Development of a non-attached multi-person emotion recognition system based on sitting body motion signals

Automatic emotion recognition is a popular application field under the rapid development of sensing and information technology. Traditional automatic emotion recognition mainly uses attached sensors for target signal recognition, which is difficult to widely apply in practice because of expensive equipment, complex sensing systems, susceptibility to interference, and the potential to cause predictive emotional interference for users. In this work, a Non-attached Multi-person Emotion Recognition System (NMERS) is constructed, which recognizes the different emotions of multiple people through human sitting body motion signals. A flexible sensing cushion composed of four pressure sensors is used to collect real-time sitting motion signals from the user in a non-attached way. The Convolutional Neural Network-Long Short-Term Memory-Attention (CLATT) neural network model establishes the mapping relationship between the sitting body motion signals and four emotional categories, achieving an average accuracy of 98.05% for individual classification and 91.25% for cross-individual classification. Subsequently, by deploying CLATT on the upper computer and networking multiple sensing subsystems, real-time emotional state recognition of multi-person via a non-attached sensing system is successfully realized. NMERS builds a bridge between human body motion signals and emotional states, enhancing the practical application value of automatic emotion recognition systems.