Self-Paced Dynamic Infinite Mixture Model for Fatigue Evaluation of Pilots' Brains

Edmond Q. Wu; Mengchu Zhou; Dewen Hu; Longjun Zhu; Zhiri Tang; Xu Yi Qiu; Ping Yu Deng; Li Min Zhu; He Ren

doi:10.1109/TCYB.2020.3033005

Self-Paced Dynamic Infinite Mixture Model for Fatigue Evaluation of Pilots' Brains

Edmond Q. Wu, Mengchu Zhou, Dewen Hu, Longjun Zhu, Zhiri Tang, Xu Yi Qiu, Ping Yu Deng, Li Min Zhu, He Ren

Electrical and Computer Engineering

Research output: Contribution to journal › Article › peer-review

67 Scopus citations

Abstract

Current brain cognitive models are insufficient in handling outliers and dynamics of electroencephalogram (EEG) signals. This article presents a novel self-paced dynamic infinite mixture model to infer the dynamics of EEG fatigue signals. The instantaneous spectrum features provided by ensemble wavelet transform and Hilbert transform are extracted to form four fatigue indicators. The covariance of log likelihood of the complete data is proposed to accurately identify similar components and dynamics of the developed mixture model. Compared with its seven peers, the proposed model shows better performance in automatically identifying a pilot's brain workload.

Original language	English (US)
Pages (from-to)	5623-5638
Number of pages	16
Journal	IEEE Transactions on Cybernetics
Volume	52
Issue number	7
DOIs	https://doi.org/10.1109/TCYB.2020.3033005
State	Published - Jul 1 2022

All Science Journal Classification (ASJC) codes

Software
Control and Systems Engineering
Information Systems
Human-Computer Interaction
Computer Science Applications
Electrical and Electronic Engineering

Keywords

Brain fatigue
dynamic mixture model
electroencephalogram (EEG)
machine learning
self-paced learning

Access to Document

10.1109/TCYB.2020.3033005

Cite this

@article{4f10180b9ace424b90d61e514cd6189e,

title = "Self-Paced Dynamic Infinite Mixture Model for Fatigue Evaluation of Pilots' Brains",

abstract = "Current brain cognitive models are insufficient in handling outliers and dynamics of electroencephalogram (EEG) signals. This article presents a novel self-paced dynamic infinite mixture model to infer the dynamics of EEG fatigue signals. The instantaneous spectrum features provided by ensemble wavelet transform and Hilbert transform are extracted to form four fatigue indicators. The covariance of log likelihood of the complete data is proposed to accurately identify similar components and dynamics of the developed mixture model. Compared with its seven peers, the proposed model shows better performance in automatically identifying a pilot's brain workload.",

keywords = "Brain fatigue, dynamic mixture model, electroencephalogram (EEG), machine learning, self-paced learning",

author = "Wu, {Edmond Q.} and Mengchu Zhou and Dewen Hu and Longjun Zhu and Zhiri Tang and Qiu, {Xu Yi} and Deng, {Ping Yu} and Zhu, {Li Min} and He Ren",

note = "Publisher Copyright: {\textcopyright} 2013 IEEE.",

year = "2022",

month = jul,

day = "1",

doi = "10.1109/TCYB.2020.3033005",

language = "English (US)",

volume = "52",

pages = "5623--5638",

journal = "IEEE Transactions on Cybernetics",

issn = "2168-2267",

publisher = "IEEE Advancing Technology for Humanity",

number = "7",

}

TY - JOUR

T1 - Self-Paced Dynamic Infinite Mixture Model for Fatigue Evaluation of Pilots' Brains

AU - Wu, Edmond Q.

AU - Zhou, Mengchu

AU - Hu, Dewen

AU - Zhu, Longjun

AU - Tang, Zhiri

AU - Qiu, Xu Yi

AU - Deng, Ping Yu

AU - Zhu, Li Min

AU - Ren, He

PY - 2022/7/1

Y1 - 2022/7/1

N2 - Current brain cognitive models are insufficient in handling outliers and dynamics of electroencephalogram (EEG) signals. This article presents a novel self-paced dynamic infinite mixture model to infer the dynamics of EEG fatigue signals. The instantaneous spectrum features provided by ensemble wavelet transform and Hilbert transform are extracted to form four fatigue indicators. The covariance of log likelihood of the complete data is proposed to accurately identify similar components and dynamics of the developed mixture model. Compared with its seven peers, the proposed model shows better performance in automatically identifying a pilot's brain workload.

AB - Current brain cognitive models are insufficient in handling outliers and dynamics of electroencephalogram (EEG) signals. This article presents a novel self-paced dynamic infinite mixture model to infer the dynamics of EEG fatigue signals. The instantaneous spectrum features provided by ensemble wavelet transform and Hilbert transform are extracted to form four fatigue indicators. The covariance of log likelihood of the complete data is proposed to accurately identify similar components and dynamics of the developed mixture model. Compared with its seven peers, the proposed model shows better performance in automatically identifying a pilot's brain workload.

KW - Brain fatigue

KW - dynamic mixture model

KW - electroencephalogram (EEG)

KW - machine learning

KW - self-paced learning

UR - http://www.scopus.com/inward/record.url?scp=85097947772&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85097947772&partnerID=8YFLogxK

U2 - 10.1109/TCYB.2020.3033005

DO - 10.1109/TCYB.2020.3033005

M3 - Article

C2 - 33284758

AN - SCOPUS:85097947772

SN - 2168-2267

VL - 52

SP - 5623

EP - 5638

JO - IEEE Transactions on Cybernetics

JF - IEEE Transactions on Cybernetics

IS - 7

ER -

Self-Paced Dynamic Infinite Mixture Model for Fatigue Evaluation of Pilots' Brains

Abstract

All Science Journal Classification (ASJC) codes

Keywords

Access to Document

Other files and links

Fingerprint

Cite this