Skip to main content
main-content

Über dieses Buch

The book is about all aspects of computing, communication, general sciences and educational research covered at the Second International Conference on Computer & Communication Technologies held during 24-26 July 2015 at Hyderabad. It hosted by CMR Technical Campus in association with Division – V (Education & Research) CSI, India. After a rigorous review only quality papers are selected and included in this book. The entire book is divided into three volumes. Three volumes cover a variety of topics which include medical imaging, networks, data mining, intelligent computing, software design, image processing, mobile computing, digital signals and speech processing, video surveillance and processing, web mining, wireless sensor networks, circuit analysis, fuzzy systems, antenna and communication systems, biomedical signal processing and applications, cloud computing, embedded systems applications and cyber security and digital forensic. The readers of these volumes will be highly benefited from the technical contents of the topics.

Inhaltsverzeichnis

Frontmatter

Gesture Controlled Wireless Device for Disabled

Wheelchairs were made for physically challenged persons in order to move them from one place to another, but these required a lot of mechanical effort because of which another person was needed for this work. Then came the wired system which reduced the effort up to an extent but was not very successful. The proposed module overcomes the previous limitations of the mechanical and wired systems. According to this technology, one is able to control a remote device easily from a distant site. This paper is about wireless communication between two wireless modules, a robot and a hand movement controlled device fitted with tilt sensor on it. Free radio frequency of 2.4 GHz with 16 channels, Zigbee technology is used, keeping all wireless IEEE 802.15.4 global open standards true.

Shantanu, Manish Sharma, Bhupendra Singh, Mohit Agarwal, Amit Kumar

Implementation of Genetic Algorithm for Optimization of Network Route

Problem in the real world requires modeling the problem mathematically and drawing conclusions based on the solutions of the mathematical problem. One of the alternatives is evolutionary computation, which encompasses three main components––evolution strategies, genetic algorithms, and evolution programs. Genetic algorithm takes a possible solution to a particular problem on a simple chromosome with variable genes and uses the data structure to apply the combination of operators to these structures in order to protect vital assets and search for optimum solutions. Shortest path routing algorithms are a well-established problem and addressed by many researchers in different ways. In the present work, one such algorithm was used for routing which is based on genetic algorithm.

Kamal Kant Sharma, Inderpreet Kaur

An Investigation of Gabor PCA and Different Similarity Measure Techniques for Image Classification

A method of attributing an image to a particular category from a large collection of images is stated as Image Classification. In this paper, we propose diverse subspace techniques, which concentrate on consistency and orientations of an image, extracting color, shape, and texture data with orthogonal transformation into uncorrelated space. Initially, preprocessing is done by transforming image to HSV color space as it is similar to human color perception property. Later, most informative score features are obtained using PCA, MPCA, KPCA, and GPCA with linear and nonlinear projection onto lower dimensional space which are further classified using diverse similarity measures and neural networks. The performance analysis is carried out on large multi-class datasets such as Corel-1K, Caltech-101, and Caltech-256 and the improvised correctness rate is witnessed in comparison with several benchmarking methods.

N. Hemavathi, T. R. Anusha, K. Mahantesh, V. N. Manjunath Aradhya

A Low-Power High-Speed Double Manchester Carry Chain with Carry-Skip Using D3L

In this paper, multi-output domino 8-bit Manchester carry chain with carry-skip capability using data-driven logic is proposed. In this, two parallel carry chains compute even and odd carries independently and the carry-skip capability is applied to the odd carry chain. The dynamic power consumption is reduced using the data-driven dynamic logic, where the clock is replaced with data. The circuits are designed and simulated using Cadence Virtuoso tool with CMOS 180 nm TSMC technology. Further, the structures are implemented for 16, 32, and 64-bits. The PDP of 64-bit double Manchester carry chain with skip capability using D3L shows an improvement of 16 % among the reported ones.

J. Asha, Kala Bharathan, Anuja T. Samuel

Study and Analysis of Electrocardiography Signals for Computation of R Peak Value for Sleep Apnea Patient

In this work, identification of sleep apnea symptoms is performed using Electrocardiography (ECG). ECG wave analysis is performed for sleep apnea patient. Sleep Apnea is a type of sleep disorder and it is also recognized by polysomnography (PSG) devices. Proposed article uses eight male patient data of similar age group (ranging from 51 to 53) and similar height (ranging from 173 to 179). The article found a relationship between the varying degrees of sleep apnea and the corresponding R peak value. First, ECG signal is preprocessed and then R peak value of different apnea patients is calculated.

Mridu Sahu, Saransh Shirke, Garima Pathak, Prashant Agarwal, Ravina Gupta, Vishal Sodhi, N. K. Nagwani, Shrish Verma

Design and Implementation of Two-Wheeled Self-Balancing Vehicle Using Accelerometer and Fuzzy Logic

Two-wheeled self-balancing vehicle commercially known as “Segway” is a promising upcoming mode of transportation in many fields viz. corporate worlds, tourist place, medical field, or for personal use. In this paper, a control strategy and sensor-based control of two-wheeled self-balancing vehicle is proposed. The concept of the stabilizing the vehicle is inspired from the inverse pendulum theory. Based on steady-state space mathematical model, the entire system control is divided into two subsystems: self-balance control system (forward or backward motion balancing) and yaw control system (left or right movement). The control strategy used is fuzzy logic and is applied to both subsystems. A prototype model of the self-balancing vehicle is developed and the proposed mathematical model and control logic are verified by testing on the developed prototype.

Sunu S. Babu, Anju S. Pillai

A Time Efficient Secret Image Sharing Scheme for Group Authentication System Without Pixel Expansions

Information security is of vital importance in today’s internet world. Classified data such as military and government information are constantly transmitted over the internet. Among this, top secret data are images such as maps and surveillance footage. It is thus necessary to secure such visual data against unauthorized access. Visual secret sharing is the process of distributing “shares” of a secret image among a group of individuals. Only when all the shares have been combined, can the original secret image be obtained. In this paper, we have proposed a visual secret sharing scheme, using a simple division algorithm, for group authentication systems. This method has the advantage of being both time efficient and devoid of any pixel expansion. It can be applied to both grayscale as well as colour images and, as illustrated further ahead, ensures complete secrecy and regeneration of the original image from all the shares.

Samarpita Biswas, Nicole Belinda Dillen, Dipak Kumar Kole, Aruna Chakraborty

Imputation of Missing Gene Expressions for DNA Microarray Using Particle Swarm Optimization

While capturing gene expressions using microarray technique missing values get generated in the data set. These missing values create negative impact on downstream analysis of DNA microarray. Therefore, it is necessary to estimate them before starting further analysis. Many algorithms are proposed for imputation of missing values which are based on statistical methods. They require complete gene expression data set which is created by replacing missing values by different methods like row averaging or column averaging and later missing expressions are imputed. This may affect efficiency of algorithms. In order to deal with problem of missing values, we have proposed new method based on Swarm Intelligence which is easy to implement and apply to any kind of dataset irrespective of amount of missing values in it. This method imputes missing gene expressions in microarray data set using Particle Swarm Optimization.

