed. Deterioration rate is taken to be time-dependent. Shortages are allowed and fully backlogged. Then a solution procedure is shown to find the optimal replenishment policy of the considered problem. At last, article provides numerical example to illustrate the developed model. Sensitivity analysis is also given with respect to major parameters.

Business in the present highly competitive scenario emphasises the need to satisfy customers. Generally, uncertainty in demand is observed from customer side when products are deteriorating in nature. This uncertain demand cannot be predicted precisely, which causes fuzziness in related constraints and cost functions. Synchronizing inventory, procurement, and transportation of deteriorating natured products with fuzzy demand, and fuzzy holding cost at source and destination becomes essential in supply chain management (SCM). The current study demonstrates a fuzzy optimization model with an objective to minimize the cost of holding, procurement, and transportation of multi products from multi sources to multi destinations (demand point) with discount policies on ordered and weighted transportation quantity. A case study is illustrated to validate the model.

Promotion plays an important role in determining success of a product/service. Out of the many mediums available, promotion through means of advertisements is most effective and is most commonly used. Due to increasing popularity of the Internet, advertisers yearn for placing their ads on web. Consequently, web advertising has become one of the major sources of income for many websites. Several websites provide free services to the users and generate revenue by placing ads on its webpages. Advertisement for any product/service is placed on the site considering various aspects such as webpage selection, customer demography, product category, page, slot, time, etc. Further, different advertisers bid different costs to place their ads on a particular rectangular slot of a webpage, that is, many ads compete with each other for their placement on a specific position. Hence, in order to maximize the revenue generated through the ads, optimal placement of ads becomes imperative. In this paper, we formulate an advertisement planning problem for web news media maximizing their revenue. Mathematical programming approach is used to solve the problem. A case study is presented in the paper to show the application of the problem.

Growth in number of documents increases day by day, and for managing this growth the document clustering techniques are used document clustering is a significant tool to allocating web search engines for data mining and knowledge discovery. In this paper, we have introduced a new framework graph-based frequent Term set for document clustering (GBFTDC). In this study, document clustering has been performed for extraction of useful information from document dataset based on frequent term set. We have generated association rules to perform pre-processing and then have applied clustering approach.

Greecomputing is now more than just being environmentally responsible. It is also the exercise of utilizing optimal IT resources in a more efficient way. It is realized by the computer professionals and also by the Scientists that one of the key enablers of Green computing is virtualisation. Virtual computing and management will enable toward environmentally sustainable ICT infrastructure. The desktop virtualisation enables to utilise the untapped processing power of today’s high-power PCs and storage devices. The same or improved performance can be delivered with reduced operating expenses, a smaller carbon footprint and significantly curtailed greenhouse gas emissions. In this work the authors have made a complete study on Desktop virtualisation, Thin client architecture, and its role in Green computing.

Microarray technique is used to study the role of genetics involved in the development of diseases in an early stage. Recently microarray has made an enormous contribution to explore the diverse molecular mechanisms involved in tumorigenesis. The end product of microarray is the digital image, whose quality is often degraded by noise caused due to inherent experimental variability. Therefore, noise reduction is a most contributing step involved in the microarray image processing to obtain high intensity gene expression results and to avoid biased results. Microarray data of breast cancer genes was obtained from National Institute of Animal Science and Rural Development Administration, Suwon, South Korea. Two algorithms were created for noise reduction and to calculate the intensity of gene expression of breast cancer susceptibility gene 1 (BRCA1) and breast cancer susceptibility gene 2 (BRCA2). The new algorithm successively decreased the noise and the expression value of microarray gene image was efficiently enhanced.

Human-Computer-Interface (HCI) has become an emerging area of research among the scientific community. The uses of machine learning algorithms are dominating the subject of data mining, to achieve the optimized result in various areas. One such area is related with emotional state classification using bio-electrical signals. The aim of the paper is to investigate the efficacy, efficiency and computational loads of different algorithms scientific comparisons that are used in recognizing emotional state through cardiovascular physiological signals. In this paper, we have used Decision tables, Neural network, C4.5 and Naïve Bayes as a subject under study, the classification is done into two domains:

High Arousal and Low Arousal.

