Nature Inspired Computing

With an incessant development of the information technology, ontology has been widely applied to various fields for knowledge representation. Therefore, ontology construction and ontology extension has become a great area of research. Creating ontology should not be confined to the thinking process of few ontology engineers. To develop common ontologies for information sharing, they should satisfy the requirements of different people for a particular domain. Also, ontology engineering should be a collaborative process for faster development. As Social Web is growing, its simplicity proves to be successful in attracting mass participation. This paper aims in developing a platform “EasyOnto” which provide simple and easy graphical user interface for users to collaboratively contribute in developing semiformal ontology.

Cloud computing widely uses resource sharing and computing framework over the Internet. Data security is the key objective while sharing data over untrusted environment. This paper presents a novel biometric inspired homomorphic encryption algorithm (BIHEA) for secured data/files transmission over hybrid cloud environment. The proposed algorithm encrypts the user data at run-time by providing the authorized user biometric-feature-based one time password. Every time a user is authenticated by a totally different one time password. The BIHEA provides a good solution to commonly identified theft seen in cloud environment like phishing, shoulder surfing.

In today’s world, people prefer Internet applications for fulfilling their needs. One cannot give guarantee for all applications get completed and all completed are not to the level of user satisfactory. Most of the solutions exist only for major cases such as optimal response, nearby output, similar answer, failure, fraudulences. Some may be discarded by the user itself, but all applications cannot be left as that, few holds significance. At the outset, we strive to provide solutions for such significant applications to the level of user satisfactory. In this paper, a way is analysed to reprocess such applications by taking the relevance feedback based on their input and obtained output and reaches their convenience using semantic intelligence and neural networks.

Decision trees are outstanding tools to help anyone to select the best course of action. They generate a highly valuable arrangement in which one can place options and study possible outcomes of those options. They also facilitate users to make a fair idea of the pros and cons related to each possible action. A decision tree is used to represent graphically the decisions, the events, and the outcomes related to decisions and events. Events are probabilistic and determined for each outcome. The aim of this paper is to do detailed analysis of decision tree and its variants for determining the best appropriate decision. For this, we will analyze and compare various decision tree algorithms such as ID3, C4.5, CART, and CHAID.

It is generally believed that the existence of all organisms present on this earth has their point of convergence in a common gene pool. The current species passed through an evolutionary process which is still underway. The theoretical assumptions relating to the common descent of all organisms are based on four simple facts: first, they had wide geographical dispersal; second, the different life forms were not remarkably unique and did not possess mutually exclusive characteristics; third, some of their attributes which apparently served no purpose had an uncanny similarity with some of their lost functional traits; and last, based on their common attributes these organisms can be put together into a well-defined, hierarchical and coherent group, like a family tree. Phylogenetic networks are the main tools that can be used to represent biological relationship between different species. Biologists, mathematicians, statisticians, computer scientists and others have designed various models for the reconstruction of evolutionary networks and developed numerous algorithms for efficient predictions and analysis. Even though these problems have been studied for a very long time, but the computational model built to solve the biological problems fail to give accurate results while working on real biological data, which could be due to the premises on which the model is based. The objective of this paper is to test and analyse the transmission of commonly occurring diseases to fit into more realistic models. The problems are not only important because we need to know how they came into existence and how they migrated, but also helpful for the treatment of such diseases and drug discovery.

Malaria is a disease, which affects many people around the globe. In this study, we propose a fuzzy diagnosis approach for the clinical diagnosis of the type of malaria which affects the patient. By the help of the prescribed method, one can easily diagnose the type of malaria, without conducting any laboratory test. On the basis of relation between symptoms and various types of infection present in patients, we develop hypothetical medical information-based case study of patients with assigned degree of membership, non-membership, and intuitionistic index. By using the procedure, we can easily diagnose the type of malaria; for example, patient p ₁ is suffering from Plasmodium malariae (Pm), p ₂ is suffering from Plasmodium ovale (Po), p ₃ is suffering from Plasmodium falciparum (Pf), and p ₄ is suffering from Plasmodium vivax (Pv) and P. malariae (Pm). Also, we can develop a computer program for the proposed procedure.

