Yogendra Narayan

National Institute of Technical Teachers Training and Research

Papers

Total Citations

H-Index

About

Yogendra Narayan is a researcher specializing in biomedical signal processing, machine learning, and human-machine interface systems, with a particular focus on surface electromyography (sEMG) and its applications in assistive and robotic technologies. His work addresses a deeply meaningful challenge: leveraging muscle signal data to improve the lives of individuals with physical disabilities through intelligent, responsive systems. Narayan's most impactful contribution, "Binary Movement Classification of sEMG Signal Using Linear SVM and Wavelet Packet Transform" (2016, 18 citations), demonstrates his expertise in combining time-domain feature extraction with Support Vector Machine classifiers to accurately decode human movement intent from muscle signals. Building on this foundation, his 2018 study on ensemble algorithms and Principal Component Analysis for robot control (12 citations) further advanced the field of sEMG-driven robotics, showcasing his ability to refine and scale classification methodologies. His earlier work on automated balancing platforms using Arduino microcontrollers reflects a broader interest in low-cost, accessible robotics and embedded systems. Collectively, Narayan's research bridges the gap between signal processing theory and practical robotic applications, making meaningful strides toward intuitive prosthetic and rehabilitation technologies that hold real promise for enhancing human capability.