Correlation Coefficient Correction for Walking Velocity Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for estimating walking velocity and stride accuracy vary significantly among individuals due to differences in physique and walking style, leading to inconsistent estimation results.
Innovation Solution
A correlation coefficient correction method that dynamically adjusts the correlation coefficients between vertical movement acceleration and walking velocity or stride based on individual walking characteristics, using sensors like GPS and inertial measurement units to improve estimation accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a fixed correlation expression is used for stride estimation, then the device complexity is reduced, but the measurement precision varies significantly among different users
Solution Approach 1:
The patent applies dynamics by making the correlation coefficient adjustable and adaptable to individual users. The system transitions from a fixed correlation expression to a dynamic one where the correlation coefficient can be corrected based on each user's actual walking characteristics, thereby improving measurement precision without significantly increasing device complexity
Solution Approach 2:
The patent changes the parameter of the correlation coefficient from a fixed value to a variable that can be corrected and optimized. By allowing the correlation coefficient to be adjusted based on individual user data, the system achieves better measurement precision for different users while maintaining the overall simplicity of the estimation method
2Measurement precision
If the correlation coefficient is corrected to reflect individual walking characteristics, then the measurement precision is improved, but the device complexity increases
Solution Approach 1:
The patent implements feedback by using the actually measured walking velocity as a reference to correct the correlation coefficient. The system continuously compares the estimated velocity with the actual velocity and adjusts the correlation coefficient accordingly, improving measurement precision through this feedback mechanism while keeping the complexity manageable
Solution Approach 2:
The system applies self-service by automatically correcting its own correlation coefficient using the user's actual walking data. The correction process is performed autonomously without requiring external intervention, allowing the system to improve its accuracy for each user independently while maintaining reasonable complexity
Data Source
AI summary
Disclosed are a correlation coefficient correction method, a correlation coefficient correction apparatus, and a program, capable of improving estimation accuracy of a walking velocity or a stride of a moving object, and an exercise analysis method capable of analyzing a user's exercise with high accuracy. In one aspect, the correlation coefficient correction method includes calculating a reference velocity by using a detection result in a first sensor, calculating characteristic information regarding walking of a moving object by using a detection result in a second sensor mounted on the moving object, and correcting a correlation coefficient in a correlation expression indicating a correlation between the characteristic information and a walking velocity or a stride of the moving object by using the reference velocity.