Mental State Classification Using Multi-Graph Features

Author:

Chen Guodong,Helm Hayden S.,Lytvynets Kate,Yang Weiwei,Priebe Carey E.

Abstract

We consider the problem of extracting features from passive, multi-channel electroencephalogram (EEG) devices for downstream inference tasks related to high-level mental states such as stress and cognitive load. Our proposed feature extraction method uses recently developed spectral-based multi-graph tools and applies them to the time series of graphs implied by the statistical dependence structure (e.g., correlation) amongst the multiple sensors. We study the features in the context of two datasets each consisting of at least 30 participants and recorded using multi-channel EEG systems. We compare the classification performance of a classifier trained on the proposed features to a classifier trained on the traditional band power-based features in three settings and find that the two feature sets offer complementary predictive information. We conclude by showing that the importance of particular channels and pairs of channels for classification when using the proposed features is neuroscientifically valid.

Funder

Microsoft Research

Publisher

Frontiers Media SA

Subject

Behavioral Neuroscience,Biological Psychiatry,Psychiatry and Mental health,Neurology,Neuropsychology and Physiological Psychology

Reference43 articles.

1. Filter bank common spatial pattern (FBCSP) in brain-computer interface,;Ang,2008

2. Inference for multiple heterogeneous networks with a common invariant subspace;Arroyo;J. Mach. Learn. Res,2021

3. Statistical inference on random dot product graphs: a survey.;Athreya;J. Mach. Learn. Res,2018

4. Out-of-sample extensions for LLE, Isomap, MDS, Eigenmaps, and spectral clustering;Bengio;Adv. Neural Inform. Process. Syst,2003

5. Optimizing spatial filters for robust EEG single-trial analysis;Blankertz;IEEE Signal Process. Mag,2007

Cited by 2 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3