The classification of EEG-based winking signals: a transfer learning and random forest pipeline

Jothi Letchumy Mahendra Kumar; Mamunur Rashid; Rabiu Muazu Musa; Mohd Azraai Mohd Razman; Norizam Sulaiman; Rozita Jailani; Anwar P P Abdul Majeed

doi:10.7717/peerj.11182

The classification of EEG-based winking signals: a transfer learning and random forest pipeline

PeerJ. 2021 Mar 31:9:e11182. doi: 10.7717/peerj.11182. eCollection 2021.

Authors

Jothi Letchumy Mahendra Kumar¹, Mamunur Rashid², Rabiu Muazu Musa³, Mohd Azraai Mohd Razman¹, Norizam Sulaiman², Rozita Jailani⁴, Anwar P P Abdul Majeed^{1

5}

Affiliations

¹ Innovative Manufacturing, Mechatronics and Sports Laboratory, Faculty of Manufacturing and Mechatronics Engineering Technology, Universiti Malaysia Pahang, Pekan, Pahang Darul Makmur, Malaysia.
² Faculty of Electrical and Electronics Engineering Technology, Universiti Malaysia Pahang, Pekan, Pahang, Malaysia.
³ Centre for Fundamental and Liberal Education, Universiti Malaysia Terengganu, Kuala Nerus, Terengganu, Malaysia.
⁴ Faculty of Electrical Engineering, Universiti Teknologi MARA, Shah Alam, Selangor, Malaysia.
⁵ Centre for Software Development & Integrated Computing, Universiti Malaysia Pahang, Gambang, Malaysia.

Abstract

Brain Computer-Interface (BCI) technology plays a considerable role in the control of rehabilitation or peripheral devices for stroke patients. This is particularly due to their inability to control such devices from their inherent physical limitations after such an attack. More often than not, the control of such devices exploits electroencephalogram (EEG) signals. Nonetheless, it is worth noting that the extraction of the features and the classification of the signals is non-trivial for a successful BCI system. The use of Transfer Learning (TL) has been demonstrated to be a powerful tool in the extraction of essential features. However, the employment of such a method towards BCI applications, particularly in regard to EEG signals, are somewhat limited. The present study aims to evaluate the effectiveness of different TL models in extracting features for the classification of wink-based EEG signals. The extracted features are classified by means of fine-tuned Random Forest (RF) classifier. The raw EEG signals are transformed into a scalogram image via Continuous Wavelet Transform (CWT) before it was fed into the TL models, namely InceptionV3, Inception ResNetV2, Xception and MobileNet. The dataset was divided into training, validation, and test datasets, respectively, via a stratified ratio of 60:20:20. The hyperparameters of the RF models were optimised through the grid search approach, in which the five-fold cross-validation technique was adopted. The optimised RF classifier performance was compared with the conventional TL-based CNN classifier performance. It was demonstrated from the study that the best TL model identified is the Inception ResNetV2 along with an optimised RF pipeline, as it was able to yield a classification accuracy of 100% on both the training and validation dataset. Therefore, it could be established from the study that a comparable classification efficacy is attainable via the Inception ResNetV2 with an optimised RF pipeline. It is envisaged that the implementation of the proposed architecture to a BCI system would potentially facilitate post-stroke patients to lead a better life quality.

Keywords: Continuous wavelet transform; EEG; Random forest; Transfer learning; Winking.

Grants and funding

This work was supported by Universiti Malaysia Pahang via grant number RDU180321. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.