Scheduling plays a vital role in our real life, same as CPU scheduling majorly affects the performance of computer system. For better performance, scheduling depends upon the parameters of jobs (arrival time, burst time, priority, etc.). Different algorithms have been used to find the above factors. Many algorithms such as FCFS, SJF, round-robin, priority are applied, but all these techniques provide a sequence of jobs relevant to their properties. Developing an appropriate sequence using previously known algorithms takes exponential time. This paper proposes an efficient method for process scheduling using a deadline-aware approximation algorithm, where required schedule has a certain weightage of priority and burst time of job. Here, GA and modified GA are compared in terms of number of iterations, number of test cases, requirement percentage and tardiness (fitness value). The results demonstrate that modified GA approach produces solutions very close to the optimal one in comparison with GA.

Profitability is an important factor for sustainability of an organization. Profitability is important but cash flow is also important for the basic obligations like taxes, payroll, etc. In this paper, we have worked on the optimization of resource-constrained scheduling with discounted cash flow (payment scheduling or RCPSPDCF). We have conceptualized bio-inspired computing algorithm namely Genetic Algorithm. Microsoft dependency injection is also being used. It can be further used for problems like resource optimization (Madan and Madan in GASolver-A solution to resource constrained project scheduling, 2013) [1], Time versus Cost optimization (Madan and Madan in Optimizing time cost trade off scheduling) [2].

There is a partitioning of a data set X into c-clusters in clustering analysis. In 1984, fuzzy c-mean clustering was proposed. Later, fuzzy c-mean was used for the segmentation of medical images. Many researchers work to improve the fuzzy c-mean models. In our paper, we proposed a novel intuitionistic possibilistic fuzzy c-mean algorithm. Possibilistic fuzzy c-mean and intuitionistic fuzzy c-mean are hybridized to overcome the problems of fuzzy c-mean. This proposed clustering approach holds the positive points of possibilistic fuzzy c-mean that will overcome the coincident cluster problem, reduces the noise and brings less sensitivity to an outlier. Another approach of intuitionistic fuzzy c-mean improves the basics of fuzzy c-mean by using intuitionistic fuzzy sets. Our proposed intuitionistic possibilistic fuzzy c-mean technique has been applied to the clustering of the mammogram images for breast cancer detector of abnormal images. The experiments result in high accuracy with clustering and breast cancer detection.

The advent of new technologies like ZigBee, RFID, Android, Arduino has revolutionized the era of embedded system design. Nowadays, every user is surrounded by smart devices (robots) which make their life easier and comfortable. It has also been predicted by the researchers that by 2020, there will be billions of embedded devices talking to each other as compared to human beings termed as Internet of things (IoT). This paper is concerned with the development of autonomous mobile robot used for wireless control and navigation. This robot is equipped with ZigBee (for wireless data transfer), RFID reader (for reading the RFID tags to change the robot direction), and Arduino (for calculating the shortest path and providing commands to robot after reaching a RFID tag). This mobile robot has wide variety of applications in indoor navigation. The basic functionality of the proposed design is simulated on a chart paper designed by us, and the complete design is implemented around Arduino microcontroller with required necessary interfaces.

In this article, a mixed family of q-Bernoulli–Euler polynomials is introduced by means of generating function, series definition, and determinantal definition. Further, the numbers related to the q-Bernoulli–Euler polynomials are considered, and the graph of the q-Bernoulli–Euler polynomials is also drawn for index n = 3 and \( q = 1/2 \).

