Tripura Institute of Technology

About: Tripura Institute of Technology is a based out in . It is known for research contribution in the topics: Electric power system & Renewable energy. The organization has 63 authors who have published 92 publications receiving 510 citations.

A Hybrid Machine Learning Approach for Prediction of Heart Diseases

Abstract: Heart diseases are the chief cause of death all over the world over the last few decades. To avoid heart disease or coronary illness and discover indications early, individuals over 55 years must have a total cardiovascular checkup. Researchers and specialists developed various intelligent techniques to improve capacity of the health care professionals in recognition of cardiovascular disease. In cardiovascular disease finding and treatment, single data mining strategies are giving the reasonable precision and accuracy. Nevertheless the usage data mining procedure be capable of reducing the number of test that is required to be carried out. In order to decrease the Figure of deaths from heart diseases there has to be a quick and efficient detection technique providing better accuracy and precision. The aim of this paper is to present an efficient technique of predicting heart diseases using machine learning approaches. Hence we proposed a hybrid approach for heart prediction using Random forest classifier and simple k-means algorithm machine learning techniques. The dataset is also evaluated using two other different machine learning algorithms, namely, J48 tree classifier and Naive Bayes classifier and results are compared. Results attained through Random forest classifier and the corresponding confusion matrix shows robustness of the methodology.

Efficient FPGA Implementation of Address Generator for WiMAX Deinterleaver

Abstract: In this brief, a low-complexity and novel technique is proposed to efficiently implement the address generation circuitry of the 2-D deinterleaver used in the WiMAX transreceiver using the Xilinx field-programmable gate array (FPGA). The floor function associated with the implementation of the steps, required for the permutation of the incoming bit stream in channel interleaver/deinterleaver for IEEE 802.16e standard is very difficult to implement in FPGA. A simple algorithm along with its mathematical background developed in this brief, eliminates the requirement of floor function and thereby allows low-complexity FPGA implementation. The use of an internal multiplier of FPGA and the sharing of resources for quadrature phase-shift keying, 16-quadrature-amplitude modulation (QAM), and 64-QAM modulations along with all possible code rates makes our approach to be novel and highly efficient when compared with conventional look-up table-based approach. The proposed approach exhibits significant improvement in the use of FPGA resources. Exhaustive simulation has been carried out to claim supremacy of our proposed work.

Design of QoS Routing Framework Based on OLSR Protocol

Abstract: Mobile Ad-hoc Networks (MANET) is the self organizing collection of mobile nodes. The communication in MANET is done via a wireless media. In order to support the growing need for multimedia and real time applications, QoS support has become essential. However it is a challenge to route QoS in wireless environment due to node’s dynamic nature and mobility. This paper aims towards efficient QoS routing using OLSR (Optimized Link State Routing) by enhancing the MPR (Multi Point Relay) selection criteria. Considering the QoS parameters of effective bandwidth and end-to-end delay, a new algorithm has been proposed to map the QoS parameters into a single numeric weight in order to select the MPR node. The simulation results establish the efficiency of the proposed methodology.

Classification of power system voltage stability conditions using Kohonen's self-organising feature map and learning vector quantisation

Abstract: SUMMARY This paper presents an artificial neural network–based approach, in which Kohonen's self-organising feature map technique in association with learning vector quantisation has been applied to classify the power system operating states on the basis of their degree of static voltage stability. The proposed scheme can seamlessly integrate itself within the energy management systems in the smart grid scenario. A self-organising feature map has been considered to be an ideal choice because the state classification problem is a typical multiclass pattern classification problem, which can be efficiently handled by a self-organising feature map with much shorter training time compared with other neural networks. The self-organising feature map provided information about the operating states of the power system and classified them into three categories, namely, normal state, intermediate state and emergency (or alert) state. To augment the classification accuracy of self-organising feature map, a learning vector quantisation–based supervised classification was also adopted. The proposed method was tested on a real 203-bus system of an Indian power utility, and the results obtained has been compared with standard voltage stability indicator–based classical voltage stability assessment results. Copyright © 2011 John Wiley & Sons, Ltd.