Physiological-signal-based mental workload estimation via transfer dynamical autoencoders in a deep learning framework

Abstract

Evaluating operator mental workload (MW) in human-machine systems via neurophysiological signals is crucial for preventing unpredicted operator performance degradation. However, the feature of physiological signals is associated with the historical values at the previous time steps and its statistical properties vary across individuals and types of mental tasks. In this study, we propose a new transfer dynamical autoencoder (TDAE) to capture the dynamical properties of electroencephalograph (EEG) features and the individual differences. The TDAE consists of three consecutively-connected modules, which are termed as feature filter, abstraction filter, and transferred MW classifier. The feature and abstraction filters introduce dynamical deep network to abstract the EEG features across adjacent time steps to salient MW indicators. Transferred MW classifier exploits large volume EEG data from an source-domain EEG database recorded under emotional stimuli to improve the model training stability. We tested our algorithms on two target EEG databases. The classification performance shows TDAE significantly outperforms existing shallow and deep MW classification models. We also investigated how to select TDAE hyper-parameters and found its superiority in accuracy can be achieved with proper filter orders.

Current Status, Challenges, and Possible Solutions of EEG-Based Brain-Computer Interface: A Comprehensive Review

“…The overall accuracy attained was 78%. With regard to the mental workload (MW) classification, several studies have been carried out (Yin and Zhang, 2017;Yang et al, 2019;Yin et al, 2019). An adaptive Stacked Denoising Auto Encoder (SDAE) was developed in Attia et al (2018) to tackle cross-session MW classification from EEG, and it was reported that the proposed classifier achieved an accuracy of 95.5%.…”

Contemporary Value Assessment of Marxist Ideology under the Context of Deep Learning

“…Numerous practices have proven that Marxism is a universally applicable reality since the May Fourth Movement and the dissemination of Marx to China. No matter in the war years or in the socialist construction in peacetime [ 12 – 14 ], Marxism has always been a guiding light for the Chinese revolution, and only under the guidance of Marxism can the Chinese revolution be invincible. In the cultivation of cultural self-confidence of college students, adhering to the Marxist view of culture has a double significance.…”

“…Cultural self-confidence has been mentioned by national leaders many times. Extensive and in-depth discussion on the cultural self-confidence of college students and new initiatives to adapt to the growth of college students under the threshold of Marxist cultural outlook are of great significance to the expansion of the breadth and depth of cultural self-confidence of college students and to the process of advancing Marxist cultural theory, which is not only beneficial to the cultivation of cultural self-confidence of college students but enables also college students to clearly understand the mainstream ideology of Chinese characteristics, which can stimulate the whole nation creativity and innovation of culture [ 14 – 16 ]. Second, it favors the advancement of ideological and political education disciplines in colleges and universities.…”

Deep Learning in EEG: Advance of the Last Ten-Year Critical Period

“…The cross-task workload classification was made by using a CNN+RNN model [116]. Another study used transfer learning strategy to improve model generalization for the classification of mental workload [117].…”