Mental Workload Estimation with Electroencephalogram Signals by Combining Multi-Space Deep Models

TL;DR

This paper presents a novel multi-space deep learning approach combining time and frequency domain analysis of EEG signals to accurately estimate mental workload levels, with potential applications in healthcare.

Contribution

It introduces a new architecture that combines Temporal Convolutional Networks and Multi-Dimensional Residual Blocks for improved mental workload estimation from EEG signals.

Findings

Achieved 74.98% accuracy in three-class mental workload classification.

Surpassed baseline data accuracy of 69.00%.

Demonstrated effective continuous mental workload estimation with a CCC of 0.629.

Abstract

The human brain remains continuously active, whether an individual is working or at rest. Mental activity is a daily process, and if the brain becomes excessively active, known as overload, it can adversely affect human health. Recently, advancements in early prediction of mental health conditions have emerged, aiming to prevent serious consequences and enhance the overall quality of life. Consequently, the estimation of mental status has garnered significant attention from diverse researchers due to its potential benefits. While various signals are employed to assess mental state, the electroencephalogram, containing extensive information about the brain, is widely utilized by researchers. In this paper, we categorize mental workload into three states (low, middle, and high) and estimate a continuum of mental workload levels. Our method leverages information from multiple spatial dimensions to achieve optimal results in mental estimation. For the time domain approach, we employ Temporal Convolutional Networks. In the frequency domain, we introduce a novel architecture based on combining residual blocks, termed the Multi-Dimensional Residual Block. The integration of these two domains yields significant results compared to individual estimates in each domain. Our approach achieved a 74.98% accuracy in the three-class classification, surpassing the provided data results at 69.00%. Specially, our method demonstrates efficacy in estimating continuous levels, evidenced by a corresponding Concordance Correlation Coefficient (CCC) result of 0.629. The combination of time and frequency domain analysis in our approach highlights the exciting potential to improve healthcare applications in the future.