Real-time hand gesture SEMG using spectral estimation and LVQ for two-wheel control

Abstract

In this paper, a real-time experimental of Hand Gesture SEMG using Spectral Estimation and Linear Vector Quantization for Two-Wheel Machine Control is proposed. The raw SEMG signals been captured from SEMG amplifier and the Auto Regressive (AR) Covariance returned the power spectral density (PSD) magnitude squared frequency response. Up to 4 channels of AR data will be combined and a fine tuning step by using LVQ will then incorporate for pattern classification. The database then been build and use for real-time experimental control classification. Captured data will send through serial port and Two-Wheel Machine will receive and move accordingly. The detail of the experiment and simulation conducted described here to verify the differentiation and effectiveness of combined channels PSD method SEMG pattern classification of hand gesture for real-time control. © 2010 Springer-Verlag.