Dual-network architecture indoor positioning method based on parameter constraint
A parameter-constrained, indoor positioning technology, applied in the field of indoor positioning, can solve the problems of difficult positioning, limited data feature extraction ability, insufficient field differences, etc., to achieve the effect of reducing feature differences
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0086] Example
[0087] With this model, the RSS public data set collected at the University University of Spain is experimentally, and the area of the data acquisition area is about 308.4 square meters, and a total of 48 grids are divided into 620 access points. With the first month of sample and label as source domain data, a total of 8,640 samples; samples using the Nth month (n ≥ 2) are used as the label target domain data, the number of samples is 3120, using the item (N +) 1) Each RSS data received in real time as a month is the test data, verify the model effect.
[0088] The neural network comprises 5 full-connection layers, and the number of neurons of each layer is 256, 128, 128, 128, 128, 128, 128, 128, and the initialization parameter is set to random initialization.
[0089] The present invention designs two sets of experiments to verify the superiority of the proposed algorithm. The first group of experiments is a comparison of the method of the background technica...
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.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap