Human upper limb muscle strength prediction device and method based on radial basis function neural network

• Main Authors: SHI HAOZHENG, TANG GANG, WANG SHIHUI, WANG DONGMEI
• Format: Patent
• Language: Chinese; English
• Published: 23.10.2020
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DIAGNOSIS; HUMAN NECESSITIES; HYGIENE; IDENTIFICATION; MEDICAL OR VETERINARY SCIENCE; PHYSICS; SURGERY

The invention discloses a human muscle strength prediction device and method based on a radial basis function neural network. The human upper limb muscle strength prediction device refers to an electromyographic signal and joint angle detection processing device, and comprises a surface electromyographic signal sensor, a magnetic sensitive angle sensor and a signal preprocessing unit. The prediction method comprises muscle force training and a prediction process and comprises the following steps: based on a surface electromyographic signal characteristic value of the radial basis function neural network, training of joint angle and muscle force and a muscle force prediction process, collecting required motion trail data through a vicon motion capture system; calculating muscle force to bepredicted by adopting the acquired motion trail data based on an upper limb muscle-bone model of an open source software Opensim; and acquiring electromyographic signals and joint angle data of the upper limb muscles in the m