Frequency-Optimized Local Region Common Spatial Pattern Approach for Motor Imagery Classification

This paper presents a novel feature extraction approach for motor imagery classification overcoming the weakness of conventional common spatial pattern (CSP) methods, especially for small sample settings. We consider local CSPs generated from individual channels and their neighbors (termed "loc...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on neural systems and rehabilitation engineering 2019-07, Vol.27 (7), p.1378-1388
Main Authors: Park, Yongkoo, Chung, Wonzoo
Format: Article
Language:English
Subjects:
Algorithms
Brain-Computer Interfaces
Brain-computer interfaces (BCIs)
Channels
Classification
common spatial pattern (CSP)
Competition
Covariance matrices
Datasets
Dispersion
Electroencephalography
electroencephalography (EEG)
Emulation
Feature extraction
Filter banks
Human-computer interface
Humans
Image classification
Imagination - physiology
local feature
Mental task performance
motor imagery (MI)
Movement - physiology
Mutual information
Optimization
Photic Stimulation
Reproducibility of Results
Signal Processing, Computer-Assisted
Support Vector Machine
Task analysis
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper presents a novel feature extraction approach for motor imagery classification overcoming the weakness of conventional common spatial pattern (CSP) methods, especially for small sample settings. We consider local CSPs generated from individual channels and their neighbors (termed "local regions") rather than a global CSP generated from all channels. The novelty is to select a few good local regions using interquartile range (IQR) or an "above the mean" rule based on variance ratio dispersion score (VRDS) and inter-class feature distance (ICFD); instead of computationally expensive cross-validation method. Furthermore, we develop frequency optimization using filter banks by extending the VRDS and ICFD to frequency-optimized local CSPs. The proposed methods are tested on three publicly available brain-computer interface (BCI) datasets: BCI competition III dataset IVa, BCI competition IV dataset I, and BCI competition IV dataset IIb. The proposed method exhibits substantially improved classification accuracy compared to recent related motor imagery (MI) classification methods.
ISSN:1534-4320
1558-0210
DOI:10.1109/TNSRE.2019.2922713