Cross-Participant EEG-Based Assessment of Cognitive Workload Using Multi-Path Convolutional Recurrent Neural Networks.

Publisher: MDPI Country of Publication: Switzerland NLM ID: 101204366 Publication Model: Electronic Cited Medium: Internet ISSN: 1424-8220 (Electronic) Linking ISSN: 14248220 NLM ISO Abbreviation: Sensors (Basel) Subsets: MEDLINE

Original Publication: Basel, Switzerland : MDPI, c2000-

Cognition*; Electroencephalography ; Humans ; Neural Networks, Computer ; Workload

Applying deep learning methods to electroencephalograph (EEG) data for cognitive state assessment has yielded improvements over previous modeling methods. However, research focused on cross-participant cognitive workload modeling using these techniques is underrepresented. We study the problem of cross-participant state estimation in a non-stimulus-locked task environment, where a trained model is used to make workload estimates on a new participant who is not represented in the training set. Using experimental data from the Multi-Attribute Task Battery (MATB) environment, a variety of deep neural network models are evaluated in the trade-space of computational efficiency, model accuracy, variance and temporal specificity yielding three important contributions: (1) The performance of ensembles of individually-trained models is statistically indistinguishable from group-trained methods at most sequence lengths. These ensembles can be trained for a fraction of the computational cost compared to group-trained methods and enable simpler model updates. (2) While increasing temporal sequence length improves mean accuracy, it is not sufficient to overcome distributional dissimilarities between individuals’ EEG data, as it results in statistically significant increases in cross-participant variance. (3) Compared to all other networks evaluated, a novel convolutional-recurrent model using multi-path subnetworks and bi-directional, residual recurrent layers resulted in statistically significant increases in predictive accuracy and decreases in cross-participant variance.

Hum Factors. 2003 winter;45(4):635-43. (PMID: 15055460)
Front Neuroinform. 2015 Jun 18;9:16. (PMID: 26150785)
IEEE Trans Neural Netw Learn Syst. 2016 Feb;27(2):347-60. (PMID: 26595929)
Front Hum Neurosci. 2017 Jul 14;11:359. (PMID: 28769775)
Neural Comput. 1997 Nov 15;9(8):1735-80. (PMID: 9377276)
Neural Comput. 2000 Oct;12(10):2451-71. (PMID: 11032042)
Neural Netw. 2005 Jun-Jul;18(5-6):602-10. (PMID: 16112549)
Hum Factors. 1998 Mar;40(1):79-91. (PMID: 9579105)
Neural Netw. 2015 Jan;61:85-117. (PMID: 25462637)
J Neural Eng. 2018 Oct;15(5):056013. (PMID: 29932424)
Neural Netw. 2009 Nov;22(9):1305-12. (PMID: 19560898)
Front Neurorobot. 2017 Apr 10;11:19. (PMID: 28443015)
J Neural Eng. 2012 Aug;9(4):045008. (PMID: 22832068)
Neuroimage. 2012 Jan 2;59(1):64-9. (PMID: 21867763)
Eur J Neurosci. 2014 Dec;40(12):3774-84. (PMID: 25288492)

Keywords: EEG; MATB; cognitive workload; convolutional; cross-participant; ensemble; mental workload; neural network; recurrent; temporal specificity

Date Created: 20180428 Date Completed: 20180605 Latest Revision: 20240318

20240318

PMC5982227

10.3390/s18051339

29701668