Walking Training System Abnormal Pattern Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing walking training systems lack the ability to effectively identify and address abnormal walking patterns in trainees, particularly for individuals with paralysis, leading to inadequate rehabilitation outcomes.
Innovation Solution
A learning system that includes a data acquisition unit, sensor, and control unit to detect and analyze walking motion data, generating learning data to construct a model that identifies abnormal walking patterns and adjusts settings to improve training efficacy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a walking training apparatus includes sensors and actuators to assist walking motion, then the training can be more effectively guided, but the system complexity increases
Solution Approach 1:
The system divides the walking training into multiple detection phases (pre-walking, during-walking, post-walking) and processes different types of data (motion amounts, abnormal walking patterns, setting parameters) separately through specialized units (detection unit, evaluation unit, learning unit), making the complex system more manageable and maintainable
Solution Approach 2:
The system implements a closed-loop feedback mechanism where sensor data is continuously collected, processed through the learning model to identify abnormal walking patterns, and used to adjust actuator control in real-time, improving training effectiveness through adaptive control
2Measurement precision
If the system collects and processes detailed walking motion data to identify abnormal patterns, then rehabilitation outcomes improve, but data processing requirements and computational complexity increase
Solution Approach 1:
The system extracts and focuses on specific critical features from the comprehensive sensor data, namely motion amounts (joint angles, step length, walking speed) and abnormalities in walking patterns, rather than processing all raw data, thereby reducing computational complexity while maintaining detection accuracy
Solution Approach 2:
The learning model is pre-trained using historical data and predetermined abnormal walking criteria before actual training sessions, enabling the system to quickly identify abnormal patterns during real-time operation without requiring complex on-the-fly processing
3Manufacturing precision
If the learning model uses rehabilitation data from multiple walking cycles before and after changes, then the model accuracy improves, but the time required for data collection and processing increases
Solution Approach 1:
The system collects and processes a limited but sufficient number of walking cycles (before and after changes) rather than all possible historical data, achieving adequate model accuracy while minimizing time consumption. The learning unit selectively processes only the necessary data points needed for effective pattern recognition
Data Source
AI summary
The learning apparatus 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.