Sage Journals: Discover world-class research

Abstract

Brain Computer Interface (BCI) enables us to record and process the information generated by the brain and process them. Due to high variability of the Electroencephalogram (EEG) data, multiple trails are recorded for a particular task. The present work aims to improve the accuracy for motor imagery task classification by selecting the most prominent trail from the multiple trails recorded during motor imagery. In this paper, we propose a novel weight optimization algorithm for common spatial filtering (CSP) using evolutionary algorithms (i.e. cuckoo search algorithm (CSA), firefly algorithm (FA) and gravitational search algorithm (GSA)) to select the most prominent trial from the multiple trails recorded for feature extraction. The features extracted from the selected trials were thus used for motor imagery task classification. The performance was evaluated on the extracted features from the selected trials using two classifiers namely linear discriminant analysis (LDA) and support vector machines (SVM). It is observed that FA with band power as a feature gives the best performance in comparison to the earlier reported methods i.e. average, error based and alternating direction method of multipliers (ADMM).

Keywords

Brain computer interface common spatial pattern cuckoo search algorithm electroencephalography firefly algorithm gravitational search algorithm linear discriminant analysis support vector machine

Get full access to this article

View all access options for this article.

References

Graimann

, Allison

and Pfurtscheller

, brain– computer interfaces: A gentle introduction, In Brain-Computer Interfaces (2010), 1–27. Springer, Chapter 1.

Sanei

, Ferdowsi

, Nazarpour

and Cichocki

, Advances in electroencephalography signal processing [Life Sciences], IEEE Signal Process Mag30(1) (2013), 170–176.

Blankertz

, Tomioka

, Kawanabe

L.M.

and Müller

K.R.

, Optimizing spatial filters for robust EEG single-trial analysis, IEEE Signal Process. Mag25(1) (2008), 41–56.

Ramoser

, Müller-Gerking

and Pfurtscheller

, Optimal spatial filtering of single trial EEG during imagined hand movement, IEEE Trans. Neural Syst.Rehabil. Eng8(4) (2000), 441–446.

, Chen

, Gao

and Brown

E.N.

, A hierarchical Bayesian approach for learning sparse spatio-temporal decompositions of multichannel EEG, NeuroImage56(4) (2015), 1929–1945.

, Chen

, Gao

, Li

, Brown

E.N.

and Gao

, Probabilistic common spatial patterns for multichannel EEG analysis, IEEE Trans. Pattern Anal. Mach.Intell37(3) (2015), 639–653.

and Guan

, An extended EM algorithm for joint feature extraction and classification in brain-computer interfaces, Neural Comput18(11) (2011), 2730–2761.

Bashashati

, Fatourechi

, Ward

R.K.

and Birch

G.E.

, A survey of signal processing algorithms in brain– computer interfaces based on electrical brain signals, J. Neural Eng4(2) (2005), R32–R57.

Lemm

, Blankertz

, Curio

and Müller

K.R.

, Spatio-spectral filters for improving the classification of single trial EEG, IEEE Trans Biomed Eng52(9) (2005), 1541–1548.

10.

Dornhege

, Blankertz

, Krauledat

, Losch

, Curio

and Muller

K.R.

, Combined optimization of spatial and temporal filters for improving brain-computer interfacing, IEEE Trans Biomed Eng53(11) (2006), 2274–2281.

11.

Higashi

and Tanaka

, Simultaneous design of FIR filter banks and spatial patterns for EEG signal classification, IEEE Trans Biomed Eng60(4) (2013), 1100–1110.

12.

, Gao

, Hong

and Gao

, Classifying single-trial EEG during motor imagery by iterative spatio-spectral patterns learning (ISSPL), IEEE Trans Biomed Eng55(6) (2008), 1733–1743.

13.

Tomida

, Higashi

and Tanaka

, A joint tensor diagonalization approach to active data selection for EEG classification, Department of Electrical and Electronic Engineering Tokyo University of Agriculture and Technology (2013), 983–987.

14.

Tomida

, Tanaka

, Ono

, Yamagishi

and Higashi

, Active data selection for motor imagery EEG classification, IEEE Trans Biomed Eng62(2) (2015), 458–67.

15.

Tomida

, Higasi

and Tanaga

, A joint tensordiagonalization approach to active data selection for EEG classification, IEEE Int Conf Acoust, Speech, Signal Processing (2013), 983–987.

16.

Osman,

I.H.

and Laporte,

, Metaheuristics: A bibliography, Ann Oper Res63 (1996), 513–623.

17.

Yang

X.S.

and Deb

, Cuckoo search via levy flights, world congress on nature & biologically inspired computing(NaBIC), IEEE Publications (2009), 210–214.

18.

Fister

, Fister

Jr , Yang

X.S.

and Brest

, A comprehensive review of firefly algorithms, Journal of Swarm and Evolutionary Computation13(1) (2013), 34–46.

19.

Yang

X.S

, Natural-Inspired Metahuristic Algorithm, Luniver Press, UK, (2008).

20.

Rashedi

, Nezamabadi-pour

and Saryazdi

, GSA: A gravitational search algorithm, Information Sciences179(13) (2009), 2232–2248.

21.

Yger

, Lotte

and Sugiyama

, Averaging covariance for EEG signal classification based on the CSP: An empirical study, 23rd European Signal Processing Conference (EUSIPCO) (2015), 2771–2775.

22.

Zhang

, Zhou

, Jin

, Wang

and Cichocki

, Optimizing spatial patterns with sparse filter bands for motor-imagery based brain– computer interface, Journal of Neuroscience Methods255 (2015), 85–91.

23.

Buccino

A.P.

, Keles

H.O.

and Omurtag

, Hybrid EEG-fNIRS asynchronous brain computer interface for multiple motor tasks, PLOS ONE, doi:10.1371/journal.pone.0146610January 5, (2016).

24.

Kumar

, Sharma

and Tsunoda

, An improved discriminative filter bank selection approach for motor imagery EEG signal classification using mutual information, kumar et al. BMC Bioinformatics18(Suppl 16) (2017), 545. doi:10.1186/s12859-017-1964-6, pp. 125–137.

Motor imagery task classification using intelligent algorithm with prominent trial selection

Abstract

Keywords

Get full access to this article

References