Motion behavior identification method based on LSTM model
A recognition method and motion technology, applied in the field of human motion recognition, to achieve the effect of overcoming manual feature extraction and good recognition accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0021] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be described in further detail below in conjunction with specific embodiments and with reference to the accompanying drawings.
[0022] Step S1 is specifically: using a sports bracelet to obtain time-series data of a person's exercise, specifically the heart rate collected by the heart rate monitor and the acceleration in the XYZ direction collected by the three-axis acceleration sensor.
[0023] Step S2 is specifically: labeling the collected data of different test subjects according to their current sports categories to form a complete data set with a dimension F that can be used for supervised learning.
[0024] Such as figure 1 As shown, the step S3 specifically includes: performing preprocessing on the collected data. Firstly, the data of the transition state and the motion state are removed, the missing values are filled, and the time stam...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com