Kannan Arputharaj

Bio: Kannan Arputharaj is an academic researcher from VIT University. The author has contributed to research in topics: Wireless sensor network & Fuzzy logic. The author has an hindex of 11, co-authored 38 publications receiving 399 citations. Previous affiliations of Kannan Arputharaj include Anna University & College of Engineering, Guindy.

Knowledge mining from clinical datasets using rough sets and backpropagation neural network.

Abstract: The availability of clinical datasets and knowledge mining methodologies encourages the researchers to pursue research in extracting knowledge from clinical datasets. Different data mining techniques have been used for mining rules, and mathematical models have been developed to assist the clinician in decision making. The objective of this research is to build a classifier that will predict the presence or absence of a disease by learning from the minimal set of attributes that has been extracted from the clinical dataset. In this work rough set indiscernibility relation method with backpropagation neural network (RS-BPNN) is used. This work has two stages. The first stage is handling of missing values to obtain a smooth data set and selection of appropriate attributes from the clinical dataset by indiscernibility relation method. The second stage is classification using backpropagation neural network on the selected reducts of the dataset. The classifier has been tested with hepatitis, Wisconsin breast cancer, and Statlog heart disease datasets obtained from the University of California at Irvine (UCI) machine learning repository. The accuracy obtained from the proposed method is 97.3%, 98.6%, and 90.4% for hepatitis, breast cancer, and heart disease, respectively. The proposed system provides an effective classification model for clinical datasets.

Intrusion detection using dynamic feature selection and fuzzy temporal decision tree classification for wireless sensor networks

Abstract: Intrusion detection systems assume a noteworthy job in the provision of security in wireless Sensor networks. The existing intrusion detection systems focus only on the detection of the known types of attacks. However, it neglects to recognise the new types of attacks, which are introduced by malicious users leading to vulnerability and information loss in the network. In order to address this challenge, a new intrusion detection system, which detects the known and unknown types of attacks using an intelligent decision tree classification algorithm, has been proposed. For this purpose, a novel feature selection algorithm named dynamic recursive feature selection algorithm, which selects an optimal number of features from the data set is proposed. In addition, an intelligent fuzzy temporal decision tree algorithm is also proposed by extending the decision tree algorithm and integrated with convolution neural networks to detect the intruders effectively. The experimental analysis carried out using KDD cup data set and network trace data set demonstrates the effectiveness of this proposed approach. It proved that the false positive rate, energy consumption, and delay are reduced in the proposed work. In addition, the proposed system increases the network performance through increased packet delivery ratio.

An intelligent fuzzy rule-based e-learning recommendation system for dynamic user interests

Abstract: A relevant and suitable content recommendation is an important and challenging task in e-learning. Relevant terms are retrieved in a recommender system that should also cope with varying user preferences over time. This paper proposes a novel recommendation system which provides suitable contents by refining the final frequent item patterns evolving from frequent pattern mining technique and then classifying the final contents using fuzzy logic into three levels. This is achieved by generating frequent item patterns after consolidating the user interest changes with an extended error margin quotient. Moreover, fuzzy rules are used in this work to enable the rule mining constraints for accommodating all types of learners while applying rules on the pattern tables. This method aims at mining the data stream preferences into equal-sized windows and caters to the varying user interest ratings over time. Experiments prove its efficiency and accuracy over existing conventional methods.

Intelligent fuzzy rule-based approach with outlier detection for secured routing in WSN

