Vigilance estimation using truncated l1 distance kernel-based sparse representation regression with physiological signals

Xuan Zhang, Dixin Wang, Hongtong Wu, Jinlong Chao, Jitao Zhong, Hong Peng, Bin Hu

Abstract: Highlights•A vigilance estimation framework based on TL1 kernel and physiological signals is proposed.•The indefinite kernel was introduced to solve the problem of physiological signal recognition.•The validation experimental results demonstrate the advantages of the proposed framework in terms of performance and parameter stability.