Subject-Independent Brain-Computer Interfaces Based on Deep Convolutional Neural Networks

• Published in: IEEE transaction on neural networks and learning systems Vol. 31; no. 10; pp. 3839 - 3852
• Main Authors: Kwon, O-Yeon, Lee, Min-Ho, Guan, Cuntai, Lee, Seong-Whan
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.10.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Band theory; Bayesian analysis; Brain; Brain modeling; Brain–computer interface (BCI); Calibration; convolutional neural networks (CNNs); Covariance matrix; deep learning (DL); EEG; Electrodes; Electroencephalography; electroencephalography (EEG); Embedding; Feature extraction; Filter banks; Frequencies; Frequency dependence; Human-computer interface; Imagery; Information theory; Interfaces; Mathematical models; Mental task performance; Model accuracy; motor imagery (MI); Neural networks; Optimization; Representations; Spectra; subject-independent; Task analysis

For a brain-computer interface (BCI) system, a calibration procedure is required for each individual user before he/she can use the BCI. This procedure requires approximately 20-30 min to collect enough data to build a reliable decoder. It is, therefore, an interesting topic to build a calibration-f...