A Real-Time Capable Linear Time Classifier Scheme for Anticipated Hand Movements Recognition from Amputee Subjects Using Surface EMG Signals

• Published in: Ingénierie et recherche biomédicale Vol. 42; no. 4; pp. 277 - 293
• Main Authors: Arunraj, M., Srinivasan, A., Arjunan, S.P.
• Format: Journal Article
• Language: English
• Published: Elsevier Masson SAS 01.08.2021
• Subjects: EMG; Fourier features; Internal Medicine; Kernel; Non-negative factorization; Random projection; Tikhonov regularization; Random projection; Tikhonov regularization; Kernel; EMG; Non-negative factorization; Fourier features

•A fast kernel approximation is applied for capturing non-linear properties of EMG.•A non-negative constraint is applied for accuracy improvement in certain cases.•The sparsity issue of EMG signals is ad- dressed via collaborative representation.•Obtained state-of-the-art results for both accuracy a...