Rehabilitation Evaluation Apparatus Symmetric Signal Correlation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing rehabilitation evaluation methods face challenges in accurately assessing the recovery level of paralyzed limbs due to variations in muscle activity and sensor placement, leading to inefficient and time-consuming trial-and-error adjustments of myoelectric potential sensors.
Innovation Solution
A rehabilitation evaluation apparatus that uses myoelectric-signal acquisition units, sensor signal acquisition, and similarity calculation to select correlated myoelectric signals from symmetric sensor placements on both sides of the body, eliminating non-relevant signals and reducing the need for frequent sensor adjustments, thereby enabling accurate and efficient recovery level evaluation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the number of places at which myoelectric potentials are measured is increased, then the possibility of capturing relevant muscle signals improves, but data on non-working muscles becomes dominant and evaluation accuracy deteriorates
Solution Approach 1:
The patent extracts and selects only the myoelectric signals that are correlated with the sensor signal from the plurality of acquired myoelectric signals. The selection unit identifies and extracts relevant muscle signals while discarding irrelevant ones, thereby maintaining evaluation accuracy without requiring excessive measurement points.
Solution Approach 2:
The patent applies local quality by selectively processing different myoelectric signals based on their relevance to the training motion. Instead of treating all measurement points uniformly, the system identifies specific locations (muscles) that are locally relevant to the motion being evaluated and gives those signals priority in the evaluation process.
2Device complexity
If the number of places at which myoelectric potentials are measured is decreased, then data processing becomes simpler, but relevant muscle signals may be overlooked and evaluation accuracy deteriorates
Solution Approach 1:
The patent uses feedback by continuously monitoring the correlation between myoelectric signals and sensor signals. The selection unit uses the sensor signal as a reference to feedback-select which myoelectric signals are relevant, ensuring that even with fewer measurement points, the captured signals are those that matter for accurate evaluation.
Solution Approach 2:
The patent performs preliminary action by pre-identifying and selecting relevant myoelectric signals before the actual evaluation process. The selection unit determines which muscles are relevant based on their correlation with the sensor signal, preparing the data set in advance to ensure accuracy without requiring excessive measurement points.
3Measurement precision
If myoelectric sensors are adjusted through trial-and-error to find optimal positions, then measurement accuracy improves, but the time required for rehabilitation training increases
Solution Approach 1:
The patent applies self-service by allowing the system to automatically identify and select relevant muscle signals without requiring manual trial-and-error adjustment by trainers. The selection unit autonomously determines which myoelectric signals are relevant based on their correlation with sensor signals, eliminating time-consuming manual adjustment while maintaining measurement accuracy.
Solution Approach 2:
The patent replaces the mechanical trial-and-error adjustment process with an automated signal processing system. Instead of physically moving sensors to find optimal positions through manual trial and error, the system uses computational methods to identify relevant signals, substituting mechanical adjustment with automated selection based on signal correlation.
4Adaptability or versatility
If multiple myoelectric sensors are used to capture comprehensive muscle data, then the ability to identify working muscles improves, but the complexity of signal processing and selection increases
Solution Approach 1:
The patent extracts only the necessary myoelectric signals from the comprehensive set of acquired signals. The selection unit identifies and extracts signals that are correlated with the sensor signal, discarding irrelevant ones. This extraction process maintains the ability to identify working muscles while simplifying subsequent signal processing by eliminating unnecessary data.
Data Source
AI summary
A rehabilitation evaluation apparatus includes a sensor signal acquisition unit configured to acquire a sensor signal output from a detection sensor, a selection unit configured to select at least one myoelectric signal having a correlation with the sensor signal acquired by the sensor signal acquisition unit from among the plurality of second myoelectric signals on the second-side part acquired by the myoelectric-signal acquisition unit, and a similarity output unit configured to select a first myoelectric signal that has been output from a myoelectric sensor attached in a place that is left-right symmetric to a place of the myoelectric sensor that has output the second correlated myoelectric signal selected by the selection unit from among a plurality of first myoelectric signals on the first-side part acquired by the myoelectric-signal acquisition unit, calculate a similarity between these correlated myoelectric signals, and outputs the calculated similarity.