文献类型：期刊文献

英文题名：Bayesian Nonnegative CP Decomposition-Based Feature Extraction Algorithm for Drowsiness Detection

作者：Qian, Dong[1];Wang, Bei[1];Qing, Xiangyun[1];Zhang, Tao[2];Zhang, Yu[1];Wang, Xingyu[1];Nakamura, Masatoshi[3]

机构：[1]East China Univ Sci & Technol, Minist Educ, Key Lab Adv Control & Optimizat Chem Proc, Shanghai 200237, Peoples R China;[2]Tsinghua Univ, Dept Automat, Beijing 100086, Peoples R China;[3]Saga Univ, Inst Adv Res & Educ, Res Inst Syst Control, Saga 8400047, Japan

年份：2017

卷号：25

期号：8

起止页码：1297

外文期刊名：IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING

收录：;EI(收录号：20173704159403);WOS:【SCI-EXPANDED(收录号:WOS:000407478000023)】；

基金：This study was supported in part by the Scientific Research Foundation for the Returned Overseas Chinese Scholars, State Education Ministry, the Shanghai Natural Science Foundation under Grant 16ZR1407500, and the Medical Cooperation Project by Shanghai Municipal Science and Technology Commission under Grant 12DZ1940903.

语种：英文

外文关键词：Automatic rank determination; Bayesian nonnegative CP decomposition (BNCPD); daytime short nap; drowsiness detection; variational inference

摘要：Daytime short nap involves physiological processes, such as alertness, drowsiness and sleep. The study of the relationship between drowsiness and nap based on physiological signals is a great way to have a better understanding of the periodical rhymes of physiological states. A model of Bayesian nonnegative CP decomposition (BNCPD) was proposed to extract common multiway features from the group-level electroencephalogram (EEG) signals. As an extension of the nonnegative CP decomposition, the BNCPD model involves prior distributions of factor matrices, while the underlying CP rank could be determined automatically based on a Bayesian nonparametric approach. In terms of computational speed, variational inference was applied to approximate the posterior distributions of unknowns. Extensive simulations on the synthetic data illustrated the capability of our model to recover the true CP rank. As a real-world application, the performance of drowsiness detection during daytime short nap by using the BNCPD-based features was compared with that of other traditional feature extraction methods. Experimental results indicated that the BNCPD model outperformed other methods for feature extraction in terms of two evaluation metrics, as well as different parameter settings. Our approach is likely to be a useful tool for automatic CP rank determination and offering a plausible multiway physiological information of individual states.