Rejecting Unknown Gestures Based on Surface-Electromyography Using Variational Autoencoder

• Published in: IEEE transactions on neural systems and rehabilitation engineering Vol. 32; pp. 750 - 758
• Main Authors: Dai, Qingfeng, Wong, Yongkang, Kankanhalli, Mohan, Li, Xiangdong, Geng, Weidong
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.01.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Decoding; Density; Electromyography; Feature extraction; Gaussian distribution; Gesture recognition; Normal distribution; Open-set recognition; Prototypes; Statistical analysis; surface electromyography; Training; variational autoencoder

The conventional surface electromyography (sEMG)-based gesture recognition systems exhibit impressive performance in controlled laboratory settings. As most systems are trained in a closed-set setting, the systems's performance may see significant deterioration when novel gestures are presented...