Learning System for Abnormal Walking Pattern Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing walking training systems struggle to effectively identify and address abnormal walking patterns in trainees, which can hinder the appropriateness and effectiveness of walking training.
Innovation Solution
A learning system that includes a data acquisition unit, a data generation unit, and a learning unit to analyze rehabilitation data from a walking training system. This system evaluates walking motion data against predetermined abnormal walking criteria, generates learning data from this evaluation, and performs machine learning to construct a model that outputs setting parameters associated with abnormal walking patterns.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a walking training system uses sensors to detect motion amounts and evaluates walking patterns, then the ability to identify abnormal walking patterns is improved, but the device complexity increases
Solution Approach 1:
The patent replaces complex mechanical evaluation systems with a sensor-based detection system. Sensors detect motion amounts (joint angles, positions) which are then processed through a learning model to identify abnormal walking patterns, eliminating the need for complex mechanical evaluation mechanisms while improving measurement precision
Solution Approach 2:
The learning model acts as an intermediary between sensor data and abnormal walking pattern identification. It processes raw sensor data (motion amounts) and transforms it into meaningful evaluations of abnormal walking patterns, simplifying the overall system architecture while maintaining high measurement precision
2Productivity
If the system collects and processes rehabilitation data through machine learning, then the effectiveness of walking training is improved, but the loss of time increases
Solution Approach 1:
The system performs preliminary data processing by collecting and storing rehabilitation data during training sessions. The learning model is pre-trained to recognize abnormal walking patterns, allowing for rapid real-time evaluation without requiring extensive processing time during actual training, thus maintaining high productivity while minimizing time loss
Solution Approach 2:
The system continuously collects and processes rehabilitation data without interruption during training sessions. The learning model operates in real-time to continuously identify abnormal walking patterns, ensuring that data processing is an ongoing useful action rather than a separate time-consuming step, thereby maintaining training effectiveness while reducing time loss
3Adaptability or versatility
If the system uses learning models to analyze walking data, then the adaptability to different trainees is improved, but the device complexity increases
Solution Approach 1:
The learning model adapts to different trainees by processing and analyzing motion amount parameters (joint angles, positions, velocities) that vary between individuals. The model learns from rehabilitation data to identify abnormal walking patterns specific to each trainee's characteristics, providing high adaptability while using a relatively simple sensor-based parameter collection system
Solution Approach 2:
The learning model serves multiple functions: it detects abnormal walking patterns, evaluates training progress, and provides feedback for training adjustment. This multi-functionality is achieved through a single integrated model that processes the same sensor data (motion amounts) for different purposes, improving adaptability without proportionally increasing device complexity
Data Source
AI summary
The learning system includes a data generation unit configured to generate learning data based on rehabilitation data and a learning unit configured to perform machine learning using the learning data. A sensor is provided to detect a plurality of motion amounts in a walking motion of a trainee, and it is evaluated that, when one of the motion amounts matches one of abnormal walking criteria, that the walking motion is an abnormal walking pattern that meets the matched abnormal walking criterion. The data generation unit generates each of the pieces of rehabilitation data before and after a change in the results of evaluation of the abnormal walking pattern as learning data. The learning unit sequentially inputs each of the pieces of rehabilitation data as one data set, thereby performing machine learning.