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

Sensor network data anomaly judgment method based on graph neural network

A sensor network and neural network technology, applied in the field of abnormal judgment of sensor network data

Active Publication Date: 2021-06-15
GUILIN UNIV OF ELECTRONIC TECH
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The processing of graph signals by early neural networks was compromised by using convolutional neural networks. Since convolutional neural networks are used to process data with a Euclidean structure, this method has many defects.

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
  • Sensor network data anomaly judgment method based on graph neural network
  • Sensor network data anomaly judgment method based on graph neural network
  • Sensor network data anomaly judgment method based on graph neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0034] A sensor network data abnormal judgment method based on a graph neural network, comprising the following steps:

[0035] 1) Carry out graph modeling on the sensor network data: assume that the sensor network data is X=[x 1 ,x 2 ,...,x m ]∈R n ×m , where x i ∈ R n , i=1,2,...,m is the data acquired by n sensors in the current sensor network at time i, C={(a 1 ,b 1 ),(a 2 ,b 2),…,(a n ,b n )} is a set of coordinates of n sensors in the sensor network, where a i is the latitude, b i is the longitude, i=1,2,...,n, and accordingly, a graph G={V,E,W} can be constructed, where V is a collection of nodes in the graph, corresponding to each sensor in the sensor network, E is a set of edges, which are used to describe the similarity and adjacency relationship between nodes, W is a weight matrix, and the internal elements of the weight matrix indicate whether there is a spatial connection between the corresponding two nodes. The definition is shown in formula (1):

...

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 discloses a sensor network data anomaly judgment method based on a graph neural network, and the method is characterized in that the method comprises the following steps: 1) carrying out graph modeling on sensor network data; (2) extracting spatial features in a graph model by using a graph convolutional network; (3) extracting time features in the graph model by using a gating loop unit; (4) performing anomaly judgment on the extracted spatial and temporal features by using a full-connection layer. The method can perform anomaly judgment by analyzing the historical data of the sensor network.

Description

technical field [0001] The invention relates to the technical field of neural network, graph model and graph signal processing, in particular to a sensor network data abnormality judgment method based on graph neural network. Background technique [0002] Sensors have been widely used to monitor physical or environmental conditions in different locations, such as temperature, humidity, air pressure, and wind speed. Multiple sensors distributed in different locations form a sensor network, and sensor networks are widely used in both civilian and military fields. Therefore, it is particularly important to judge the abnormality of each sensor in the sensor network. The abnormal judgment can understand the operating status of the sensor or the abnormal changes in the surrounding environment of the sensor. important role. [0003] The graph is a typical non-Euclidean structure (Non-Euclidean Structure). This type of data is highly random and has an irregular structure. It is sp...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F2218/08G06F2218/12G06F18/2433
Inventor 蒋俊正陈俊杰
Owner GUILIN UNIV OF ELECTRONIC TECH