Chanda Panse, Manali Kshirsagar, Dhananjay Raje, Dipak Wajgi

Deep Belief Network Based Part-of-Speech Tagger for Telugu Language

Indian languages have very less linguistic resources, though they have a large speaker base. They are very rich in morphology, making it very difficult to do sequential tagging or any type of language analysis. In natural language processing, parts-of-speech (POS) tagging is the basic tool with which it is possible to extract terminology using linguistic patterns. The main aim of this research is to do sequential tagging for Indian languages based on the unsupervised features and distributional information of a word with its neighboring words. The results of the machine learning algorithms depend on the data representation. Not all the data contribute to creation of the model, leading a few in vain and it depends on the descriptive factors of data disparity. Data representations are designed by using domain-specific knowledge but the aim of Artificial Intelligence is to reduce these domain-dependent representations, so that it can be applied to the domains which are new to one. Recently, deep learning algorithms have acquired a substantial interest in reducing the dimension of features or extracting the latent features. Recent development and applications of deep learning algorithms are giving impressive results in several areas mostly in image and text applications.

M. Jagadeesh, M. Anand Kumar, K. P. Soman

On Context Awareness for Multisensor Data Fusion in IoT

With the advances in sensor technology, data mining techniques and the internet, information and communication technology further motivates the development of smart systems such as intelligent transportation systems, smart utilities and smart grid. With the availability of low cost sensors, there is a growing focus on multi-sensor data fusion (MSDF). Internet of Things (IoT) is currently connecting more than 9 billion devices. IoT includes the connectivity of smart things which focuses more on the interactions and interoperations between things and people. Key problem in IoT middleware is to develop efficient decision level intelligent mechanisms. Therefore, we focus on IoT middleware using context-aware mechanism. To get automated inferences of the surrounding environment, context -aware concept is adopted by computing world in combination with data fusion. We conduct a comprehensive review on context awareness for MSDF in IoT and discuss the future directions in the area of context-aware computing.

Shilpa Gite, Himanshu Agrawal

CRiPT: Cryptography in Penetration Testing

The speed and the rate at which the softwares are developed worldwide to meet the customer requirement(s) is increasing day by day. In order to meet the customer target-oriented deadline(s), the softwares are developed at fast pace, often missing vital security checks in the process. These checks become crucial when the software developed are deployed over the network in the client–server architecture and more significantly in the MVC (Model View Controller) architecture scenario. Then one may ask what is the solution? Possible answer is in secure system software engineering which incorporates principles of penetration testing. Penetration testing is one of the amicable and acceptable solution. It might not be a perfect one but it is effective. A penetration test is an attack on the system with the intent of finding security loopholes, potentially gaining access to it, its functionality and data. In this work, we have proposed a methodology for implementing penetration testing. We have taken several cryptographic algorithms such as AES, DES, MD5, and SHA to demonstrate our unique methodology which blends the cryptographic techniques with software engineering principles.

Sachin Ahuja, Rahul Johari, Chetna Khokhar

Simultaneous Localization and Mapping for Visually Impaired People for Outdoor Environment

Today, mobile phones are equipped with at least half a dozen sensors such as accelerometer, gyroscope, proximity, and ambient light sensor. Mobile phone is increasingly being used to address various challenges on part of information dissemination, navigation, guidance, and short-range device-to-device communication. With the availability of sensors, there is a growing focus on the development of localization and mapping algorithms using mobile. In this paper, we focus on the simultaneous localization and mapping algorithm (SLAM) for visually impaired people. We have conducted an initial study on a visually impaired person for outdoor navigation in our University campus.

Anurag Joshi, Himanshu Agrawal, Poorva Agrawal

Automatic ECG Image Classification Using HOG and RPC Features by Template Matching

Cardiac disease is the most dangerous killer all over the world. Electrocardiogram plays a significant role for cardiac disease diagnosis. In this work with the advent of image processing technology, a confirmative tool is developed for heart disease diagnosis. The proposed work demonstrates an automatic classification system of ECG images using Histogram of Oriented Gradients (HOG) and Row Pixel Count (RPC) features. The intention of this work is to classify three major types of cardiac diseases namely Arrhythmia, Myocardial Infarction, and Conduction Blocks by template matching. The experiments were conducted on the Physiobank dataset of both normal and abnormal patients. A comparison is made for the experimental results obtained using HOG and RPC, and the performance is studied. The HOG gives a better performance of 94.0 % accuracy.

V. Rathikarani, P. Dhanalakshmi, K. Vijayakumar

Enhancement of Fuzzy Rank Aggregation Technique

The rankings of an object based on different criteria pose the problem of choice to give a ranking to that object at a position nearest to all the rankings. Generating a ranking list of such objects previously ranked is called rank aggregation. The aggregated ranking is analyzed by computing Spearman Footrule distance. The ranking list chosen by minimizing Spearman Footrule distance is NP-Hard problem even if number of lists is greater than four for partial lists. In the context of web, rank aggregation has been applied in meta-searching. However, the usage of prevailing search engines and meta-search engines, even though some of them being designated as successful, reveal that none of them have been effective in production of reliable and quality results, the reason being many. In order to improve the rank aggregation, we proposed the enhancement in the existing Modified Shimura technique by the introduction of a new OWA operator. It not only achieved better performance but also outperformed other similar techniques.

Mohd Zeeshan Ansari, M. M. Sufyan Beg, Manoj Kumar

Intelligent Telecommunication System Using Semantic-Based Information Retrieval

Artificial intelligence refers to the ability by which a system studies human ideas and applies them in computerized machines. One of the advantages of a speech recognition system is to simultaneously convert the user’s voice into text. The current telephony system provides a feature of recording a voice call, but it has no processing capability to analyze a phone call. In our project, we introduce an intelligent agent into the telephony system. An unattended phone call is recorded and a recognizer converts the analog signal into a digital signal for speech processing. The analyzer consists of a database which holds some important preprocessed keywords and the intelligent agent can formulate the state of the situation. In case of urgency, the message is examined by the parser to identify the time of the incident and the sentiment analyzer has been used to avoid prank calls. Thus, an epistle would be sent to the user in case of exigency or the voice message is stored by default method.

E. Ajith Jubilson, P. Dhanavanthini, P. Victer Paul, V. Pravinpathi, M. RamCoumare, S. Paranidharan

Minimizing Excessive Handover Using Optimized Cuckoo Algorithm in Heterogeneous Wireless Networks

In this paper we worked out to find the best solution for the two constraints in heterogeneous wireless environments: finding the best available network in a reasonable amount of time with optimized parameter values (such as cost of network should be minimum) and try to minimize the number of handovers, when mobile node is moving by overlapping of different wireless networks provided by different network providers. Here the decision problem is formulated as multiple objective optimization problems and simulated using cuckoo optimizing algorithm. In this paper our simulation result shows that the number of handovers can be minimized if we take optimized network parameter values.

