Title: Time-frequency series based movement imagery classification

Authors: Sumanta Bhattacharyya; Manoj Kumar Mukul

Addresses: Department of ECE, BIT Mesra, Ranchi, Jharkhand 835215, India ' Department of ECE, BIT Mesra, Ranchi, Jharkhand 835215, India

Abstract: This paper proposes a novel pre-processing and feature extraction method for movement imagery classification based on Electroencephalogram (EEG) signal for Brain-Computer Interface (BCI). The proposed pre-processing method considers the time-frequency analysis of EEG signal. The Short Time Fourier Transforms (STFT) based time-frequency analysis is applied to generate the Time-Frequency Series (TFS) of Electrooculogram (EOG) corrected EEG signal. Further, the generated TFS of particular frequency bin is transformed into time domain signal by Inverse Short Time Fourier Transforms (ISTFT). The generated time domain signal of particular frequency bin is passed through feature extraction method. An asymmetry coefficient based on Hjorth parameter as a feature extracted for each frequency bin and further subjected to Support Vector Machine (SVM) classifier for their classification. The proposed method of EEG signal pre-processing and feature extraction outperforms the conventional method of EEG signal pre-processing like Discriminative Frequency Band Common Spatial Pattern (DFBCSP).

Keywords: asymmetry property; BCI; brain-computer interface; EEG; electroencephalogram; Hjorth parameter; movement imagery; STFT; short-time Fourier transforms; TFS; time frequency series.

DOI: 10.1504/IJBET.2018.093103

International Journal of Biomedical Engineering and Technology, 2018 Vol.27 No.1/2, pp.151 - 165

Received: 10 Feb 2017
Accepted: 19 Dec 2017
Published online: 09 Jul 2018 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article