Gait Analysis Estimation Device Using Principal Component Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems for estimating falling risk factors rely on specific measurement devices and cannot accurately assess falling risk without analyzing gait conditions based on moving image data or measuring gait parameters using devices like sheet-type pressure sensors or motion capture systems.
Innovation Solution
An estimation device that acquires physical ability-related data through gait measurement, performs principal component analysis on this data, and estimates falling risk information, allowing for the estimation of falling risk factors using sensor data from footwear-mounted sensors and attribute data like BMI and age.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If moving image data captured by cameras or specialized measurement devices is used to analyze gait conditions, then falling risk estimation can be performed, but the system cannot estimate falling risk using general sensor data from footwear-mounted sensors
Solution Approach 1:
The patent introduces a machine learning model as an intermediary that bridges the gap between general sensor data and accurate falling risk estimation. The model processes feature amounts extracted from sensor data (acceleration, angular velocity, etc.) and transforms them into meaningful falling risk assessments, enabling accurate estimation without requiring specialized measurement devices
Solution Approach 2:
The patent changes the approach from using raw sensor data directly to using processed feature amounts as input to the machine learning model. By transforming sensor data into meaningful features (step detection, gait pattern recognition, etc.), the system achieves accurate falling risk estimation using general sensor data rather than requiring specialized equipment
2Measurement precision
If specialized measurement devices like sheet-type pressure sensors or motion capture systems are used, then gait parameters can be measured accurately, but the system cannot measure gait parameters including gait factors in daily life settings
Solution Approach 1:
The patent replaces expensive, complex specialized measurement devices with inexpensive, easily deployable footwear-mounted sensors. These simple sensors can be worn by individuals in their daily lives without requiring specialized facilities, yet they provide sufficient data for accurate gait parameter measurement through the machine learning model
Solution Approach 2:
The patent substitutes complex mechanical measurement systems (motion capture, pressure sensors) with electronic sensor data processing. By using acceleration sensors and angular velocity sensors embedded in footwear, combined with machine learning algorithms, the system achieves accurate gait analysis in natural daily life settings without requiring specialized measurement equipment
3Measurement precision
If multiple gait parameters are analyzed to estimate falling risk factors, then estimation accuracy improves, but the complexity of data processing and analysis increases
Solution Approach 1:
The patent implements self-service through automated machine learning processing. The system automatically extracts features from sensor data, processes multiple gait parameters, and generates falling risk assessments without requiring manual analysis. The machine learning model handles the complexity of processing multiple parameters internally, simplifying the overall system while maintaining high accuracy
Data Source
AI summary
Provided is an estimation device including a data acquisition unit that acquires first feature amount data related to a physical ability measured according to a gait of a subject and attribute data of the subject, an estimation unit that constructs second feature amount data related to a physical ability factor and an attribute factor by performing principal component analysis on the acquired first feature amount data and the acquired attribute data, and estimates falling risk information according to a falling risk factor using the constructed second feature amount data, and an output unit that outputs the estimated falling risk information.