MIN2Net: End-to-End Multi-Task Learning for Subject-Independent Motor Imagery EEG Classification

• Published in: IEEE transactions on biomedical engineering Vol. 69; no. 6; pp. 2105 - 2118
• Main Authors: Autthasan, Phairot, Chaisaen, Rattanaphon, Sudhawiyangkul, Thapanun, Rangpong, Phurin, Kiatthaveephong, Suktipol, Dilokthanakul, Nat, Bhakdisongkhram, Gun, Phan, Huy, Guan, Cuntai, Wilaiprasitporn, Theerawit
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.06.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: autoencoder (AE); Brain-computer interfaces (BCIs); Calibration; Classification; deep metric learning (DML); EEG; Electroencephalography; Feature extraction; Human-computer interface; Image classification; Interfaces; Learning; Measurement; Mental task performance; motor imagery (MI); Motor skill learning; multi-task learning; Multitasking; Representations; Task analysis; Training
• ISSN: 0018-9294; 1558-2531; 1558-2531
• DOI: 10.1109/TBME.2021.3137184

Objective: Advances in the motor imagery (MI)-based brain-computer interfaces (BCIs) allow control of several applications by decoding neurophysiological phenomena, which are usually recorded by electroencephalography (EEG) using a non-invasive technique. Despite significant advances in MI-based BCI, EEG rhythms are specific to a subject and various changes over time. These issues point to significant challenges to enhance the classification performance, especially in a subject-independent manner. Methods: To overcome these challenges, we propose MIN2Net, a novel end-to-end multi-task learning to tackle this task. We integrate deep metric learning into a multi-task autoencoder to learn a compact and discriminative latent representation from EEG and perform classification simultaneously. Results: This approach reduces the complexity in pre-processing, results in significant performance improvement on EEG classification. Experimental results in a subject-independent manner show that MIN2Net outperforms the state-of-the-art techniques, achieving an F1-score improvement of 6.72% and 2.23% on the SMR-BCI and OpenBMI datasets, respectively. Conclusion: We demonstrate that MIN2Net improves discriminative information in the latent representation. Significance: This study indicates the possibility and practicality of using this model to develop MI-based BCI applications for new users without calibration.