dc.contributor.authorDai, Zhongxiang
dc.contributor.authorBezerianos, Anastasios
dc.contributor.authorChen, Annabel Shen-Hsing
dc.contributor.authorSun, Yu
dc.date.accessioned2018-11-28T08:54:38Z
dc.date.available2018-11-28T08:54:38Z
dc.date.issued2017
dc.identifier.citationDai, Z., Bezerianos, A., Chen, A. S.-H., & Sun, Y. (2017). Mental workload classification in n-back tasks based on single trial EEG. Chinese Journal of Scientific Instrument, 38(6), 1335-1344.en_US
dc.identifier.issn0254-3087en_US
dc.identifier.urihttp://hdl.handle.net/10220/46720
dc.description.abstractMental workload estimation has been under extensive investigation over the years, because the capability of monitoring the cognitive workload enables the prevention of cognitive overloading and improvement of workplace safety. Electroencephalogram (EEG) signals has been found to be an objective and non intrusive measure of mental workload. However, the evaluation of cognitive workload based on single trial EEG data, which is an essential step towards real time workload monitoring and brain computer interface, has been a major challenge. Recently, a number of advanced feature extraction methods and machine learning algorithms have been employed in EEG based mental workload assessment. In this study, we performed single trial workload classification using the EEG data recorded during the performance of n back tasks with 2 levels of difficulty (corresponding to low and high levels of workload respectively), examined the effectiveness of 3 types of feature extraction (spectral power, discrete wavelet transform and common spatial filtering), and evaluated the performance of 4 classification algorithms (support vector machine, K nearest neighbors, random forest and gradient boosting classifiers). Our findings indicate that common spatial filtering was the best performing individual feature extraction method for single trial based workload classification, and the optimal performance was achieved by combining the features from either spectral power or discrete wavelet transform with those from common spatial filtering, and adopting the random forest classifier. This study might provide some helpful guidance on the selection of feature extraction methods as well as machine learning algorithms in mental workload evaluation based on single trial EEG data.en_US
dc.format.extent10 p.en_US
dc.language.isoenen_US
dc.relation.ispartofseriesChinese Journal of Scientific Instrumenten_US
dc.rights© 2017 《仪器仪表学报》杂志社. This paper was published in Chinese Journal of Scientific Instrument and is made available as an electronic reprint (preprint) with permission of 《仪器仪表学报》杂志社. The published version is available at: [http://yqyb.etmchina.com/yqyb/ch/reader/view_abstract.aspx?file_no=J1601227&flag=1]. One print or electronic copy may be made for personal use only. Systematic or multiple reproduction, distribution to multiple locations via electronic or other means, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper is prohibited and is subject to penalties under law.en_US
dc.subjectElectroencephalogramen_US
dc.subjectSingle-trialen_US
dc.subjectDRNTU::Social sciences::Psychologyen_US
dc.titleMental workload classification in n-back tasks based on single trial EEGen_US
dc.typeJournal Article
dc.contributor.schoolSchool of Social Sciencesen_US
dc.description.versionPublished versionen_US
dc.identifier.urlhttp://yqyb.etmchina.com/yqyb/ch/reader/view_abstract.aspx?file_no=J1601227&flag=1


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record