Salavadi Ananda Kumar, K. E. Sreenivasa Murthy

Audio Songs Classification Based on Music Patterns

In this work, effort has been made to classify audio songs based on their music pattern which helps us to retrieve the music clips based on listener’s taste. This task is helpful in indexing and accessing the music clip based on listener’s state. Seven main categories are considered for this work such as

devotional, energetic, folk, happy, pleasant, sad

and,

sleepy

. Forty music clips of each category for training phase and fifteen clips of each category for testing phase are considered; vibrato-related features such as jitter and shimmer along with the mel-frequency cepstral coefficients (MFCCs); statistical values of pitch such as min, max, mean, and standard deviation are computed and added to the MFCCs, jitter, and shimmer which results in a 19-dimensional feature vector. feedforward backpropagation neural network (BPNN) is used as a classifier due to its efficiency in mapping the nonlinear relations. The accuracy of 82 % is achieved on an average for 105 testing clips.

Rahul Sharma, Y. V. Srinivasa Murthy, Shashidhar G. Koolagudi

Software Reliability Based on Software Measures Applying Bayesian Technique

Safety critical systems such as nuclear power plants, chemical plants, avionics, etc., see an increasing usage of computer-based controls in regulation, protection, and control systems. Reliability is an important quality factor for such safety critical digital systems. The characteristics of such digital critical systems are explicitly or implicitly reflected by its software engineering measures. Therefore, these measures can be used to infer or predict the reliability of the system. Hence Software Engineering measures are the best indicators of the software reliability. This paper proposes a methodology to predict software reliability using software measures. The selected measures are used to develop Bayesian belief network model predict reliability of such safety critical digital systems.

Anitha Senathi, Gopika Vinod, Dipti Jadhav

On Context Awareness and Analysis of Various Classification Algorithms

Internet of Things (IoT) is currently connecting 9 billion devices and is expected to grow by three times in next 5 years, and hence will connect over 27 billion devices. IoT is touching every walk of human life such as health care, smart utilities, smart grid, smart homes, and smart spaces. To make things or object smart, IoT middleware makes use of appropriate intelligent mechanisms. Context-aware solutions are addressing the challenges of IoT middleware, hence becoming an important building block. We provide an analytical study of various algorithms for classification. We consider three algorithms and test the performances of each on small dataset as well as on larger dataset with 1969 instances. Performance evaluation is done using Mean Square Error and Absolute Mean Square Error.

Umang Nanda, Shrey Rajput, Himanshu Agrawal, Antriksh Goel, Mohit Gurnani

Neural Network-Based Automated Priority Assigner

The testing of a system starts with the crafting of test cases. Not all the test cases are, however, equally important. The test cases can be prioritized using policies discussed in the work. The work proposes a neural network model to prioritize the test cases. The work has been validated using backpropagation neural network. 200 test cases were crafted and the experiment was carried out using 2, 5, 10, 15, and 20 layers neural network. The results have been reported and lead to the conclusion that neural network-based priority analyzer can predict the priority of a test.

Harsh Bhasin, Esha Khanna, Kapil Sharma

Design of IMC Controller for TITO Process with Dynamic Closed-Loop Time Constant

An IMC controller is designed for two input and two output (TITO) processes with dead time where the closed-loop time constant is varied depending on the process operating condition. For a TITO process, proper decoupling can minimize the loop interaction. Here, we develop an inverted decoupler so that the TITO process can be decoupled into two SISO processes. Each SISO process is considered to be a first-order process with dead time (FOPDT) and IMC controller is designed for each FOPDT process. To make the controller structure proper, we incorporate a first-order filter with closed-loop time constant (λ) which is the only tunable parameter. Instead of a fixed value, dynamic nature is incorporated in selecting the value of λ based on a simple mathematical relation. Superiority of the proposed IMC controller is verified through performance comparison with the well-known multiloop tuning relations.

Parikshit Kumar Paul, Chanchal Dey, Rajani K. Mudi

All Optical SOA-MZI-Based Encryption Decryption System Using Co Propagating Optical Pulses and CW Wave at 40 Gb/s

This paper presents novel optical encryption and decryption systems using a semiconductor optical amplifier at 40 Gb/s. Proposed scheme exploits cross-phase modulation phenomenon in SOA. Our design is mainly based on SOA Mach-Zehnder interferometer structure, optical couplers, CW light, and EDFA. We demonstrate that our implementation is more feasible than conventional SOA-MZI encryption system, where only single optical pulse source is used. Experimental evaluation using eye diagrams shows robustness of our proposed encryption decryption system against eavesdropping.

Vipul Agarwal, Vijayshri Chaurasia

Exploiting Common Nodes in Overlapped Clusters for Path Optimization in Wireless Sensor Networks

For operational efficiency, most WSNs employ clustering approach where the cluster head is responsible for finding the shortest path to the sink for all of its cluster nodes. While clustering, it is a common observation that the clusters often tend to overlap, and hence nodes in the overlap region are capable of communicating directly with neighboring nodes within one hop distance. However, traditionally the nodes belonging to one cluster are prohibited from making overtures with other nodes outside its cluster. A common node exploitation (CNE) approach is proposed that deviates from this traditional approach and paves a methodology to exploit the proximity of the common nodes to the other nodes. Two algorithms are developed based on CNE approach for location aware, randomly deployed WSNs to find alternate, shorter, and optimized path to the sink. Simulations performed have shown that the CNE approach outperforms traditional approaches.

Devendra Rao BV, D. Vasumathi, Satyanarayana V. Nandury

Maximizing Availability and Minimizing Markesan for Task Scheduling in Grid Computing Using NSGA II

Large distributed platform for computationally exhaustive applications is provided by the Computational Grid (CG). Required jobs are allotted to the computational grid nodes in grid scheduling in order to optimize few characteristic qualities of service parameters. Availability is the most important parameter of the computational nodes which is the likelihood of computational nodes accessible for service in specified period of time. In this paper, emphasis has given on optimization of two quality of service (QoS) parameter makespan (MS) and availability grid system for the task execution. Since, the scheduling problem is NP-Hard, so a meta-heuristics-based evolutionary techniques are often applied to solve this. We have proposed NSGA II for this purpose. The performance estimation of the proposed Availability Aware NSGA II (AANSGA II) has been done by writing program in Java and integrated with gridsim. The simulation results evaluate the performance of the proposed algorithm.

Dinesh Prasad Sahu, Karan Singh, Shiv Prakash

Moving Object Detection for Visual Surveillance Using Quasi-euclidian Distance

Moving object detection is a fundamental step for visual surveillance system, other image processing, and computer vision applications. The most popular and common technique for moving foreground detection is background subtraction. In dynamic background, Gaussian Mixture Model performs better for object detection. In this work, a GMM-based background model is developed. This work proposes a quasi-euclidian distance measure in order to measure the variation in terms of distance, between modeled frame and test frame. To classify the pixel, this distance is compared with a suitable threshold. The connected component and blob labeling has been used to improve the model with a threshold. Morphological filter is used to improve the foreground information. The experimental study shows that the proposed work performs better in comparison to considered state-of-the-art methods in term precision, recall, and

f

-measure.

Dileep Kumar Yadav, Karan Singh

IoTA: Internet of Things Application

The world is changing, so is our lifestyle which is getting dependent on the numerous electronic devices. The very idea of what would happen if these entities start communicating with each other is enthralling and amazing. In this paper we explore the world of IoT (Internet of Things) which is quite new and unexplored. Today, many vendors are logging into this field and are designing new and innovative hardware and software applications; so in the near future communication is bound to happen not only between electronic devices which are in LoS (Line of Sight) but also between those devices that are located remotely and would communicate with each other in a distributed computing domain using RPC (Remote Procedure calls) in a client-server architecture environment. To our idea and knowledge this is the first major foray into this domain and to make it happen we have undertaken a case study of HMIS (Health care Management Information System) and analyzed its results.

