Medical Robot Learning Data Extraction via Behavior Basis Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In machine learning applications for medical support robots, there is a need for a technique to extract optimal learning data effectively.
Innovation Solution
An information processing apparatus is developed, comprising an acquisition unit for obtaining treatment images, a behavior output unit for providing behavior information and basis regions, a basis output unit for outputting basis information, a presentation unit for displaying this information to users, and a storage unit for storing user input as learning data for multiple recognizers and classifiers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple recognizers are used to output behavior information and basis regions, then the accuracy of machine learning is improved, but the device complexity increases
Solution Approach 1:
The system divides the recognition task into multiple specialized recognizers (first recognizer for offline learning, second recognizer for online learning), each handling specific aspects of behavior recognition. This segmentation allows each recognizer to be optimized for its specific function, improving overall accuracy while maintaining manageable complexity through modular architecture.
Solution Approach 2:
The system adds a temporal dimension to recognition by implementing both offline and online learning modes. The offline recognizer processes historical data while the online recognizer handles real-time data, creating a multi-dimensional approach that improves accuracy without simply increasing the complexity of a single recognizer.
2Productivity
If learning data is extracted and stored for multiple recognizers and classifiers, then the productivity of machine learning is improved, but the loss of information increases
Solution Approach 1:
The system implements feedback mechanisms where the presentation unit displays behavior information and basis information to users, allowing user input that feeds back into the learning data storage. This feedback loop ensures that only relevant and validated information is stored as learning data, improving productivity while minimizing information loss through selective refinement.
Solution Approach 2:
The system changes the parameters of learning data by extracting and storing only specific behavior information and basis information that are relevant to the recognition tasks. This parameter selection process transforms raw data into optimized learning data, improving productivity while reducing information loss by focusing on essential features.
Data Source
AI summary
An information processing apparatus according to one embodiment of the present technology includes an acquisition unit, a behavior output unit, a basis output unit, a presentation unit, and a storage unit. The acquisition unit acquires a treatment image related to treatment. The behavior output unit outputs behavior information related to a behavior of a medical device related to the treatment, and a basis region indicating position information of a basis on which the behavior information is output, by inputting the treatment image to each of a plurality of recognizers. The basis output unit outputs basis information related to the basis by inputting the treatment image cropped on the basis of the basis region to a classifier. The presentation unit presents a plurality of pieces of the behavior information and a plurality of pieces of the basis information to the user. The storage unit stores input information input by the user on the basis of the behavior information and the basis information, as learning data of the plurality of recognizers and the classifier.