Dynamic Coefficient Adjustment for Movement Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing movement classification methods using sensors, such as those involving Kalman filters, fail to accurately differentiate between various executions of fitness or sports exercises, particularly due to fixed mathematical models that do not account for individual differences in performance and physical abilities, leading to classification errors.
Innovation Solution
A method that adjusts coefficients within a predetermined range using sensor data, allowing for a dynamic mathematical model selection based on movement sequences, incorporating techniques like Kalman filters and Fourier series to enhance accuracy and adapt to user-specific execution variations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If fixed mathematical models with fixed coefficients are used for movement classification, then the device complexity is reduced and ease of operation is improved, but measurement precision and classification accuracy deteriorate due to inability to account for individual differences in exercise execution
Solution Approach 1:
The patent applies dynamics by transitioning from fixed coefficients to dynamically adjustable coefficients in the mathematical model. The coefficients are adapted based on sensor data and individual exercise execution patterns, allowing the model to evolve and personalize classification parameters in real-time, thereby improving accuracy without requiring a completely new system architecture
Solution Approach 2:
The patent implements parameter changes by modifying the coefficients of the mathematical model based on observed sensor data and individual execution variations. By adjusting these parameters dynamically, the system adapts to different users and their unique movement patterns, enhancing classification precision while maintaining the same underlying model structure
2Adaptability or versatility
If fixed mathematical models are used, then ease of manufacture and implementation are improved, but adaptability to different users and exercise variations deteriorates
Solution Approach 1:
The system applies self-service by automatically adapting its own coefficients through feedback from sensor data without requiring manual reconfiguration or complex setup procedures. The mathematical model self-adjusts to individual user patterns, providing adaptability while keeping implementation simple - the system does the adaptation work autonomously based on observed data
3Measurement precision
If coefficients are adjusted dynamically based on sensor data, then measurement precision and classification accuracy are improved, but device complexity and computational requirements increase
Solution Approach 1:
The patent applies partial action by adjusting only the necessary coefficients within predetermined ranges rather than completely re-computing the entire mathematical model. This selective adjustment approach achieves improved accuracy through targeted parameter modifications while limiting computational overhead and avoiding excessive processing requirements
4Reliability
If coefficients are kept within predetermined ranges during adjustment, then reliability and reduction of classification errors are improved, but adaptability to capture all exercise variations may be limited
Solution Approach 1:
The patent applies preliminary action by establishing predetermined ranges for coefficients before the classification process begins. These pre-defined boundaries ensure that coefficient adjustments remain within reliable and validated limits, preventing overfitting or erroneous classifications while still allowing sufficient flexibility to capture genuine exercise variations through controlled adaptation
Data Source
AI summary
A method for classifying movements. In the method, sensor data are first received. A characteristic measured variable is then ascertained from the received sensor data, and a movement sequence is classified based on the characteristic measured variable. The sensor data are input into a mathematical model, which includes coefficient(s) and is dependent on the characteristic measured variable. The mathematical model is selected based on the movement sequence. An equation of state of a sensor data value is determined, the equation of state including the coefficient(s). The sensor data value maps a curve of the characteristic measured variable. The coefficient(s) are adjusted based on the sensor data, the coefficient being kept within a predetermined range during the adjustment. The mathematical model is adjusted on the basis of the adjusted coefficient. An item of information is output, the type of the classified movement being part of the information.