Bearing faults are one of the major sources of malfunctioning in machinery. A reliable bearing health condition monitoring system is very useful in industries in early fault detection and to prevent machinery breakdown. This paper is focused on fault diagnosis of ball bearing using adaptive neuro fuzzy classifier (ANFC) and support vector machine (SVM). The vibration signals are captured and analyzed for different types of defects. The specific defects consider as inner race with spall, outer race with spall, and ball with spall. Statistical techniques are applied to calculate the features from the vibration data and comparative experimental study is carried using ANFC and SVM. The results show that these methods give satisfactory results and can be used for automated bearing fault diagnosis.

This paper examines the relationship between the operations of forward and reverse logistics and the environmental performance measures like

$$\mathrm{{CO}}_{2 }$$

emission in the network due to transportation activities in closed-loop supply chain network design. A closed-loop structure in the green supply chain logistics and the location selection optimization was proposed in order to integrate the environmental issues into a traditional logistic system. So, we present an integrated and a generalized closed-loop network design, consisting four echelons in forward direction (i.e., suppliers, plants, and distribution centers, first customer zone) and four echelons in backward direction (i.e., collection centers, dismantlers, disposal centers, and second customer zone) for the logistics planning by formulating a cyclic logistics network problem. The model presented is bi objective and captures the trade-offs between various costs inherent in the network and of emission of greenhouse gas CO

$$_{2}$$

. experiments were presented, and the results showed that the proposed model and algorithm were able to support the logistic decisions in a closed loop supply chain efficiently and accurately.

In modular-based software systems, each module has different alternatives with variation in their functional and nonfunctional properties, e.g., reliability, cost, delivery time, etc. The success of such systems largely depends upon the selection process of commercial-off-the shelf (COTS) components. In component-based software (CBS) development, it is desirable to choose the components that provide all necessary functionalities and at the same time optimize nonfunctional attributes of the system. In this paper, we have discussed the multiobjective optimization model for COTS selection in the development of a modular software system using CBSS approach. Fuzzy mathematical programming (FMP) is used for decision making to counter the effects of unreliable input information.

Biometrics-based authentication has advantages over other mechanisms, but there are several variabilities and vulnerabilities that need to be addressed. No single modality or combinations of modalities can be applied universally that is best for all applications. This paper deliberates different combinations of physiological biometric modalities with different levels of fusion. In our experiments, we have selected Face, Palmprint, Finger Knuckle Print, Iris, and Handvein modalities. All the modalities are of image type and publicly available, comprising at least 100 users. Proper selection of modalities for fusion can yield desired level of performance. Through our experiments it is learnt that a multimodal system which is considered just by increasing number of modalities by fusion would not yield the desired level of performance. Many alternate options for increased performance are presented.

Primary Goal of a Data mining technique is to detect and classify the data from a large data set without compromising the speed of the process. Data mining is the process of extracting patterns from a large dataset. Therefore the pattern discovery and mining are often time consuming. In any data pattern, a data is represented by several columns called the linear low dimensions. But the data identity does not equally depend upon each of these dimensions. Therefore scanning and processing the entire dataset for every query not only reduces the efficiency of the algorithm but at the same time minimizes the speed of processing. This can be solved significantly by identifying the intrinsic dimensionality of the data and applying the classification on the dataset corresponding to the intrinsic dataset only. Several algorithms have been proposed for identifying the intrinsic data dimensions and reducing the same. Once the dimension of the data is reduced, it affects the classification rate and classification rate may drop due to reduction in number of data points for decision. In this work we propose a unique technique for classifying the leukemia data by identifying and reducing the dimension of the training or knowledge dataset using Iterative process of Intrinsic dimensionality discovery and reduction using Principal Components Analysis (PCA) technique. Further the optimized data set is used to classify the given data using Support Vector Machines (SVM) classification. Results show that the proposed technique performs much better in terms of obtaining optimized data set and classification accuracy.

