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

Clustering algorithm and echo state network-based abnormal consumption behavior detection method

An echo state network and detection method technology, which is applied in the information field to achieve the effect of overcoming the problem of overfitting, improving the accuracy and improving the prediction accuracy.

Inactive Publication Date: 2017-10-27
HENAN UNIV OF SCI & TECH
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] Aiming at the above-mentioned problems such as overfitting existing in the existing forecast-based anomaly detection, the present invention provides a method for detecting abnormal consumption behavior based on clustering algorithm and echo state network prediction

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
  • Clustering algorithm and echo state network-based abnormal consumption behavior detection method
  • Clustering algorithm and echo state network-based abnormal consumption behavior detection method
  • Clustering algorithm and echo state network-based abnormal consumption behavior detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The present invention will be further elaborated below in combination with specific embodiments.

[0039] The overall implementation process of the technology of the present invention is as attached figure 1 As shown, the specific steps are as follows:

[0040] 1) Determine the relevant time series collection scope: the collection scope includes the card consumption Log data of the entire class of students to be predicted;

[0041] 2) Data preprocessing: collect data from the one-card database, convert the collected consumption Log data into a time series form; sum the consumption data of three meals a day to obtain time series data with a day as the time step. After obtaining the time series data, stabilize the non-stationary data and remove the trend and periodicity of the data;

[0042] 3) Preliminary anomaly detection: For the data that requires anomaly detection, the conventional all-in-one card anomaly detection method is initially used to determine whether the...

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 dynamic time warping and echo state network time sequence prediction-based one-card data abnormal detection method. By adding dynamic time warping-based related sequences as input sequences of echo states, random noises of one-card data are eliminated, the accuracy of echo state network prediction is improved, and the abnormal detection accuracy is finally improved.

Description

technical field [0001] The invention relates to the field of information technology, in particular to a method for detecting abnormal consumption behavior based on a clustering algorithm and an echo state network. Background technique [0002] With the in-depth development of digitalization and informatization in colleges and universities, the campus card has been widely used. A large number of student consumption records are stored in the card, and valuable information is mined to analyze student behavior, which greatly promotes the efficient operation of student management. [0003] At present, the analysis based on the one-card data is very extensive, such as studying the characteristics of students' learning, consumption, and work and rest behaviors in the school through the campus one-card data; through the clustering algorithm on the one-card consumption data, analyzing the relationship between the one-card consumption and academic performance; and based on Anomaly de...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q30/02G06Q30/00G06Q40/02G06N3/04G06N3/08G06K9/62
CPCG06N3/08G06Q30/0185G06Q30/0201G06N3/045G06Q40/03G06F18/23
Inventor 张各各王辉任宁宁陈祥涛周毅
Owner HENAN UNIV OF SCI & TECH
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