Sachin Ahuja, Rahul Johari, Chetna Khokhar

Improving Performance of Wireless Mesh Networks Through User Association Method

IEEE 802.11-based wireless mesh networks (WMNs) are emerging as the promising technology to provide last-mile broadband Internet access. A WMN is composed of mesh clients (MCs) and mesh access points (MAPs). A mesh client has to associate with one of the MAPs in order to access the network. Since the client performance depends on the selected MAP, how to select a best MAP is an open research problem. The traditional association mechanism used in WLAN, is based on received signal strength (RSS) which received criticism in the literature as it does not consider many important factors such as access point load, channel conditions, medium contention, etc. This paper proposes a novel scheme of MAP selection in WMNs. The basic idea is to reduce the negative impact of low throughput clients over high throughput clients. The performance of our scheme is evaluated through simulations and we show that our scheme performs better than RSS-based association scheme.

G. Vijaya Kumar, C. Shoba Bindu

Characterization of Human Fingernails Using Iterative Thresholding Segmentation

In this paper, we present new fingernail biometric as a possibility in pattern recognition and establish its prospects experimentally. In this perspective composition, we propose a method adapted in three stages. In stage one, the finger biometric which exhibits Gaussians of objects is identified as background and foreground elements is modeled for segmentation of relevant regions. Preliminary methods include intensity adjustment to reduce noise, contrast enhancement for edge detection, and morphological operation to improve finger region from noisy background. In stage two, iterative histogram-based thresholding of multispectral image (R, G, and B components) to binarize fingernail region from finger object is adapted. In stage three, geometric feature calculation makes it possible to identify fingernail into different shapes as oval, round, and rectangular. Nail dimension and shape features are used for the recognition. With this designed system, we are able to achieve 80 % recognition rate and initial results are encouraging.

N. S. Kumuda, M. S. Dinesh, G. Hemantha Kumar

Confidential Terms Detection Using Language Modeling Technique in Data Leakage Prevention

Confidential documents detection is a key activity in data leakage prevention methods. Once the document is marked as confidential, then it is possible to prevent data leakage from that document. Confidential terms are significant terms, which indicate confidential content in the document. This paper presents confidential terms detection method using language model with Dirichlet prior smoothing technique. Clusters are generated for training dataset documents (confidential and nonconfidential documents). Language model is created separately for confidential and nonconfidential documents. Expand nonconfidential language model in a cluster using similar clusters, which helps to identify the confidential content in the nonconfidential documents. Smoothing assigns a nonzero probability value to unseen words and improves accuracy of the language model.

Peneti Subhashini, B. Padmaja Rani

ECG-Driven Extraction of Respiration Rate Using Ensemble Empirical Mode Decomposition and Canonical Correlation Analysis

Respiratory signal and electrocardiogram are correlated to each other. In this paper, respiration rate has been extracted from ECG. We purpose a novel combination of Canonical Correlation Analysis (CCA) and Ensemble Empirical Mode Decomposition (EEMD) in order to remove the artifacts, and we have estimated the respiratory rate from the denoised ECG by creating the envelope of the denoised signal. The canonical correlation corresponding to the artifacts was removed on the basis of correlation coefficient of denoised signal and ground truth signal. The MIT-Polysomonographic and Apnea-ECG databases of physionet bank were used to acquire the ECG signals. Real-time Baseline wander noise from MIT-NSTDB was added to each record, and the respiratory rate determined was compared with the corresponding respiratory signals. The average signal-to-noise ratio improvement in case of denoising using EEMD-CCA is 20.8989 db. The average BPM error in respiration rate derived from ECG denoised from EEMD is ±2.5 BPM.

Vineet Kumar, Gurpreet Singh

An Efficient On-Chip Implementation of Reconfigurable Continuous Time Sigma Delta ADC for Digital Beamforming Applications

SONAR and RADAR makes use of multiple beamforming systems. A novel Onboard Digital Beamforming (DBF) system suitable for various applications is implemented with mixed signal design of Sigma Delta ADC architecture. FPGA is configured as a Reconfigurable On-chip Sigma Delta ADC and analyzed for a multichannel beamforming system with Spartan 6, Virtex 4, and Virtex 6 FPGA. With the architectural variation, major advantages can be seen in SONAR beamforming and similar array processing applications.

Anjani Harsha Vardhini Palagiri, Madhavi Latha Makkena, Krishna Reddy Chantigari

Random Forest for the Real Forests

A forest is a vast area of land covered predominantly with trees and undergrowth. In this paper, adhering to cartographic variables, we try to predict the predominant kind of tree cover of a forest using the Random Forests (RF) classification method. The study classifies the data into seven classes of forests found in the Roosevelt National Forest of Northern Colorado. With sufficient data to create a classification model, the RF classifier gives reasonably accurate results. Fine-tuning of the algorithm parameters was done to get promising results. Besides that a dimensionality check on the dataset was conducted to observe the possibilities of dimensionality reduction.

Sharan Agrawal, Shivam Rana, Tanvir Ahmad

Hybrid GA and PSO Approach for Transmission Expansion Planning

Metaheuristic techniques are enormously being used nowadays for their applications in field like Power system and are being applied to many optimization problems of power system due to difficult approach of classical methods. Transmission expansion planning (TEP) is a challenging task to deal in power system. A new approach, hybrid genetic algorithm particle swarm optimization (HGAPSO) for solving TEP problem, is introduced to eliminate the drawback of GA and PSO. Problems of immature convergence in particle swarm optimization (PSO) and low convergence speed in genetic algorithm (GA) mitigate to the hybridization of both techniques. Proposed HGAPSO Algorithm is tested for three standard electric test systems for TEP problem in MATLAB tool. Experimental results found by HGAPSO are compared with GA and PSO Algorithm to test its performance for TEP problem.

Shilpi Sisodia, Yogendra Kumar, Arun Kumar Wadhwani

Pattern Detection Framework for MRI Images and Labeling Volume of Interest (VoI)

In the current scenario of Biomedical Research, the Magnetic Resonance Imaging (MRI) images visual analytics processing applications are facing challenges of the use of different techniques under different frameworks supported by different software tools. The establishment of different frameworks under different software tools and migration of data from one framework to another as well as one tool or environment to another poses critical difficulties and large time consumption. To reduce this hassle, the need of common framework is identified and the same is undertaken in this work. To address this issue, a framework MRI Image Pattern Detection Framework (MIPDF) is proposed to take care for the reduction of cited hassle and improved visual analytics to support medical professionals in their act of detection and diagnosis of diseases by identifying regularity and irregularity with improved visualization and analytics results.

