Graph Signal Processing Based Cross-Subject Mental Task Classification Using Multi-Channel EEG Signals

• Published in: IEEE sensors journal Vol. 22; no. 8; pp. 7971 - 7978
• Main Authors: Mathur, Priyanka, Chakka, Vijay Kumar
• Format: Journal Article
• Language: English
• Published: New York IEEE 15.04.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Brain-Computer Interface (BCI); Cognitive tasks; Eigenvalues; Eigenvectors; Electroencephalography; Feature extraction; graph Laplacian energy (GLE); graph signal processing (GSP); Graphical representations; Human-computer interface; Information transfer; joint total variation energy (JTVE) and cross subject classification; Laplace equations; Laplacian matrix; Mathematical analysis; Matrix decomposition; MTMC EEG signals; Nodes; Radial basis function; Random noise; Signal classification; Signal processing; Smoothness; Task analysis; two norm total variation of eigen vector (TNTV)

Classification of mental tasks from electroencephalogram (EEG) signals play a crucial role in designing various brain-computer interface (BCI) applications. Most of the current techniques consider each channel as independent, neglecting the functional connectivity of the brain during mental activity...