National Institute of Technology, Meghalaya

About: National Institute of Technology, Meghalaya is a education organization based out in Shillong, India. It is known for research contribution in the topics: Control theory & Electric power system. The organization has 503 authors who have published 1062 publications receiving 6818 citations. The organization is also known as: NIT Meghalaya & NITM.

A comparative study on the computation of directional overcurrent relay coordination in power systems using PSO and TLBO based optimization

Abstract: Purpose – Directional Overcurrent Relay (DOCR) coordination computation allowing for desired and high-level accuracy in interconnected power systems is very difficult and is a highly constraint-oriented optimization problem. The purpose of this paper is to study the effectiveness of a newly reported optimization technique, Teaching Learning Based Optimization (TLBO), in protective relay coordination comparing with a widely used optimization technique, Particle Swarm Optimization (PSO). Design/methodology/approach – DOCR coordination in electric power systems is considered as an optimization problem by formulating objective function and specifying problem constraints. Optimum values of the DOCR adjustment parameters (time dial setting and plug setting) in terms of reliable coordination margin and operating times of relays are computed by both the algorithms, TLBO and PSO. Optimal coordination is verified in three test bus systems: IEEE 6-bus, Western System Coordinating Council 9-bus and IEEE 14-bus system...

Human gait based gender identification system using Hidden Markov Model and Support Vector Machines

Abstract: The paper presents an approach towards human gender recognition system The Silhouettes from Center for Biometrics and Security Research (CASIA) gait database are segmented in order to identify major body points and to generate corresponding point-light display The features such as two dimensional coordinates of major body points and joint angles are extracted from the point-light display The features are classified using Hidden Markov Model (HMM) and Support Vector Machines (SVM) The study yields a recognition rate of 6918% and 7679% with 100 subject data using HMM and SVM respectively There has been a significant improvement in recognition accuracy using joint angles as the features