Sweat Volume Detection via Sweat Print Imaging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for sweat volume detection, such as the test paper color change method, face challenges due to variations in sweat production across body parts, non-uniform adhesion of test paper, and environmental factors like temperature and humidity, leading to significant measurement errors.
Innovation Solution
A method for sweat volume detection based on sweat print imaging, which involves collecting raw data sets of sweat print images under varying environmental conditions, partitioning images into regions based on color value extremes, constructing an error prediction model using a Back-propagation neural network, and calculating sweat volume with reduced error through trained models.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If test paper color change method is used for sweat volume detection, then the detection process is simple, but measurement precision deteriorates due to variations in sweat production across body parts, non-uniform adhesion, and environmental factors
Solution Approach 1:
The patent divides the sweat print image into multiple regions based on color value extremes, calculating sweat volume for each region separately and then summing them. This segmentation approach addresses the non-uniform adhesion and regional variation problems by treating different areas independently, thereby improving measurement precision while maintaining operational simplicity through automated image processing.
2Device complexity
If test paper color change method is used, then device complexity is low, but reliability deteriorates due to significant measurement errors from environmental factors like temperature and humidity
Solution Approach 1:
The patent incorporates environmental parameters (temperature and humidity) as inputs to the BP neural network model. By changing the detection approach from simple color comparison to a model that accounts for environmental parameter variations, the system achieves higher reliability without significantly increasing device complexity, as the processing is done through software algorithms.
3Ease of operation
If simple color card comparison method is used, then ease of operation is maintained, but measurement precision deteriorates due to significant differences in color change range across regions
Solution Approach 1:
The patent transitions from one-dimensional color card comparison to two-dimensional image analysis, dividing the sweat print into multiple regions and analyzing color values across the entire image space. This dimensional change allows for more precise measurement by capturing regional variations, while the automated processing maintains operational simplicity.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enables accurate and rapid detection of sweat volume by accounting for environmental factors and regional variations, improving the reliability of sweat rate calculations and providing guidance for exercise and hydration.
Implementation Method 1
a test paper to obtain a to-be-tested sweat print image formed on the test paper
Implementation Method 2
constructing an error prediction model based on a Back-propagation (BP) neural network
Data Source
AI summary
The present disclosure provides a method for sweat volume detection based on sweat print imaging, comprising: obtaining a raw data set, the raw data set including at least one sweat print image formed by dropping different volumes of sweat on a test paper under different environmental parameters; obtaining a color value extreme of the sweat print image and dividing the sweat print image into at least one region; calculating a sweat error based on a total sweat collection volume and a real sweat volume; obtaining a trained error prediction model; obtaining a to-be-tested sweat print image and current environmental parameters; inputting the current environmental parameters and a count of regions of the to-be tested sweat print image into the trained error prediction model to determine a sweat error of the to-be-tested sweat print image; calculating a sweat volume and a sweat rate based on the sweat error.