Neuromuscular Source Signal Separation for Stable Structure Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Neuromuscular signals detected by sensors are influenced by sensor position, movement, and contact quality, making it difficult to use them for robust and reliable applications such as controlling devices or predicting motor tasks.
Innovation Solution
Applying source separation techniques to recorded neuromuscular signals to obtain neuromuscular source signals, which are less sensitive to these factors, and identifying associated biological structures using a trained statistical classifier.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If neuromuscular sensors are used to detect electrical activity from multiple biological structures, then the sensors can capture comprehensive neural activation information, but the signals become complex and superimposed making it difficult to identify specific biological structures
Solution Approach 1:
The patent applies Independent Component Analysis (ICA) to decompose the complex superimposed neuromuscular signals into separate independent source signals, each corresponding to a specific biological structure. This segmentation process separates the mixed signals captured by the sensors into distinct components, enabling identification of individual muscle or neural sources while preserving the comprehensive information from all sources.
2Ease of operation
If neuromuscular sensors are positioned on the body surface to detect electrical activity, then the sensors can non-invasively capture neural activation, but the signals become sensitive to sensor position, movement, and contact quality
Solution Approach 1:
The patent introduces ICA as an intermediary computational process that processes the raw sensor signals to remove artifacts caused by sensor movement and position changes. The ICA algorithm identifies and separates artifact components from genuine neuromuscular signals, thereby maintaining signal reliability while preserving the ease of non-invasive surface measurement.
3Reliability
If source separation techniques are applied to obtain neuromuscular source signals, then the signals become less sensitive to sensor position and movement, but additional processing steps are required
Solution Approach 1:
The ICA algorithm operates autonomously to separate the mixed signals into independent sources without requiring manual intervention or complex configuration. The algorithm automatically identifies the mixing matrix and source signals, providing robust source separation that reduces sensitivity to sensor artifacts while maintaining relatively simple processing that can be implemented through standardized computational routines.
Data Source
AI summary
A system comprising a plurality of neuromuscular sensors, each of which is configured to record a time-series of neuromuscular signals from a surface of a user's body; and at least one computer hardware processor programmed to perform: applying a source separation technique to the time series of neuromuscular signals recorded by the plurality of neuromuscular sensors to obtain a plurality of neuromuscular source signals and corresponding mixing information; providing features, obtained from the plurality of neuromuscular source signals and/or the corresponding mixing information, as input to a trained statistical classifier and obtaining corresponding output; and identifying, based on the output of the trained statistical classifier, and for each of one or more of the plurality of neuromuscular source signals, an associated set of one or more biological structures.