Iris recognition has become a popular technique for differentiating individuals on the basis of their iris texture with high accuracy. One of the decisive steps of iris recognition is iris segmentation because it notably affects the accuracy of feature extraction and matching steps. Most state-of-the-art algorithms use circular Hough transform (CHT) for segmenting the iris from an eye image. But, CHT does not work efficiently for eye images having less contrast. Therefore, a new approach is proposed here for isolating and normalizing the iris region, which is more robust than CHT. Experiments are performed on IITD iris database. The proposed algorithm works better than the traditional CHT.

Wireless sensor networks (WSNs) contain many sensor nodes which are deployed in the various geographical areas to perform various tasks like monitoring, data aggregation and data processing. For performing all these operations, energy is highly consumed, thus sensor nodes begin to die soon and also creates energy holes in some of the geographical locations. All the sensor nodes are powered by battery, and it is quite difficult to replace the battery, and so energy consumption is prime objective to increase the network lifetime. Clustering and tree-based routing like LEACH, PEDAP, TBC and TREEPSI solves most of the energy consumption problem as it saves energy during a lot of operations in WSNs. In this paper, we propose an optimal tree-based routing protocol (OTBRP) that is efficient in terms of stability period (time period before first node dead) and therefore offers good network lifetime. The parameters like first node dead, half node dead and last node dead are considered for the measurement of network lifetime. In order to evaluate the performance of OTBRP, the comparison is made with the GSTEB and PEGASIS. Simulation results show that there is a gain of approx. 200 and 150% in stability period in comparison with PEGASIS and GSTEB, respectively.

Advancement in wireless network technologies, such as wearable and implantable biosensors, along with present developments in the embedded computing area is enabling the design, progress and implementation of body area networks. Security in BANs is a big issue. In this paper, a new security algorithm for body area networks named Sybil attack prevention algorithm for body area networks (SAPA-BAN) is proposed. This algorithm protects the BANs from Sybil attack. It provides the confidentiality and integrity to the data or critical information about the patient’s health sent by a BAN to the coordinating centre/emergency services. This algorithm is energy efficient and reliable also because it operates on less energy. SAPA-BAN performs better in terms of throughput, packet delivery ratio, end-to-end delay, hops count and overhead. A comparative analysis of SAPA-BAN with respect to LSA is performed on the basis of above said parameters.

SAW E-nose sensor is one of the chemical sensor detectors to sense and detect the toxic vapors or gases. This paper proposes an approach to process the SAW sensor data and to predict the type of chemical warfare agents (CWA). Artificial neural network (ANN) approach is one of the pattern recognition technique for processing the signal produced by SAW E-nose. We have applied Principal component analysis (PCA) technique to normalize the data sets of SAW sensors. Here, we have designed a system to predict the toxic vapors like ammonia, acetone, ethylene, and ethanol. This pattern recognition system also classifies the humidity of the toxic vapors. Sensor arrays were used for predicting different types of toxic vapor as a result. The results were obtained through MATLAB tool with sensor data set converted from analog to digital data type.

Text mining works widely in the field of research techniques, which allow an individual to store text and its important terms in form of electronic document (.doc, .txt). Obliviously, one cannot remember such huge amount of text; moreover, the manual approach is more time-taking, unreliable, and accessible to that person only. Text mining techniques optimize this approach by extracting and storing this data. Computational comparison, file read, file write are more efficiently done. With the help of Pico-Nym Cloud (PNC), we generated more semantically similar, related, and significant patterns. The give, generate, and get sequence modeling is adopted. Over the other available Web applications, we present our application with improved stemming, relation, and average case consideration. This approach does not limit the displayed number of words as all the generated sets can be traversed with the GUI, with opted size of patterns. This PNC is highly applicable in bioinformatics, related information retrieval from document, sentimental analysis using social Web sites (Twitter and Facebook), query expansion (Google) and many more.