Abstract: In wireless sensor networks (WSNs), energy optimization and the provision of security are the major design challenges. Since the wireless sensor devices are energy constrained, the issue of high energy consumption by the malicious nodes must be addressed well in order to enhance the network performance by making increased network lifetime, reduced energy consumption and delay. In the past, many researchers worked in the provision of new techniques for providing improved security to WSN in order to enhance the reliability in the routing process. However, most of the existing routing techniques are not able to achieve the required security through the use of intelligent techniques for safeguarding the sensor nodes from malicious attacks. In order to address these problems, a new fuzzy temporal clustering-based secured communication model with trust analysis and outlier detection has been developed in this research work. For this purpose, a new fuzzy temporal rule-based cluster-based routing algorithm with trust modelling and outlier detection for monitoring the nodes participating in the communication has been proposed. In addition, a fuzzy temporal rule- and distance-based outlier detection algorithm is also proposed in this paper for distinguishing the malicious nodes from other nodes within each cluster of the network and has been used in the secured routing algorithm. The proposed secure routing algorithm uses the temporal reasoning tasks of explanation-based learning and prediction as well as spatial constraints for making efficient routing decisions through the application of trust and key management techniques for performing effective authentication of nodes and thereby isolating the malicious nodes from communication through outlier detection. By applying these two proposed algorithms for communication in the proposed work, it is proved through experiments that the proposed secure routing algorithm and the outlier detection algorithm are able to perform secured and reliable routing through genuine cluster head nodes more effectively. Moreover, these two algorithms provide improved quality of service with respect to the reliability of communication, packet delivery ratio, reduction in end-to-end delay and reduced energy consumption.

Information retrieval

Abstract: The major change in the second edition of this book is the addition of a new chapter on probabilistic retrieval. This chapter has been included because I think this is one of the most interesting and active areas of research in information retrieval. There are still many problems to be solved so I hope that this particular chapter will be of some help to those who want to advance the state of knowledge in this area. All the other chapters have been updated by including some of the more recent work on the topics covered. In preparing this new edition I have benefited from discussions with Bruce Croft, The material of this book is aimed at advanced undergraduate information (or computer) science students, postgraduate library science students, and research workers in the field of IR. Some of the chapters, particularly Chapter 6 * , make simple use of a little advanced mathematics. However, the necessary mathematical tools can be easily mastered from numerous mathematical texts that now exist and, in any case, references have been given where the mathematics occur. I had to face the problem of balancing clarity of exposition with density of references. I was tempted to give large numbers of references but was afraid they would have destroyed the continuity of the text. I have tried to steer a middle course and not compete with the Annual Review of Information Science and Technology. Normally one is encouraged to cite only works that have been published in some readily accessible form, such as a book or periodical. Unfortunately, much of the interesting work in IR is contained in technical reports and Ph.D. theses. For example, most the work done on the SMART system at Cornell is available only in reports. Luckily many of these are now available through the National Technical Information Service (U.S.) and University Microfilms (U.K.). I have not avoided using these sources although if the same material is accessible more readily in some other form I have given it preference. I should like to acknowledge my considerable debt to many people and institutions that have helped me. Let me say first that they are responsible for many of the ideas in this book but that only I wish to be held responsible. My greatest debt is to Karen Sparck Jones who taught me to research information retrieval as an experimental science. Nick Jardine and Robin …

Breast cancer classification using deep belief networks

Abstract: We present a CAD scheme using DBN unsupervised path followed by NN supervised path.Our two-phase method 'DBN-NN' classification accuracy is higher than using one phase.Overall accuracy of DBN-NN reaches 99.68% with 100% sensitivity & 99.47% specificity.DBN-NN was tested on the Wisconsin Breast Cancer Dataset (WBCD).DBN-NN results show classifier performance improvements over previous studies. Over the last decade, the ever increasing world-wide demand for early detection of breast cancer at many screening sites and hospitals has resulted in the need of new research avenues. According to the World Health Organization (WHO), an early detection of cancer greatly increases the chances of taking the right decision on a successful treatment plan. The Computer-Aided Diagnosis (CAD) systems are applied widely in the detection and differential diagnosis of many different kinds of abnormalities. Therefore, improving the accuracy of a CAD system has become one of the major research areas. In this paper, a CAD scheme for detection of breast cancer has been developed using deep belief network unsupervised path followed by back propagation supervised path. The construction is back-propagation neural network with Liebenberg Marquardt learning function while weights are initialized from the deep belief network path (DBN-NN). Our technique was tested on the Wisconsin Breast Cancer Dataset (WBCD). The classifier complex gives an accuracy of 99.68% indicating promising results over previously-published studies. The proposed system provides an effective classification model for breast cancer. In addition, we examined the architecture at several train-test partitions.