Unlock instant, AI-driven research and patent intelligence for your innovation.

Passive target classification method based on channel state information

A technology of channel state information and target classification, which is applied in the field of passive perception, can solve problems such as insufficient classification accuracy and insignificant changes in the signal form at the receiving end, and achieve the effects of improving classification accuracy, improving usability, and high classification accuracy

Active Publication Date: 2020-05-01
ANHUI UNIVERSITY
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

First of all, for human bodies with similar height and body shape, the signal form of the receiving end does not change significantly. If the traditional received signal strength indicator measurement value is still used as the base signal at this time, it will inevitably bring about the problem of insufficient classification accuracy.
In addition, finding easily distinguishable targets based on a signal that does not vary significantly at the receiver will be more difficult

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 target classification method based on channel state information
  • Passive target classification method based on channel state information
  • Passive target classification method based on channel state information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0083] The first is data collection, using figure 2 Experimenters with different heights and weights shown in image 3 In the experimental scene shown, the four positions of the hexagonal mark collect data. The experimental platform uses a router as the transmitter, 80cm away from the ground; 50cm. Use no encryption to connect to the specified router, and use the ping-i 0.01 command to generate about 100 data packets per second. Each experimenter fixes at each position for 1 minute, and can collect about 6,000 data packets. Take 4,000 data packets in the middle steady state. The channel state information includes two kinds of information, amplitude and phase. The original phase information is chaotic and irregular. So only extract the magnitude from 4000 packets. This experiment is divided into 4 height segments, namely 150-159cm, 160-169cm, 170-179cm, 180-189cm.

[0084] Secondly, the data of different experimenters at different locations are preprocessed, that is, the w...

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 relates to a passive target classification method based on channel state information. The method comprises the following steps in sequence: collecting data, preprocessing the data, training a neural network, and classifying results. The method has the advantages that the deployment cost is low, the classification accuracy is high, manual feature extraction is not needed, and privacyis protected; and the stable channel state information is used for replacing the received signal strength which fluctuates greatly along with time change to serve as a base signal, and for fine-grained height classification, the channel state information can well reflect the difference of the target height compared with a received signal strength indication value.

Description

technical field [0001] The invention relates to the technical field of passive perception in wireless networks, in particular to a passive target classification method based on channel state information. Background technique [0002] Target classification has very important application value in security monitoring, emergency rescue, border patrol, intelligent interaction and other fields. There are three methods widely used in the field of target classification, which are methods based on video images, methods based on synthetic aperture radar (SAR) and methods based on sensors. The best known methods are those based on video images and synthetic aperture radar (SAR). However, the relatively high cost of using either method hinders the possibility of deploying them for low-cost sensing, and the use of video image-based methods poses a potential risk of privacy breaches; sensor-based methods are Mixed use of multiple sensors, such as acoustic, passive infrared, magnetic fie...

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): H04W4/30H04B17/309G06K9/62G06N3/04G06N3/08
CPCH04W4/30H04B17/309G06N3/084G06N3/045G06F18/241
Inventor 张南飞蒋芳胡艳军王翊许耀华
Owner ANHUI UNIVERSITY