Cloud Computing is captivating many organizations and individuals because it provides a framework where the user can access diverse resources such as applications, storage capacity, network bandwidth, and many resources. Cloud users rent the resources that they need from the cloud provider. The optimum allocation of resources to the users in a dynamic environment is a major challenge for the cloud providers. Virtualization technology in Cloud enables allocation of resources to the end user applications in Cloud by hosting numerous Virtual Machines on a single host. There are number of approaches to decide the placement of Virtual Machines to the various hosts. As numbers of applications are submitted by the users, some of the hosts become overloaded and some become under loaded. As a result, some of the user applications hosted on a Virtual Machine of one host needs to be transferred to another Virtual Machine of another host. The migration of Virtual Machines from one host to another needs to be minimized to improve the response time, turnaround time for an end user application. This paper addresses the various VM placement and VM selection algorithms and their scope of improvement.

Distributed Denial of Services (DDoS) attack is the one of the most dangerous threats in the cloud computing. A group of zombies tries to attack a single target so that the victim is not able to use the resources more, and it leads to shutting down the system. And the actual attacker is hard to trace. In the proposed method, we used a hybrid approach which is Artificial Bee Colony and Back Propagation Artificial Neural Network. The proposed method is used to detect the DDoS attack in cloud computing. Firstly, the Artificial Bee Colony selects the weights and thresholds on the basis of minimum mean square error. And these weights and thresholds are used to initialize Back Propagation Artificial Neural Network. And then the training is performed based on the Back Propagation technique. It increases the speed and accuracy of detecting the DDoS attack.

Redirection spam is a technique whereby a genuine search user is forced to pass through a series of redirections and finally land on a compromised Web site that may present an unwanted content or download malware on his machine. Such malicious redirections are a threat to Web security and must be detected. In this paper, we explore the Artificial Neural Network algorithms for modeling redirection spam detection by conducting the performance evaluation of the three most used training algorithms, namely scaled conjugate gradient (trainscg), Bayesian regularization (trainbr), and Levenberg–Marquardt (trainlm). Our results indicate that the network trained using Bayesian regularization outperformed the other two algorithms. To establish the success of our results, we have used two datasets comprising of 2200 URLs and 2000 URLs, respectively.

There are numerous methods for extracting useful information from data. This paper describes a method for predicting performance of students. This method modifies the basic particle swarm optimization (PSO) algorithm using a set of rules. An attribute is selected from a set of performance attributes of the students. This attribute is used to frame rules. These rules determine the value of a modifying factor. This factor changes the mathematical expression of the function used in PSO for finding the solution. These rules are based on number of students in a particular shift. Other attributes are assigned different indexes. These indexes indicate number of students deviating from average value. The modified PSO algorithm takes the values of these indexes as inputs and generates a solution set which minimizes the values of indexes. A comparison of the solution set given by modified PSO and the solution set with unmodified PSO is presented. A brief outline of the modified PSO is given. The selection of the modifying factor and design of rules is described. These rules are based on the number of students in a particular shift. The different possible classes for the shift attribute are given. Thus, a decision strategy for predicting performance is described.

Neural networks and genetic programming have long since helped humans in diagnoses and treatment of human diseases. However, not much has been done for man’s best friend—the canine’s. This paper thus aims to explore and find the possibility of building software which is based on the use of neural network and Cartesian genetic programming to diagnose the various diseases of canine population. During the study, its outcomes were also compared and contrasted with the results of a neural network combined with simple genetic programming-based system, the results of which confirmed the high success rate of neural network training when it is modified with Cartesian genetic programming for the use of diagnosis of various categories of canine diseases.

The power of reasoning and the ability to make better decisions has been the best gift God has bestowed upon mankind. When we developed artificial intelligence (AI) systems with the goal to think and act rationally, the focus has always been as to how the AI system can replicate the natural decision-making process as compared to humans. However, in adverse situations, the efficiency of making a decision is affected by many factors such as emotional impact which do not affect an AI system. In this paper, we will identify and draw out the factors that affect human decision making and investigate the same on an AI chatbot. Later, a comparative analysis is done to draw out where AI or the human mind excels with those factors.