Toward optimal feature and time segment selection by divergence method for EEG signals classification

• Published in: Computers in biology and medicine Vol. 97; pp. 161 - 170
• Main Authors: Wang, Jie, Feng, Zuren, Lu, Na, Luo, Jing
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.06.2018; Elsevier Limited
• Subjects: Accuracy; Algorithms; Autoregressive models; Brain; Brain-Computer Interfaces; Classification; Computational neuroscience; Computer science; Datasets; Divergence; EEG; EEG signals; Electroencephalography; Electroencephalography - methods; Feature extraction; Feature selection; Filtration; Human-computer interface; Humans; Image classification; Implants; Internal Medicine; Kullback-Leibler divergence; Mental task performance; Methods; Other; Preprocessing; Signal classification; Signal processing; Signal Processing, Computer-Assisted; Statistical models; Time segment selection; Feature selection; EEG signals; Kullback-Leibler divergence; Time segment selection; Classification
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2018.04.022

Feature selection plays an important role in the field of EEG signals based motor imagery pattern classification. It is a process that aims to select an optimal feature subset from the original set. Two significant advantages involved are: lowering the computational burden so as to speed up the learning procedure and removing redundant and irrelevant features so as to improve the classification performance. Therefore, feature selection is widely employed in the classification of EEG signals in practical brain-computer interface systems. In this paper, we present a novel statistical model to select the optimal feature subset based on the Kullback-Leibler divergence measure, and automatically select the optimal subject-specific time segment. The proposed method comprises four successive stages: a broad frequency band filtering and common spatial pattern enhancement as preprocessing, features extraction by autoregressive model and log-variance, the Kullback-Leibler divergence based optimal feature and time segment selection and linear discriminate analysis classification. More importantly, this paper provides a potential framework for combining other feature extraction models and classification algorithms with the proposed method for EEG signals classification. Experiments on single-trial EEG signals from two public competition datasets not only demonstrate that the proposed method is effective in selecting discriminative features and time segment, but also show that the proposed method yields relatively better classification results in comparison with other competitive methods. •This paper presents a novel statistical method to select the most discriminative features.•Simultaneously, this novel method automatically selects the optimal subject-specific time segment for classification.•The Parzen window is introduced in this method to estimate the conditional probability for each single feature without requiring permutation over all features.•This paper provides a potential framework for combining other feature extraction models and classification algorithms with the proposed optimal feature and time segment selection scheme for EEG signals classification.