Investigation of EEG Signal Classification Techniques for Brain Computer Interface
Mandeep Kaur Ghumman1, Satvir Singh2

1Mandeep Kaur Ghumman, Research Scholar, IKG Punjab Technical University Kapurthala, Punjab, India.
2Satvir Singh, Associate Professor, IKG Punjab Technical University Kapurthala, Punjab, India.
Manuscript received on January 26, 2020. | Revised Manuscript received on February 05, 2020. | Manuscript published on February 30, 2020. | PP: 3266-3274 | Volume-9 Issue-3, February 2020. | Retrieval Number:  C5679029320/2020©BEIESP | DOI: 10.35940/ijeat.C5679.029320
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (

Abstract: Brain-computer interface (BCI) has emerged as a popular research domain in recent years. The use of electroencephalography (EEG) signals for motor imagery (MI) based BCI has gained widespread attention. The first step in its implementation is to fetch EEG signals from scalp of human subject. The preprocessing of EEG signals is done before applying feature extraction, selection and classification techniques as main steps of signal processing. In preprocessing stage, artifacts are removed from raw brain signals before these are input to next stage of feature extraction. Subsequently classifier algorithms are used to classify selected features into intended MI tasks. The major challenge in a BCI systems is to improve classification accuracy of a BCI system. In this paper, an approach based on Support Vector Machine (SVM), is proposed for signal classification to improve accuracy of the BCI system. The parameters of kernel are varied to attain improvement in classification accuracy. Independent component analysis (ICA) technique is used for preprocessing and filter bank common spatial pattern (FBCSP) for feature extraction and selection. The proposed approach is evaluated on data set 2a of BCI Competition IV by using 5-fold crossvalidation procedure. Results show that it performs better in terms of classification accuracy, as compared to other methods reported in literature.
Keywords: Brain computer interface, electroencephalography, motor imagery, filter bank common spatial pattern, support vector machine, independent component analysis.