Automatic feature selection of motor imagery EEG signals using differential evolution and learning automata

Bhattacharyya, Saugat; Sengupta, Abhronil; Chakraborti, T.; Konar, Amit; Tibarewala, D. N.

doi:10.1007/s11517-013-1123-9

Cited by 51 publications

(26 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the wrapper approach [37, 38], the seminal work of Keirn and Aunon [4] has used a combination of forward sequential feature selection and an exhaustive search to obtain a subset of relevant and non-redundant features for the mental task classification. However, wrapper approach is not suitable for high-dimensional data as it is computationally expensive.…”

Section: Feature Selectionmentioning

confidence: 99%

Fuzzy clustering-based feature extraction method for mental task classification

Gupta

Kumar

2016

Brain Inf.

View full text Add to dashboard Cite

A brain computer interface (BCI) is a communication system by which a person can send messages or requests for basic necessities without using peripheral nerves and muscles. Response to mental task-based BCI is one of the privileged areas of investigation. Electroencephalography (EEG) signals are used to represent the brain activities in the BCI domain. For any mental task classification model, the performance of the learning model depends on the extraction of features from EEG signal. In literature, wavelet transform and empirical mode decomposition are two popular feature extraction methods used to analyze a signal having non-linear and non-stationary property. By adopting the virtue of both techniques, a theoretical adaptive filter-based method to decompose non-linear and non-stationary signal has been proposed known as empirical wavelet transform (EWT) in recent past. EWT does not work well for the signals having overlapped in frequency and time domain and failed to provide good features for further classification. In this work, Fuzzy c-means algorithm is utilized along with EWT to handle this problem. It has been observed from the experimental results that EWT along with fuzzy clustering outperforms in comparison to EWT for the EEG-based response to mental task problem. Further, in case of mental task classification, the ratio of samples to features is very small. To handle the problem of small ratio of samples to features, in this paper, we have also utilized three well-known multivariate feature selection methods viz. Bhattacharyya distance (BD), ratio of scatter matrices (SR), and linear regression (LR). The results of experiment demonstrate that the performance of mental task classification has improved considerably by aforesaid methods. Ranking method and Friedman’s statistical test are also performed to rank and compare different combinations of feature extraction methods and feature selection methods which endorse the efficacy of the proposed approach.

show abstract

Section: Feature Selectionmentioning

confidence: 99%

Fuzzy clustering-based feature extraction method for mental task classification

Gupta

Kumar

2016

Brain Inf.

View full text Add to dashboard Cite

show abstract

“…Each subsection describes the stimuli designed for the offline and online sessions (as shown in Fig. 3), creation of the feature vectors [4] and the classifiers designed for each detector. Five normal right-handed subjects in the agegroup of 22-28 years have participated in this experiment.…”

Section: Experiments and Data Processingmentioning

confidence: 99%

Motor imagery, P300 and error-related EEG-based robot arm movement control for rehabilitation purpose

Bhattacharyya

Konar

Tibarewala

2014

Med Biol Eng Comput

Self Cite

View full text Add to dashboard Cite

The paper proposes a novel approach toward EEG-driven position control of a robot arm by utilizing motor imagery, P300 and error-related potentials (ErRP) to align the robot arm with desired target position. In the proposed scheme, the users generate motor imagery signals to control the motion of the robot arm. The P300 waveforms are detected when the user intends to stop the motion of the robot on reaching the goal position. The error potentials are employed as feedback response by the user. On detection of error the control system performs the necessary corrections on the robot arm. Here, an AdaBoost-Support Vector Machine (SVM) classifier is used to decode the 4-class motor imagery and an SVM is used to decode the presence of P300 and ErRP waveforms. The average steady-state error, peak overshoot and settling time obtained for our proposed approach is 0.045, 2.8% and 44 s, respectively, and the average rate of reaching the target is 95%. The results obtained for the proposed control scheme make it suitable for designs of prosthetics in rehabilitative applications.

show abstract

“…This work uses Bacterial Foraging Algorithm [22] whose step size C is selected by the use of Learning Automata [23]. A brief description of the scheme is presented, here.…”

Section: Our Proposed Feature Selection Scheme: Bfo-lamentioning

confidence: 99%

“…At state S m , on selecting a subset of features using the k th member θ k having fitness J k which was updated in BFO using C j , the state transition probabilities are updated using Linear Reinforcement Scheme [23] given by (5) and (6).…”

Section: ) Updating State Transition Probability Matrixmentioning

confidence: 99%

A bacterial foraging optimization and learning automata based feature selection for motor imagery EEG classification

Pal

Bhattacharyya

Roy

et al. 2014

2014 International Conference on Signal Processing and Communications (SPCOM)

Self Cite

View full text Add to dashboard Cite

Selection of relevant features is an open problem inBrain-computer interfacing (BCI) research. Sometimes, features extracted from brain signals are high dimensional which in turn affects the accuracy of the classifier. Selection of the most relevant features improves the performance of the classifier and reduces the computational cost of the system. In this study, we have used a combination of Bacterial Foraging Optimization and Learning Automata to determine the best subset of features from a given motor imagery electroencephalography (EEG) based BCI dataset. Here, we have employed Discrete Wavelet Transform to obtain a high dimensional feature set and classified it by Distance Likelihood Ratio Test. Our proposed feature selector produced an accuracy of 80.291% in 216 seconds.

show abstract

Automatic feature selection of motor imagery EEG signals using differential evolution and learning automata

Cited by 51 publications

References 39 publications

Fuzzy clustering-based feature extraction method for mental task classification

Fuzzy clustering-based feature extraction method for mental task classification

Motor imagery, P300 and error-related EEG-based robot arm movement control for rehabilitation purpose

A bacterial foraging optimization and learning automata based feature selection for motor imagery EEG classification

Contact Info

Product

Resources

About