On-line anomaly detection method for large-scale high-dimensional sensor data

An anomaly detection and sensor technology, applied in neural learning methods, instruments, biological neural network models, etc., can solve problems such as inability to detect high-dimensional sensor data in real time

Active Publication Date: 2019-04-12
ANHUI AGRICULTURAL UNIVERSITY
View PDF10 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0014] The purpose of the present invention is to provide an online anomaly detection method for large-scale high-dimensional sensor data to solve the problem that the existing technology cannot detect high-dimensional sensor data in real 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
  • On-line anomaly detection method for large-scale high-dimensional sensor data
  • On-line anomaly detection method for large-scale high-dimensional sensor data
  • On-line anomaly detection method for large-scale high-dimensional sensor data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0074] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0075] Such as figure 1 As shown, the present invention provides an online anomaly detection method for large-scale high-dimensional sensor data, comprising the following steps:

[0076] (101). Acquiring historical data: Extracting several continuous data samples within a certain period of time from the management and monitoring system in the background of the sensor network as historical data X for model training.

[0077] (102), establish deep belief network-1 / 4 spherical support vector machine hybrid model, such as figure 2 Shown; Among them, the Restricted Boltzmann Machine (RBM) is a kind of probabilistic neural network, which is mainly composed of two layers of neurons, called the hidden layer and the visible layer respectively. Such as image 3 As shown, h is the state vector of neurons in the hidden layer, v is the state vector of neurons in...

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 an on-line anomaly detection method for large-scale high-dimensional sensor data. The on-line anomaly detection method comprises the following steps that (101), historical datais obtained; (102), a deep belief network-1 / 4 spherical support vector machine hybrid model is established to downgrade and test the data; (103), the historical data is adopted to train the hybrid model; (104), sensor data is collected; (105), a sliding window is created to achieve an on-line detection technology; (106), the well trained hybrid model is adopted to detect the data collected by thesensor; and (107), all abnormal data after detection is output. Algorithms and processes related to the prior art are improved, a the method achieving the on-line detection technology in high-dimensional data processing is provided, accuracy of abnormal data detection is greatly improved, and the detection time is greatly lowered.

Description

technical field [0001] The invention relates to the field of sensor network abnormal data processing methods, in particular to an online abnormal detection method for large-scale high-dimensional sensor data. Background technique [0002] With the popularity of the Internet of Things, wireless sensor networks have been widely used in various fields. By analyzing and mining the data collected and reported by sensors, it can provide valuable and effective information for various industries. However, the complex deployment environment and the sensor's own memory, CPU, and energy conditions are very easy to cause software and hardware failures in the sensor, resulting in abnormal data, and the analysis of mixed abnormal data sets will seriously affect the mining of effective information and key decision-making. formulate. Therefore, it becomes more and more important to detect abnormal data collected by wireless sensor network accurately in real time. On the one hand, timely d...

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): G01D18/00G06N3/04G06N3/08
CPCG06N3/084G01D18/00G06N3/044
Inventor乔焰金鹏焦俊马慧敏王婧崔信红沈春山
OwnerANHUI AGRICULTURAL UNIVERSITY