Rupal Snehkunj, Richa Mehta, Aashish N. Jani

A Distributed Spanning Tree-Based Dynamic Self-Organizational Framework for Web Server

Web services are playing a very important role in various business-based applications. There are an enormous amount of web services present and they are creating a huge web traffic. The organizations are trying to reduce the web traffic by having cluster-based web servers. It is a vital task to handle these cluster-based web servers while they have a varying load on it. These servers should be highly scalable and available. Load balancing is an important technique to provide rapid response to the requests of the client. As the process of load balancing occurs fault tolerance should be taken care of. This paper focuses on the scalable, fault-tolerant, and load balancing mechanism of cluster-based web servers. The distributed spanning tree structure is used for balancing the client requests among the cluster-based servers. An architecture based on DST is proposed in this paper for cluster-based web servers.

J. Amudhavel, U. Prabu, N. Saravanan, P. Dhavachelvan, R. Baskaran, V. S. K. Venkatachalapathy

Recursive Ant Colony Optimization Routing in Wireless Mesh Network

The ant colony optimization algorithm is used to find the optimal path based on the behavior of an ant while searching a food. It will communicate with other ants using the pheromone to find the best solution. In this paper, we introduce recursive ant colony optimization (RACO) in the wireless mesh network. This technique is used to subdivide a large network into smaller networks and based on the network, the shortest path is found in each subproblem, and finally it is combined to generate an optimal path for the network. In each subproblem, the iteration is performed recursively to obtain the shortest path in that subproblem. In our paper, we use recursive ant colony to reduce redundancy in connection and so the data will transfer in less time effectively. RACO is used to find best solutions more accurate than the other ant colony systems. Isolation of a subproblem is reduced in RACO.

J. Amudhavel, S. Padmapriya, R. Nandhini, G. Kavipriya, P. Dhavachelvan, V. S. K. Venkatachalapathy

Image Processing Representation Using Binary Image; Grayscale, Color Image, and Histogram

This paper presents digital image processing and its representation using binary image; grayscale, color images with the help of additive color mixing, subtractive color mixing, and histogram. It is also discusses the fundamental steps involved in an image processing such as image achievement, image development, image renovation, compression, wavelets, multi-resolution processing, morphological processing, representation, description and interpretation. Finally, it presents the per-pixel and filtering operations like invert filter, grayscale, brightness and color splitting filter.

Vaka Murali Mohan, R. Kanaka Durga, Swathi Devathi, K. Srujan Raju

A Vector Space Model Approach for Web Attack Classification Using Machine Learning Technique

Web applications usage is increasing in online services in many ways in our day-to-day life. Business service providers have started deploying their business over the web through various e-commerce applications online. The growth of online web application increases the web complexity and vulnerability in terms of security which is a major concern in the current web security research. The extensive growth of various types of web attacks is a severe threat to web security. HTTP requests are usually secret code into a web attack spread through the injection and allow them to perform malicious actions on remote systems to execute arbitrary commands. This paper proposes an efficient approach for web attack classification, using a vector space model approach (VSMA), to improve the detection and classification accuracy. It is able to automatically classify the attacks from valid requests to detect the specific web attacks. The evaluation measure shows high precision and low recall rates than the existing classifiers in comparison.

B. V. Ram Naresh Yadav, B. Satyanarayana, D. Vasumathi

Formal Verification of Secure Authentication in Wireless Mesh Network (SAWMN)

Wireless mesh network (WMN) is considered to be an evolving technique because of self-configuration and adaptive features, and it supports large-scale network especially in an organization and academics. As with any network, communication among nodes plays an important role, when two nodes in a network communicate with each other via the internet, secure authentication is an imperative challenge. In literature, there are many approaches that have been suggested to deliver a secure authentication between nodes in WMN; however, all these outlines contain some disadvantages, i.e., management cost of the public key and system complexity. In this paper, a Secure Authentication in Wireless Mesh Network (SAWMN) approach is proposed which overcomes these drawbacks and provides an efficient authentication to the mesh clients. Further, SAWMN results have been shown simulated on AVISPA SPAN to ascertain the authenticity of the proposed approach.

Ninni Singh, Hemraj Saini

Visual K-Means Approach for Handling Class Imbalance Learning

In this paper, a novel clustering algorithm dubbed as Visual K-Means (VKM) is proposed. The proposed algorithm deals with the uniform effect which is very much visible in k-means algorithm for skewed distributed data sources. The evaluation of the proposed algorithm is conducted with 10 imbalanced dataset against five benchmark algorithms on six evaluation metrics. The observations from the simulation results project that the proposed algorithm is one of the best alternatives to handle the imbalanced datasets effectively.

Ch. N. Santhosh Kumar, K. Nageswara Rao, A. Govardhan

A Framework for Discovering Important Patterns Through Parallel Mining of Protein–Protein Interaction Network

Association rule mining can be applied in the field of bioinformatics for identification of co-occurrences between various biological elements such as genes and protein. In bioinformatics, protein–protein interaction network provides useful information regarding the functions of protein. Association analysis has been used for identification of frequently occurring interactions among the proteins in the network for predicting the functions of proteins. As the amount of data is increasing exponentially, parallel implementation of association analysis for identification of co-occurrences between proteins in protein–protein interaction network will be more efficient, fast, and scalable. In this paper we proposed an efficient framework for association analysis of frequently occurring pattern in the protein–protein interaction network. The algorithm has been parallelized using Hadoop software. The performance view of the parallel algorithm has been depicted in graph and it shows that the parallel version is more effective than the sequential one.

Sarbani Dasgupta, Banani Saha

Implementing DNA Encryption Technique in Web Services to Embed Confidentiality in Cloud

Hottest buzzword of this decade is “Cloud Computing”—which has been considered as one of the potential solutions to our increasing demand for accessing, processing, storing, and using provisioned resources over the internet. However, with so many boons, it comes along with some curses as security and trust issues. There are many security issues within the cloud, and Information disclosure is a big threat to a cloud user when the information is transferred over the network using web services. In this paper, we have focused on to provide confidentiality to the user while using cloud-based web services, and an approach has been proposed for selective encryption of XML elements so as to provide confidentiality and prevent XML document form improper information disclosure. The technique used for encrypting the selective XML elements is Deoxyribonucleic Acid (DNA) Encryption. Proposed technique selectively encrypts the elements of XML file using DNA sequencing.

Gunjan Gugnani, S. P. Ghrera, P. K. Gupta, Reza Malekian, B. T. J. Maharaj

An Efficient Motion Detection Method Based on Estimation of Initial Motion Field Using Local Variance

Background subtraction is a facile way to localize the moving object in video sequences which provide sufficient different intensities of foreground pixels from the background. It has been observed that the motion detection task can be more challenging in some complex scenes, which exhibit sudden or gradual illumination, varying speed of object, similarly colored background, and shadows. In that concern, we propose an efficient motion detection method based on the initialization of background, which is further used for the foreground detection. Under this formulation, we have adopted the local property of the initial motion field to get the suitable threshold condition to make it generic for the adequate visual representation of foreground pixel intensity. The effectiveness of this method can be seen when it is compared qualitatively and quantitatively to other well-known background subtraction methods. The experimental results show that it can work well in static and dynamic backgrounds condition.

