结合动作识别与反馈调节的神经康复互动方法
By combining electromyography signal analysis, posture recognition, and multimodal feedback modulation into a neurorehabilitation interactive method, the shortcomings of existing systems in signal processing accuracy, feedback modulation, and multi-muscle group coordination judgment are addressed. This enables real-time monitoring and adaptive correction of the patient's movement state, thereby improving training effectiveness and compliance.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- THE FIRST MEDICAL CENT CHINESE PLA GENERAL HOSPITAL
- Filing Date
- 2025-12-03
- Publication Date
- 2026-07-17
AI Technical Summary
Existing neurorehabilitation training systems have shortcomings in signal processing accuracy, real-time feedback adjustment, multi-muscle group collaborative judgment, and adaptive training mechanisms, resulting in problems such as bias in muscle control pattern judgment, sluggish movement recognition, single feedback stimulation method, inability to provide individualized adjustment, and insufficient accuracy in sensor fusion synchronization.
By collecting and analyzing electromyographic signals, posture data, and target muscle activation amplitude, the threshold is dynamically adjusted. Combined with multimodal feedback stimulation, the time interval between feedback stimulation and movement adjustment is monitored, the output ratio of non-target muscles is calculated in real time, and interference is removed through differential processing and frequency domain phase inverse superposition, so as to realize real-time monitoring and adaptive correction of movement deviation.
It improves the accuracy of electromyographic feature recognition, enhances the sensitivity and timeliness of movement deviation judgment, realizes individualized feedback adjustment, reduces muscle signal crosstalk misjudgment, and improves training compliance and rehabilitation effect.
Smart Images
Figure CN121622068B_ABST