No Detail Found!

Analysis of motor imagery EEG signal classification based on amplitude-based peak detection method and pisarenko harmonic decomposition

Author(s)
JAY SARRAF School of Computer Engineering, KIIT- DU, India
VAIBHAW School of Computer Engineering, KIIT- DU, India
PRASANT KUMAR PATTNAIK School of Computer Engineering, KIIT- DU, India
Abstract
This paper presents a critical study on EEG Motor Imagery feature extraction techniques using Pisarenko Harmonic Decomposition and Peak Detection algorithm. It was found that the proposed peak detection technique for feature extractions with the KNN classifier was efficient with 95.67% accuracy as compared to 84.56% achieved using feature extraction using Pisarenko's method. Further, feature extraction using the peak detection method with the random forest and gradient boosting with the accuracy of 91.58 and 92.68% is suggested over KNN as the computation time is very high when required to compute the distance of each query instance in KNN.
Publication Details
Page(s) 4791-4800
DOI DOI not available
Published Journal: Journal of Theoretical and Applied Information Technology, Volume: 100, Issue: 15, Year: 2022

Request the full text from PASTIC

Keywords
machine learning, Classification, Classification, Brain Mapping, BCI, EEG, Motor Imagery, Signal processing
0

Citations

0

Downloads

40

Views