Control strategy for intraspinal microstimulation based on central pattern generator. Issue 3 (17th February 2023)

• Record Type: Journal Article
• Authors: Lou, Xiongjie; Wu, Yan; Lu, Song; Shen, Xiaoyan
• Is Part Of: Computer methods in biomechanics and biomedical engineering. Volume 26:Issue 3(2023)
• Page Start: 305
• Page End: 314
• Publication Date: 2023-02-17
• Subjects: intraspinal microstimulation -- central pattern generator -- spinal cord injury -- functional electrical stimulation; Biomechanics -- Data processing -- Periodicals; Biomedical engineering -- Periodicals; Biomechanics -- Periodicals; Biomedical Engineering -- methods -- Periodicals; Computing Methodologies -- Periodicals; 612.7
• DOI: 10.1080/10255842.2022.2062230
• Languages: English
• ISSNs: 1025-5842

Abstract

Abstract: Intraspinal microstimulation (ISMS) is considered as a special functional electrical stimulation (FES) method. This method can restore the movement of paralyzed limbs in patients with spinal cord injury (SCI) using electrical stimulation of spinal cord. There is a special site for central pattern generator (CPG) in the spinal cord. The ISMS acts on the CPG site, and single electrode stimulation produces alternating motion in the hindlimbs of SCI rats. Based on the long short-term memory network (LSTM), a mapping model was established between the stimulation intensity of specific CPG sites and the angle of the knee joint to reflect the motor characteristics of the rat hindlimb. We proposed an LSTM-iterative learning control (ILC) strategy to form a closed-loop control to accurately control hindlimb movement. The proposed LSTM model fits the actual joint angle curve well, and the LSTM-ILC strategy can accurately regulate the hindlimb movement, allowing rats to perform rehabilitation training based on pre-set knee trajectories.