Cargando…
A Study of Various Feature Extraction Methods on a Motor Imagery Based Brain Computer Interface System
INTRODUCTION: Brain Computer Interface (BCI) systems based on Movement Imagination (MI) are widely used in recent decades. Separate feature extraction methods are employed in the MI data sets and classified in Virtual Reality (VR) environments for real-time applications. METHODS: This study applied...
Autores principales: | , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Iranian Neuroscience Society
2016
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4892326/ https://www.ncbi.nlm.nih.gov/pubmed/27303595 |
_version_ | 1782435377661870080 |
---|---|
author | Resalat, Seyed Navid Saba, Valiallah |
author_facet | Resalat, Seyed Navid Saba, Valiallah |
author_sort | Resalat, Seyed Navid |
collection | PubMed |
description | INTRODUCTION: Brain Computer Interface (BCI) systems based on Movement Imagination (MI) are widely used in recent decades. Separate feature extraction methods are employed in the MI data sets and classified in Virtual Reality (VR) environments for real-time applications. METHODS: This study applied wide variety of features on the recorded data using Linear Discriminant Analysis (LDA) classifier to select the best feature sets in the offline mode. The data set was recorded in 3-class tasks of the left hand, the right hand, and the foot motor imagery. RESULTS: The experimental results showed that Auto-Regressive (AR), Mean Absolute Value (MAV), and Band Power (BP) features have higher accuracy values,75% more than those for the other features. DISCUSSION: These features were selected for the designed real-time navigation. The corresponding results revealed the subject-specific nature of the MI-based BCI system; however, the Power Spectral Density (PSD) based α-BP feature had the highest averaged accuracy. |
format | Online Article Text |
id | pubmed-4892326 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2016 |
publisher | Iranian Neuroscience Society |
record_format | MEDLINE/PubMed |
spelling | pubmed-48923262016-06-14 A Study of Various Feature Extraction Methods on a Motor Imagery Based Brain Computer Interface System Resalat, Seyed Navid Saba, Valiallah Basic Clin Neurosci Research Papers INTRODUCTION: Brain Computer Interface (BCI) systems based on Movement Imagination (MI) are widely used in recent decades. Separate feature extraction methods are employed in the MI data sets and classified in Virtual Reality (VR) environments for real-time applications. METHODS: This study applied wide variety of features on the recorded data using Linear Discriminant Analysis (LDA) classifier to select the best feature sets in the offline mode. The data set was recorded in 3-class tasks of the left hand, the right hand, and the foot motor imagery. RESULTS: The experimental results showed that Auto-Regressive (AR), Mean Absolute Value (MAV), and Band Power (BP) features have higher accuracy values,75% more than those for the other features. DISCUSSION: These features were selected for the designed real-time navigation. The corresponding results revealed the subject-specific nature of the MI-based BCI system; however, the Power Spectral Density (PSD) based α-BP feature had the highest averaged accuracy. Iranian Neuroscience Society 2016-01 /pmc/articles/PMC4892326/ /pubmed/27303595 Text en Copyright© 2016 Iranian Neuroscience Society This work is licensed under a Creative Commons Attribution-NonCommercial 3.0 Unported License which allows users to read, copy, distribute and make derivative works for non-commercial purposes from the material, as long as the author of the original work is cited properly. |
spellingShingle | Research Papers Resalat, Seyed Navid Saba, Valiallah A Study of Various Feature Extraction Methods on a Motor Imagery Based Brain Computer Interface System |
title | A Study of Various Feature Extraction Methods on a Motor Imagery Based Brain Computer Interface System |
title_full | A Study of Various Feature Extraction Methods on a Motor Imagery Based Brain Computer Interface System |
title_fullStr | A Study of Various Feature Extraction Methods on a Motor Imagery Based Brain Computer Interface System |
title_full_unstemmed | A Study of Various Feature Extraction Methods on a Motor Imagery Based Brain Computer Interface System |
title_short | A Study of Various Feature Extraction Methods on a Motor Imagery Based Brain Computer Interface System |
title_sort | study of various feature extraction methods on a motor imagery based brain computer interface system |
topic | Research Papers |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4892326/ https://www.ncbi.nlm.nih.gov/pubmed/27303595 |
work_keys_str_mv | AT resalatseyednavid astudyofvariousfeatureextractionmethodsonamotorimagerybasedbraincomputerinterfacesystem AT sabavaliallah astudyofvariousfeatureextractionmethodsonamotorimagerybasedbraincomputerinterfacesystem AT resalatseyednavid studyofvariousfeatureextractionmethodsonamotorimagerybasedbraincomputerinterfacesystem AT sabavaliallah studyofvariousfeatureextractionmethodsonamotorimagerybasedbraincomputerinterfacesystem |