MFFNet: Multi-dimensional Feature Fusion Network based on attention mechanism for sEMG analysis to detect muscle fatigue

Abstract Muscle fatigue detection based on surface Electromyography (sEMG) is one of the essential goals of human–computer interaction. The main challenge is that the sEMG signal is unstable and complex. Meanwhile, the individual’s difference in fatigue tolerance will increase the detection difficulty. In order to reduce the impact of the above challenges, in this article, we use the sEMG signal to detect muscle fatigue based on the Multi-dimensional Feature Fusion Network (MFFNet), which is composed of Attention Frequency domain Network (AFNet) and Attention Time domain Network (ATNet). Precisely, AFNet consists of the convolutional neural network, channel attention network and spatial attention network. ATNet is composed of a two-way long and short-term memory network and time attention network. Furthermore, through the filter and Gaussian short-time Fourier transform, we can analyze the feature of the time domain and frequency domain of sEMG. Subsequently, fuse features of different dimensions are used to predict fatigue detection in many muscle fatigue detection experiments based on sEMG. The proposed method has better performance and interpretability. Experimental results prove that the proposed method can promote the development of sEMG in the field of muscle fatigue detection.