Inherent intelligent characteristics of humans, such as human interactions and information exchanges enable them to evolve more rapidly than any other species on the earth. Human interactions are generally selective and are free to explore randomly based on the individual bias. When the interactions are indecisive, individuals consult for second opinion to further evaluate the indecisive interaction before adopting the change to emerge and evolve. Inspired by such human properties, in this paper a novel social evolution (SE) algorithm is proposed and tested on four numerical test functions to ascertain the performance by comparing the results with the state-of-the-art soft computing techniques on standard performance metrics. The results indicate that, the performance of SE algorithm is better than or quite comparable to the state-of-the-art nature inspired algorithms.

A large portion of a document is usually covered by irrelevant features. Instead of identifying actual context of the document, such features increase dimensions in the representation model and computational complexity of underlying algorithm, and hence adversely affect the performance. It necessitates a requirement of relevant feature selection in the given feature space. In this context, feature selection plays a key role in removing irrelevant features from the original feature space. Feature selection methods are broadly categorized into three groups: filter, wrapper, and embedded. Filter methods are widely used in text mining because of their simplicity, computational complexity, and efficiency. In this article, we provide a brief survey of filter feature selection methods along with some of the recent developments in this area.

Clustering is an unsupervised classification method and plays essential role in applications in diverse fields. The evolutionary methods attracted attention and gained popularity among the data mining researchers for clustering due to their expedient implementation, parallel nature, ability to search global optima, and other advantages over conventional methods. However, conventional clustering methods, e.g., K-means, are computationally efficient and widely used local search methods. Therefore, many researchers paid attention to hybrid algorithms. However, most of the algorithms lag in proper balancing of exploration and exploitation of solutions in the search space. In this work, the authors propose a hybrid method DKGK. It uses DE to diversify candidate solutions in the search space. The obtained solutions are refined by K-means. Further, GA with heuristic crossover operator is applied for fast convergence of solutions and the obtained solutions are further refined by K-means. This is why proposed method is called DKGK. Performance of the proposed method is compared to that of Deferential Evolution (DE), genetic algorithm (GA), a hybrid of DE and K-means (DEKM), and a hybrid of GA and K-Means (GAKM) based on the sum of intra-cluster distances. The results obtained on three real and two synthetic datasets are very encouraging as the proposed method DKGK outperforms all the competing methods.

Simulated boundary potential data for Electrical Impedance Tomography (EIT) are generated by a MATLAB based EIT data generator and the resistivity reconstruction is evaluated with Electrical Impedance Tomography and Diffuse Optical Tomography Reconstruction Software (EIDORS). Circular domains containing subdomains as inhomogeneity are defined in MATLAB- based EIT data generator and the boundary data are calculated by a constant current simulation with opposite current injection (OCI) method. The resistivity images reconstructed for different boundary data sets and images are analyzed with image parameters to evaluate the reconstruction.

Wireless communications is the fastest growing segment of the communications industry and over the recent years, it has rapidly emerged in the market providing users with network mobility, scalability, and connectivity. It is a flexible data communication system implemented as an extension to or as an alternative for, a wired LAN [

1

]. The placement of access points (AP) can be modeled as a nonlinear optimization problem. The work explores the measured data in terms of signal strength in the indoor WLAN 802.11 g at Malviya Bhavan, Boys Hostel Building, Indian Institute of Technology, Roorkee, Saharanpur Campus coverage using optimization technique. In the present study, an application of particle swarm optimization (PSO) is shown to determine the optimal placement of AP.

Stereovision is a technique aimed at inferring depth from two or more cameras. It plays an important role in computer vision. Single image has no depth or 3D information. Stereovision takes two images of a scene from different viewpoints usually referred to as left and right images using two cameras. Stereovision is similar to the binocular (two-eyed) human vision capturing two different views of a scene and brain processing and matching the similarity in both the images and the differences allow the brain to build depth information. OpenCV Library is used to compute the output of stereovision process—disparity and depth map.