Inter-subject cognitive workload estimation based on a cascade ensemble of multilayer autoencoders

• Published in: Expert systems with applications Vol. 211; p. 118694
• Main Authors: Zheng, Zhanpeng, Yin, Zhong, Wang, Yongxiong, Zhang, Jianhua
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.01.2023
• Subjects: Abstraction fusion; Cognitive workload; Electroencephalogram; Extreme learning machine; Stacked denoising autoencoder; Extreme learning machine; Electroencephalogram; Abstraction fusion; Cognitive workload; Stacked denoising autoencoder
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2022.118694

•The electroencephalogram (EEG) is used to evaluate human cognitive workload.•Inter-subject EEG modeling scheme is employed.•Approach of cascade ensemble of multilayer autoencoders is proposed. Machine learning approaches can build a computational model to predict cognitive workload levels by using electroencephalogram (EEG) feature inputs at the same time instant. However, when the EEG signals are recorded on different people, the accuracy of such a model could be impaired due to its incapability of fitting varied statistical distributions across different individuals. To this end, we propose an individual-independent workload estimator, a cascade ensemble of multilayer autoencoders to tackle the individual difference within the EEG features. It could assess the workload levels of an unseen subject by adapting the EEG data recorded from non-overlapped existing subjects. We first construct a deep stacked denoising autoencoder to abstract EEG features from a specific individual. Its shallow weights are optimized with individual-specific geometrical information of the features. Then, to find generalizable feature properties, we introduce Q-statistics to measure the independence between base learners. Finally, a regularized extreme learning machine is used as a cascade meta-classifier to fuse and filter high-level EEG abstractions and determine workload levels. We employ databases from two different experiments to validate our approach. The proposed framework can lead to acceptable accuracy and computational complexity compared to several existing workload classifiers.