Satrughan Kumar, Jigyendra Sen Yadav

A Survey on Texture Image Retrieval

R

e

trieving images from the large databases has always been one challenging problem in the area of image retrieval while maintaining the higher accuracy and lower computational time. Texture defines the roughness of a surface. For the last two decades due to the large extent of multimedia database, image retrieval has been a hot issue in image processing. Texture images are retrieved in a variety of ways. This paper presents a survey on various texture image retrieval methods. It provides a brief comparison of various texture image retrieval methods on the basis of retrieval accuracy and computation time with the benchmark databases. Image retrieval techniques vary with feature extraction methods and various distance measures. In this paper, we present a survey on various texture feature extraction methods by applying variants of wavelet transform. This survey paper facilitates the researchers with background of progress of image retrieval methods that will help researchers in the area to select the best method for texture image retrieval appropriate to their requirements.

Ghanshyam Raghuwanshi, Vipin Tyagi

Converged OAM

Operation, Administration, and Maintenance (OAM) is a toolset that can be used for managing different networking layers. OAM can detect and isolate the faults and also be used for performance monitoring of a network, which helps in reducing the operational cost. OAM mechanism is important for networks that are required to deliver network performance and availability objectives. OAM toolset is defined for different layers in protocol stack. This paper summarizes OAM toolset supported by Ethernet, MPLS, and IP networks. Since many standard bodies are working on enhancement of OAM, it results in multiple OAM standards which are performing the same functionality. Main objective of this paper is to detail scattered OAM toolset of Ethernet, MPLS, and IP networks and to propose a solution for OAM toolset convergence, which can be beneficial for service provider and customer.

Prashant Saste, Jason Martis

Rule Reduction of a Neuro-Fuzzy PI Controller with Real-Time Implementation on a Speed Control Process

This study is an attempt for neuro-fuzzy implementation of a prior-designed fuzzy PI controller (FPIC) with reduced number of rules but without sacrificing the controller performance up to a certain extent. To accomplish the goal, backpropagation-based learning algorithm is used to model a connectionist fuzzy controller based on an input–output data set. The resultant fuzzy controllers with reduced rule sets are much faster in operation and cheaper due to lesser memory space requirement. Effectiveness of the designed fuzzy controllers is studied through simulation as well as real-time experimentation on a servo speed control application. Both the simulation and experimental results substantiate the efficacy of the designed neuro-fuzzy controllers with lesser number of rules for approximating the behaviour of a nonlinear fuzzy controller with considerably larger rule base.

Arijit Ghosh, Satyaki Sen, Chanchal Dey

Construction of Binary and Nonbinary LDPC-like Codes from Kernel Codes

Low Density Parity Check (LDPC) codes have been of great interest to researchers due to its low complexity in encoding as well as decoding. Since the introduction of Turbo codes in 1993, importance of LDPC codes has been widely explored. Various techniques have been introduced for encoding and decoding of low density parity check codes based on algebraic structures, codes on graphs, etc. In this paper, a new method of constructing binary and nonbinary LDPC-like codes from Kernel codes defined over groups is discussed. Also, we show that constructions of binary and nonbinary LDPC-like codes are particular cases of our proposed method.

C. Pavan Kumar, R. Selvakumar, Raghunadh K. Bhattar

Simulation-Level Implementation of Face Recognition in Uncontrolled Environment

Humans rely on their visual ability to perceive and analyze the visual world. This ability if given to computers can yield scientific and relevant details about the things around us. Recognizing face under uncontrolled environment is still a challenging task, especially under head pose variation. Initially, the gesture containing test input face is estimated; it is then transformed into a reference pose which is already learnt. We have analyzed many existing available techniques for recognizing face for different gestures and proposed a novel system using a combination of support vector machine (SVM) and K-nearest neighbor (K-NN). The system is implemented using MATLAB and simulated using Modelsim. It has been tested on publicly available face databases under varying head poses. The proposed model was trained by randomly selecting 10 images, each of 12 unique individuals, thus 120 images were used for training. The system was then tested by considering 93 different poses of all the 12 unique individuals, thus 1116 images were used for testing. A demo code, along with train images, test images, and results obtained from the proposed system can be downloaded from

http://goo.gl/S5ofYR

.

Steven Lawrence Fernandes, G. Josemin Bala

Analyzing State-of-the-Art Techniques for Fusion of Multimodal Biometrics

Multimodal systems used for face recognition can be broadly classified into three categories: score level fusion, decision level fusion, and feature level fusion. In this paper, we have analyzed the performance of the three categories on various standard public databases such as Biosecure DS2, FERET, VidTIMIT, AT&T, USTB I, USTB II, RUsign, and KVKR. From our analysis, we found that score level fusion approach can effectively fuse multiple biometric modalities, and is robust to operate in less constrained conditions. In the decision fusion scheme, each decision is made after the improvement of the classifier confidence hence the recognition rate obtained is less compared to score level fusion. Feature level fusion requires less information and performs better than decision level fusion, but its recognition rate is less compared to score level fusion.

Steven Lawrence Fernandes, G. Josemin Bala

Genetic Algorithmic Approach to Mitigate Starvation in Wireless Mesh Networks

Wireless mesh networks (WMNs) have a set of self-organized and dynamically self-configurable nodes and each node may act as a router and a host. The performance of the applications running on the nodes that are more than one-hop away from the gateway suffers by starvation. Starvation occurs in a situation that nodes close to the gateway capture the resources (channel) rather than giving the chance to the nodes situated in longer distance to the gateway. In this paper, to avoid starvation, a cross-layer technique is employed to identify optimal contention window (CW) for individual nodes. The size of CW is based on the network layer quality of service (QoS) parameters and the available channel. In this work, the scheduling method uses a genetic algorithm (GA) to mitigate the starvation by selecting optimal CW. Simulations are conducted using multimedia traffic and results are compared with the priority-based scheduling method. Performance of the proposed algorithm is evaluated in terms the parameters such as throughput, packet delivery ratio, end-to-end delay and number of cache replies used. The comparison shows that GA optimization to mitigate the starvation works better than the priority-based starvation avoidance method.

Potti Balamuralikrishna, M. V. Subramanyam, K. Satya Prasad

Handwritten Indic Script Identification from Document Images—A Statistical Comparison of Different Attribute Selection Techniques in Multi-classifier Environment

Script identification from document images is an essential task before choosing script-specific

OCR

for a Multi-lingual/Multi-script country like India. The problem becomes more complex when handwritten document images are considered. Several techniques have been developed so far for

HSI

(Handwritten Script Identification) problem and the work is still in progress. But the issue of dimensionality reduction of the feature set for script identification problem has not been addressed in the literature till date. This paper presents a statistical performance analysis of different attribute selection techniques in a multi-classifier environment for

HSI

problem on Indic scripts. A

GAS

(Greedy Attribute Selection) technique for

HSI

problem has also been proposed here. Encouraging outcomes are found observing the complexities of handwritten Indic scripts.

Sk Md Obaidullah, Chayan Halder, Nibaran Das, Kaushik Roy

An FPGA-Based Embedded System for Real-Time Data Processing

An embedded architecture for high-speed data acquisition and display system is proposed for continuous data monitoring in real-time. In addition to this, a coherent averaging block is added as an IP core which average out the random noise of any signal under process. An analog to digital converter (ADC) AD9265 having maximum sampling speed of 125 MSPS is interfaced with the embedded system to digitize the signal. The entire embedded system has been implemented on FPGA using VIRTEX-II PRO device. The experimental results of the proposed work are flashed on the front panel of the LCD in real-time.

