A Novel CNN-BiLSTM Ensemble Model With Attention Mechanism for Sit-to-Stand Phase Identification Using Wearable Inertial Sensors

• Published in: IEEE transactions on neural systems and rehabilitation engineering Vol. 32; pp. 1068 - 1077
• Main Authors: Chen, Xin, Cai, Shibo, Yu, Longjie, Li, Xiaoling, Fan, Bingfei, Du, Mingyu, Liu, Tao, Bao, Guanjun
• Format: Journal Article
• Language: English
• Published: United States IEEE 2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Acceleration; Algorithms; Angular velocity; attention mechanism; bidirectional long short-term memory (Bi-LSTM); Classification algorithms; convolutional neural network (CNN); Convolutional neural networks; Deep learning; Exoskeleton; Exoskeleton Device; Exoskeletons; Feature extraction; Force; Humans; inertial measurement unit (IMU); Inertial sensing devices; Learning algorithms; Legged locomotion; Machine learning; Machine learning algorithms; Momentum transfer; Movement; phase identification; Phases; Rehabilitation robots; Sensors; Sit-to-stand transition; Sitting Position; Standing Position; Velocity; Wearable Electronic Devices; Wearable technology

Sit-to-stand transition phase identification is vital in the control of a wearable exoskeleton robot for assisting patients to stand stably. In this study, we aim to propose a method for segmenting and identifying the sit-to-stand phase using two inertial sensors. First, we defined the sit-to-stand...