System for adaptive control of prostheses using real-time electromyographic pattern recognition
DE202026102292U1Undetermined Publication Date: 2026-08-06EASWARI ENG COLLEGE +3
0 Cites 0 Cited by
Patent Information
- Authority / Receiving Office
- DE · DE
- Patent Type
- Utility models
- Current Assignee / Owner
- EASWARI ENG COLLEGE
- Filing Date
- 2026-04-23
- Publication Date
- 2026-08-06
Abstract
A system for the adaptive control of prosthetic legs using real-time electromyographic pattern recognition, comprising: a prosthetic structure with a socket interface for receiving a user's residual limb; a plurality of electromyographic sensor electrodes embedded in the socket interface and positioned to detect bioelectrical signals generated by muscle activity; a signal processing unit electrically connected to the plurality of electromyographic sensor electrodes and configured to amplify and filter the detected signals to remove noise components such as motion artifacts and electromagnetic interference; an analog-to-digital converter unit operationally connected to the signal processing unit and configured to convert processed analog signals into digital signal streams at a predefined sampling rate;a processing unit that is operationally coupled to the analog-to-digital converter unit and configured to execute stored instructions for segmenting the digital signal streams into time windows and normalizing the segmented signals; a feature extraction unit that is connected to the processing unit and configured to compute a variety of features in the time and frequency domains from the segmented signals; a pattern recognition unit that is operationally connected to the feature extraction unit and configured to classify the computed features into a variety of movement intention classes corresponding to the movements of the prosthetic limbs;an adaptive learning unit that is operationally coupled to the pattern recognition unit and configured to update classification parameters based on temporal variations in the electromyographic signals and user-specific usage patterns; a control signal generation unit configured to convert classified movement intention classes into actuator control signals; and an actuation unit located within the prosthetic structure and functionally coupled to the control signal generation unit to generate controlled mechanical movement of the prosthesis.
Need to check novelty before this filing date? Find Prior Art