Pradyut Kumar Sanki

Clustering of Noisy Regions (CNR)—A GIS Anchored Technique for Clustering on Raster Map

In this proposed work, a GIS anchored system has been approached, which initially takes as input, a digitized map, generally of a very large region, with the population of the common mass in different wards/areas fed as associated data and finally it suggests the most suitable locations for constructing a number of utility service centers. This target can be achieved by formation of clusters of the wards, where only the adjacent regions are the part of any particular cluster. Particularly, for the third world countries like India, not only the heavily populated wards, but also some small populations such as small slum areas, generally locating outskirts of the major cities, which could be viewed as noise due to their small populations, would also have to be considered for the purpose. One such popular and well-accepted clustering technique handling noise is DBSCAN Ester et al. (A density-based algorithm for discovering clusters in large spatial databases with noise,

1996

). But, the major demerit of DBSCAN algorithm is that it cannot take as input, the number of clusters to be generated. This is quiet impractical, as because the number of centers to be constructed is decided beforehand, by some planning committee. Moreover, DBSCAN simply omits the noise areas. But, with a motto to provide equal opportunity for every citizen, care should be taken for all parts of the population. The proposed technique takes a step forward towards the solution.

Anirban Chakraborty, J. K. Mandal, Pallavi Roy, Pratyusha Bhattacharya

Performance of Brightness Enhancement Technique for Narrow-Band and White-Band Images

Image enhancement technique plays a vital role in image analysis. White-band images (WBI) and narrow band images (NBI) are the two types of images that are widely used in capsule endoscopy. It is a general practice to compress the images and process them at the chip level embedded in the capsule in order to minimize the power consumption. In the due course, it is often required to enhance the features of the image so that, most favorable information from the images can be extracted. Loss of naturalness in the image while processing for image enhancement is observed. In this paper, a technique called brightness enhancement followed by color restoration is suggested for images with non-linear illumination. The technique employs a bright pass filter which acts on reflectance and luminance forms of image obtained after decomposing of the original image. The simulation experiment is carried on both white-band images and narrow-band images.

Sathi Raju Challa, D. V. Rama Koti Reddy

Z Transformation-Based High Payload Authentication Technique with Higher Region of Convergence Value (ZATHRoc)

In this paper, a Z transformation-based authentication technique has been proposed with higher Region of Convergence (ROC) value. Sequentially, five bits from the authenticating mask in row major order are considered and embedded into composite real as well as imaginary components of second, third, and fourth transform domain coefficients keeping the low frequency component unaltered which is further utilized for adjustment. The proposed method provides a good secure scheme in terms of robustness and sensitivity of higher ROC of Z transform domain and also in terms of the inclusion of random chaotic map. Comparisons have been made with existing methods such as AINCDCT (2011), Luo’s Method (2011), SCDFT (2008), and AHRocZ (2015) which exhibit a better performance with proper visual quality.

J. K. Mandal, Suman Mahapatra

Breast Tissue Density Classification Using Wavelet-Based Texture Descriptors

It has been well established that the risk of breast cancer development is associated with increased breast density. Therefore, characterization of breast tissue density is clinically significant. In the present work, the potential of various wavelet energy descriptors (derived from ten different compact support wavelet filters) has been investigated for breast tissue density classification using kNN, SVM, and PNN classifiers. The work has been carried out on the MIAS dataset. The highest classification accuracy of 96.2 % is achieved using the kNN classifier Haar wavelet energy descriptors.

Jitendra Virmani, Kriti

On New Families Related to Bernoulli and Euler Polynomials

In this article, the Laguerre-Gould Hopper based Bernoulli and Euler polynomials are introduced using operational methods. These polynomials are framed within the context of monomiality principle and their important properties are established. The operational rules and differential equations for these polynomials are also derived.

Subuhi Khan, Mahvish Ali

Vehicular Ad Hoc Networks: Trimming Pile-Ups in Data dissemination Using HTPVANET Algorithm

The extensive growth of traffic on highways and junctions hampers the safe and effective movement of traffic. The ascending car accident rate has led to research on deriving optimal solution to streamline the traffic and to take alternate measures to reduce accidents. The promise of intelligent traffic system and early warning system enables effective monitoring of road mishaps. VANET is a subset of MANET. VANET is a self-organizing network in which each vehicle is represented as a mobile node to form MANET. Communication can take place between V2V, V2I, and I2V. Due to heavy traffic on roads, road accidents are increasing day by day. We aim to find a solution that targets on reduction of factors like redundancy, latency by refining message passing mechanism between vehicle-to-vehicle (V2V), and vehicle-to-infrastructure (V2I) when an accident takes place. In this paper, the suggestive measures for reducing redundancy and latency are discussed.

R. V. S. Lalitha, G. Jaya Suma

Information Extraction from Research Papers Based on Statistical Methods

In the research field we require more time to read a single research paper; it also consumes more time to find the algorithms and limitations of the paper. So we require a fast reading system to identify this problem. This paper identifies the algorithms or techniques, or methods, and limitations of a research paper, and also classifies the area of the algorithm. Key phrases are sets of words that elucidate the relationship between context and content in the document. Key phrases are identified from the document and algorithms or techniques, or methods of that paper are extracted. Keywords are a subset of words that contain important information and the area is classified. Cue words are those that contain meaningful information used to identify the limitations of the paper.

Selvani Deepthi Kavila, D. Fathima Rani

Artificial Neural Network Classifier for Intrusion Detection System in Computer Network

An intrusion detection system is a security management tool for computers and networks. An intrusion is mainly a try to violation of network security requirements and norms. Detection deals with the countermeasures to detect such attacks. The goal of the intrusion detection system mechanism is to observe the network traffic if any packet whose pattern varies when standard to the normal behavior is said to be an anomaly and hence an attack. The main objective of this paper is to perform data preprocessing on KDD CUP 99 dataset to select a subset of features to advance the speed of the detection process. A modified Kolmogorov–Smirnov correlation-based filter algorithm is used to select features. And propose an intrusion detection model using PSO-WENN; this can classify the attacks effectively and reduce the number of false alarms generated by an intrusion detection system and improve the attack detection rate.

N. Lokeswari, B. Chakradhar Rao

Edge Detection on an Image Using Ant Colony Optimization

The edge detection is a primary technique in image processing which gives the form of the object in an image. The absolute result of edge detection method can build the boundary of the object and also the curves of the surfaces, and in image segmentation registration and object detection, edge detection method is used. There are many approval methods for edge detection, such as model-based approach, first-order derivation of edge detection, second-order derivation of edge detection, and Canny edge detection. In existing system, we used Canny method while detecting the edge of an image, and when we are using there are some defaults like noise sensitivity. To get a better result of edge detection method, we are going to propose an optimization algorithm named Ant colony optimization algorithm.

