Bed Rest State Modeling for Body Condition Prediction Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for predicting physical condition changes in subjects on a bed lack the necessary accuracy, particularly in determining bed rest states and identifying regularities in biological data to improve prediction models.
Innovation Solution
A method involving supervised machine learning to create a physical condition variation prediction model by acquiring biological information, determining bed rest states, identifying state trends, and associating regularities with physical condition variations using sensors and a system comprising load sensors, a control unit, and a storage unit to enhance prediction accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If simple body movement data is used for prediction, then the system is easy to operate, but prediction accuracy is insufficient
Solution Approach 1:
The patent segments the prediction system into multiple processing stages: data acquisition from sensors, bed rest state determination, state trend acquisition, regularity identification, and physical condition prediction. Each stage processes specific features independently, allowing complex analysis without requiring a monolithic complex system structure.
Solution Approach 2:
The patent transforms the prediction approach by adding temporal dimensionality through state trends and regularity identification. Instead of analyzing static body movement data, the system analyzes time-series patterns and fluctuations, converting simple spatial data into multi-dimensional temporal patterns that improve prediction accuracy.
2Measurement precision
If detailed biological information is collected to improve prediction accuracy, then measurement precision improves, but the quantity of data to process increases
Solution Approach 1:
The patent extracts only the most relevant features from raw biological data: bed rest state determination extracts key posture information, state trend acquisition extracts temporal patterns, and regularity identification extracts fluctuation patterns. This selective extraction reduces data volume while maintaining prediction accuracy by focusing on discriminative features.
Solution Approach 2:
The patent performs preliminary processing steps before final prediction: bed rest state determination and state trend acquisition are conducted in advance to preprocess raw data into meaningful patterns. This preliminary action reduces the complexity of the final prediction task by pre-organizing data into structured formats.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method for creating a physical condition variation prediction model (MPRE) for predicting variation in a physical condition of a subject (S) on a bed (BD) includes acquiring biological information of a subject for teaching data by a sensor (LS1 to LS4), determining a bed rest state of the subject for teaching data on the basis of the biological information of the subject for teaching data, acquiring a state trend corresponding to a trend of the bed rest state per unit time, identifying a regularity included in temporal fluctuation of the state trend, and creating, by supervised machine learning using teaching data obtained by associating the regularity and physical condition variation information indicating variation in a physical condition of the subject for teaching data, a physical condition variation prediction model obtained by learning a correlation between the regularity and the physical condition variation information of the subject for teaching data.