Multichannel dynamic modeling of non-Gaussian mixtures
作者：
Highlights：
• A non-Gaussian mixture based method for dynamic modeling is proposed.
• Comparison with Gaussian mixtures and coupled hidden Markov models.
• Classification results outperform competitive methods on simulated and real data.
• Performance was measured using balanced error rate and Kappa index.
• Meaningful patterns were extracted from EEG signals during neuropsychological tests.
摘要
•A non-Gaussian mixture based method for dynamic modeling is proposed.•Comparison with Gaussian mixtures and coupled hidden Markov models.•Classification results outperform competitive methods on simulated and real data.•Performance was measured using balanced error rate and Kappa index.•Meaningful patterns were extracted from EEG signals during neuropsychological tests.
论文关键词：Dynamic modeling,Non-Gaussian mixtures,ICA,HMM,EEG
论文评审过程：Received 2 March 2018, Revised 8 April 2019, Accepted 24 April 2019, Available online 25 April 2019, Version of Record 4 May 2019.
论文官网地址：https://doi.org/10.1016/j.patcog.2019.04.022