P. Hinduja, K. Suresh, B. Ravi Kiran

Cryptography Technique for a Novel Text Using Mathematical Functions

The encryption/decryption process is applied to text to provide security. In this work, I propose a novel method to perform encryption and decryption. In this process, one text is taken. Text is divided into set of three components, together with a private key. I built a content-addressable memory (CAM). This represents the encrypted text. The decryption process will do it in a reverse way. The benefit of the proposed model is that the plaintext and ciphertext will not be in the same dimension and the ciphertext was also represented in image format. The entire process uses a secret key for the process of encryption.

P. Prudvi Raj, Ch. Seshadri Rao

A New Hybrid Approach for Document Clustering Using Tabu Search and Particle Swarm Optimization (TSPSO)

Clustering of text documents is the quickest developing research area, because of the availability of vast amount of information in an electronic form. To solve this document cluster analysis difficulties more efficiently and quickly, this paper proposes a hybrid method using tabu search particle swarm optimization (TSPSO). First, the automatic merging optimization clustering (AMOC) algorithm was performed for the formation of clusters and then implemented the optimization model using the variance ratio criterion (VRC) as fitness function .Second, this paper combines TS and PSO algorithm to use the exploration of both algorithms and to avoid flaws of both algorithms .The testing of TSPSO algorithm is performed on several standard datasets, and the results are compared with PSO and TS. So, the proposed TSPSO is efficient and effective for the problem of document clustering; we have tested PSO, TS, and our proposed TSPSO algorithm on various text document collections.

T. Haribabu, S. Jayaprada

An Effective and Efficient Clustering Based on K-Means Using MapReduce and TLBO

A plethora of clustering methods were developed since time unknown, but these methods have failed to prove that they are flawlessly efficient and also to give an optimized result in the field it might be that, parallel programming technique like MapReduce and evolutionary methods of computation address solutions to this issue as well. We use this limitation as an advantage to combine a new efficient method for optimization, ‘Teaching Learning based Optimization (TLBO)’ and a new parallel programing technique called MapReduce to develop a new approach to provide good quality clusters. In this paper, teaching learning based optimization is collaborated along with Parallel

K

-means Using MapReduce. Firstly, it makes

K

-means with MapReduce to work with massive amount of data and after that it takes the advantage of global search ability of TLBO to provide a global optimal result.

Praveen Kumar Pedireddla, Sunita A. Yadwad

Detection of Sinkhole Attack in Wireless Sensor Network

In this paper, we proposed an efficient rule-based intrusion detection system for identifying sinkhole attacks in Wireless Sensor Networks (WSN). The sensor nodes in network are deployed in various hostile environments. The nature of WSNs is wireless and hence, security is the major challenging issue. Sinkhole attack is the major common internal attack on WSNs. These attacks are performed by creating a malicious node with the highest transmission range to the base station. Then this node broadcast sends fake routing message to all its neighbor nodes. We considered popular link quality-based multi-hop routing protocol named as Mint-Route protocol. To identify sinkhole attack, we have implemented an IDS system which consists of suitable rules. These rules will allow the IDS to detect the malicious node successfully. We demonstrated this method in random dissemination of sensor nodes in WSNs. We experimented to confirm the accuracy of our anticipated method.

Imandi Raju, Pritee Parwekar

Enhancement of Stream Ciphers Security Using DNA

This paper considers the problem of cryptanalysis of cipher streams. There are some tasks that improve the existing attacks and attempt to make eminent the partitions of ciphertext resulted by the encryption of plain text in which parts of the text are arbitrary and non-arbitrary. This paper delivers a tutorial of symmetric cryptography using LFSR with DNA prospective. The essential information speculative and computational properties of classic and contemporary cryptographic systems are exhibited, followed by scrutinization of the application of cryptography to the security of VoIP regularity in network organizations using LFSR scenario with the help of DNA using Bio-informatics. The implementation program is developed by java2.

B. Ramesh, S. A. Bhavani, P. Muralidhar

Object Recognition with Discriminately Trained Part-Based Model on HOG (Histogram of Oriented Gradients)

The object recognization techniques which are available at present cannot process the partial visible objects and cannot classify them depending on the shape. This is the main objective of my proposed system which is to recognize the object from the image if any parts of the object are visible using discriminative part-based model .The main objectives of this work was to apply the coarse root filter method and get the high-resolution parts that are converted into deformable models and are stored in training dataset. An object can be identified by matching with deformable cost of the object model present in the training dataset.

Thanikonda Alekhya, S. Ranjan Mishra

Accuracy Assessment of Images Classification Using RBF with Multi-swarm Optimization Methodology

Pattern recognition issues in contemporaneous applications and its performance enhancement in learning system using multi-swarm optimization radial basis function neural network is focused on in this paper. To improve efficiency of pattern recognition, multi-swarm optimization is used as the extension of the conventional radial basis function network. The extended neural modeling with radial network and with the incorporation of multi-swarm optimization has proved better accuracy than the traditional and PSO-RBF-neuro modeling. A comparative evaluation is carried out for retrieval accuracy for the developed recognition system and is evaluated for the accuracy for the pattern recognition system.

G. Shyama Chandra Prasad, A. Govardhan, T. V. Rao

Microstrip Patch Antenna Array with Metamaterial Ground Plane for Wi-MAX Applications

In this paper a microstrip patch antenna array, loaded with a pair of Split Ring Resonators (SRR), has been presented. This antenna is designed for IEEE 802.16a 5.8 GHz Wi-MAX applications. A pair of SRR has been etched on the ground plane of the antenna. This loading of SRR provides better matching conditions in the desired frequency band along with improvement in gain and enhancement in bandwidth. The unloaded antenna array resonates at 5.8 GHz with gain and bandwidth of 4.15 dBi and 425 MHz, respectively, whereas when the same antenna array is loaded with split ring resonators, the gain increases to 5.9 dBi and bandwidth reaches to 600 MHz. The electrical length of the patch is 0.23

λ

× 0.3

λ

. Suppression of higher harmonics and reduction in mutual coupling between the elements of patch antenna array, due to metamaterial loading, has also been analyzed.

Chirag Arora, Shyam S. Pattnaik, R. N. Baral

Tracking and Speed Estimation of Moving Vehicle for Traffic Surveillance System

Vehicle speed plays a crucial role in determining safety in traffic. In this paper vehicle speed is automatically estimated from video sequences taken from a single calibrated camera, so that this information can be used in controlling the traffic. The vehicle motion is detected and tracked along the frames. Our proposed system tracks the vehicles and gives the estimated speed of the vehicles using optical flow technique-Lucas Kanade using Pyramidal implementation.

Kamaraju Kamakula, J. Sharmila Rani, G. Santhosi, G. Gowri Pushpa

Authentication of Audio Signals in Frequency Domain (AASF)

In this paper, an approach has been made to authenticate an audio song in a collection of a similar one. Generating a unique signature with the help of another short length audio signal that will not be directly embedded into the original song but its encoded lower magnitude values will embed into the original song as a prime identity. Encoding hidden audio into lower magnitude values followed by embedding lower magnitude values into specified locations of magnitude values of original song in a predefined way that is not affected by its audible quality carries a secret authenticating message for quickly identifying it from similar signals. A comparative study has been made with similar existing techniques and experimental results are supported with mathematical formula based on Microsoft WAVE (“.wav”) stereo sound file.

Uttam Kr. Mondal, J. K. Mandal

Backmatter

Weitere Informationen