SGL-Net: An Ultralightweight Fatigue Detection Network in Fast Deployment Scenarios

Abstract

Prolonged fatigue not only affects people’s learning and work efficiency but also leads to a series of symptoms such as insomnia and forgetfulness. Timely and accurately identifying fatigue states is crucial in various industries. However, existing fatigue detection methods either rely on manually extracted features which is unable to fully utilize the deep-level information of signals or are complexly designed and hard to be implemented. In this article, we propose spectral group-guided lightweight CNN (SGL-Net), which is an ultralightweight CNN model for fatigue detection. The design concept of SGL-Net is closely related to the mechanism of information processing in the human brain. First, the spectral space embedding decomposes the electroencephalogram (EEG) signal into various rhythms, we also enrich the decomposition tree using wavelet convolution, where the complex rhythm information is decoupled. Second, we propose a novel spatial-temporal modality encoder, which captures the relationship among electrodes and evaluates the power spectrum of different rhythms. Finally, a kernel-restricted multilayer perceptron (MLP) is adopted for fatigue detection, ensuring the parameter sparsity simultaneously. We also design a well-suited hardware system for EEG acquisition on the forehead. Experimental results have demonstrated the robustness, effectiveness, and practicability of the SGL-Net in real-world applications.