Transferable multi-modal fusion continuous prediction method

• Main Authors: GUO ZHENPENG, LONG JINYI
• Format: Patent
• Language: Chinese; English
• Published: 29.12.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DIAGNOSIS; ELECTRIC DIGITAL DATA PROCESSING; HUMAN NECESSITIES; HYGIENE; IDENTIFICATION; MEDICAL OR VETERINARY SCIENCE; PHYSICS; SURGERY

The invention discloses a transferable multi-modal fusion continuous prediction method, and particularly relates to the technical field of multi-modal biological signal analysis, and the method comprises the following steps: designing an experiment normal form and a multi-modal physiological signal collection system to collect multi-modal physiological signals, taking muscle electric signals and gyroscope signals as training data, and carrying out the analysis of the multi-modal physiological signals; a virtual reality signal is used as a real label, then a neural network for simultaneously predicting a knee joint angle and a corresponding gait phase is designed, then the prediction performance of the designed neural network is evaluated, and more accurate prediction of the knee joint angle and the corresponding gait phase is provided for a subject. The invention relates to a transferable multi-modal fusion continuous prediction method for a knee joint angle and a gait phase, which is used for processing a mu