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

WLAN indoor target invasion detection method based on multi-element signal features

A technology of signal characteristics and intrusion detection, which is applied to services based on specific environments, electrical components, wireless communications, etc., and can solve problems such as a large amount of manpower and time overhead

Active Publication Date: 2018-08-17
CHONGQING UNIV OF POSTS & TELECOMM
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to solve the problem of using the existing WLAN infrastructure to realize the indoor intrusion detection method for unknown targets, a large amount of manpower and time are required to construct the RSS feature database and the problem of low intrusion detection robustness in the offline stage, and provides a multi-signal-based Feature based WLAN indoor target intrusion detection method

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
  • WLAN indoor target invasion detection method based on multi-element signal features
  • WLAN indoor target invasion detection method based on multi-element signal features
  • WLAN indoor target invasion detection method based on multi-element signal features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] specific implementation plan

[0037] to combine figure 1 Describe the embodiment of the present invention, the steps of this embodiment are as follows:

[0038] Offline phase:

[0039] Step 1: Arrange several WLAN access points AP and monitoring points MP in the target area.

[0040] to combine figure 2 The specific steps of constructing RSS feature data in silent and intrusive states using the ray tracing model of adaptive depth ray tree are as follows:

[0041] Step 2: Import and realize the environment information, combine image 3 Perform two-dimensional projection after three-dimensional modeling of the environment, and record relevant information in the environment including N (the number of active parts of the plumb plane or plumb line); D k (k=1,...,N) (numbering of the kth action part); P k and H k (k=1,..., N 1 )(vertex coordinates and height of the kth plumb line); N 1 (number of vertical lines); c k , ε k and μ k (k=1,..., N 2 )(relative permi...

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 proposes a WLAN (Wireless Local Area Network) indoor target invasion detection method based on multi-element signal features, and solves a problem that the offline stage of an indoor invasion detection method for an unknown object through the conventional WLAN infrastructure needs a large amount of manpower and time for the RSS feature database building and the invasion detection robustness is low. The method comprises the steps: firstly building a quasi-three-dimensional ray tracking model based on an adaptive depth ray tree, and carrying out the building of the RSS (Received Signal Strength) propagation characteristics in indoor silent and invasion states; secondly combining the RSS mean value, variance, maximum value, minimum value, range value and median features for building a PNN (Probabilistic Neural Network) training database; finally carrying out the multi-class discrimination of the newly collected RSS data through the trained PNN, and achieving the detection ofan invading target and the region locating. The method can be used in a radio communication network environment.

Description

[0001] technology neighborhood [0002] The invention belongs to indoor intrusion detection technology, and in particular relates to a WLAN indoor target intrusion detection method based on multiple signal features. Background technique [0003] Existing indoor target intrusion detection systems mainly use video images, Global Positioning System (Global Positioning System, GPS), infrared, ultrasonic, pressure sensors and wireless sensor networks. Among them, the video image has the problem of user privacy leakage, and it cannot be used at night or under harsh lighting conditions such as smog; GPS, infrared, ultrasonic and pressure sensors usually need to detect targets carrying special hardware devices; wireless sensor networks often require system A large number of sensor nodes are deployed in the detection area, resulting in high system deployment costs. [0004] The WLAN indoor target intrusion detection system proposed by the University of Maryland can effectively protect...

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): G06N3/00G06N3/04H04W4/33H04W24/06
CPCH04W4/33H04W24/06G06N3/006G06N3/045
Inventor 周牧林艺馨谢良波杨小龙何维
Owner CHONGQING UNIV OF POSTS & TELECOMM