Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Passive indoor personnel state detection method based on PCA-Kalman

A state detection and personnel technology, applied in the field of wireless perception, can solve the problems of insufficient positioning accuracy, low RSSI stability, and time-dependent values, so as to improve the detection rate, reduce time complexity, and reduce errors.

Active Publication Date: 2018-11-30
NORTHWEST NORMAL UNIVERSITY
View PDF4 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, from the analysis of the experimental results of these technologies, it is found that the positioning accuracy is not high enough. The main reason is that the stability of RSSI is low and its value will be affected by time.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Passive indoor personnel state detection method based on PCA-Kalman
  • Passive indoor personnel state detection method based on PCA-Kalman
  • Passive indoor personnel state detection method based on PCA-Kalman

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0021] The present invention provides a kind of passive indoor personnel state detection method based on PCA-Kalman, its flow chart, as figure 1 As shown, the detection method is specifically carried out in the following steps:

[0022] 1) Collect the position coordinates of the test area, and process the received CSI raw data: that is, use the Kalman filter algorithm to denoise the raw data, and use the improved PCA algorithm to extract the most contributing features, which will be messy After the signal is eliminated, the relatively stable data signal is selected (during the experiment, there are many additional signal interference and multi-path interference indoors, such as electronic products, indoor furniture, etc. Therefore, part of the collected data signals will be very messy and unorganized. Meaningless, such signals are classified...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a passive indoor personnel state detection method based on PCA-Kalman. The method comprises the steps of collecting the position coordinate of a test area, denoising original data, extracting the most contributive feature by using an improved PCA algorithm, reducing the dimension of CSI data, extracting the non-linear feature of an original position fingerprint, storing a processed CSI signal into a fingerprint database, and updating the fingerprint database in real time according to environment change; classifying the data in a true environment by using an SVM algorithm, dividing the detection area into multiple reference points, numbering the reference points according to an ascending order, collecting behavior state of personnel in the detection area, and transmitting the acquired CSI data and amplitude and phase changes to a server; and matching a personnel state detection result with data in the fingerprint database, and thus achieving detection on differentstates of the personnel in the indoor environment according to a matching result. According to the method, the time complexity of the algorithm is reduced, the personnel state detection rate is improved, and the errors are reduced.

Description

technical field [0001] The invention belongs to the field of wireless perception technology, and relates to a method of extracting CSI signals using commercial Wi-Fi equipment, and using a large number of effective eigenvalues ​​in the CSI to obtain signal changes of indoor personnel status, mainly used to solve indoor personnel status detection and tracking. Especially for personnel status detection under indoor Wi-Fi. Background technique [0002] With the continuous progress and development of WSNs (Wireless Sensor Networks), people's research vision is not limited to traditional indoor positioning and location perception. Several fields are currently using radio for location awareness. For example, the typical radar system based on UWB (Ultra Wideband), and the relatively new indoor positioning technology based on commercial Wi-Fi equipment, have good development advantages in all aspects. Such as indoor intrusion detection, campus security, shopping mall personnel det...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): H04W4/02H04W64/00H04W4/33G06K9/62
CPCH04W4/02H04W4/33H04W64/00G06F18/2135G06F18/2411
Inventor 党小超黄亚宁郝占军司雄
Owner NORTHWEST NORMAL UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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