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

Traffic sequence data anomaly detection method and system based on non-parametric modeling

A sequence data and anomaly detection technology, which is applied in the traffic control system of road vehicles, traffic flow detection, traffic control system, etc., can solve the problems of slow processing speed and inability to score abnormal scores of a large amount of traffic data

Active Publication Date: 2021-09-07
UNIV OF JINAN
View PDF13 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

On the one hand, most traditional algorithms often have a certain degree of residual error and heteroscedasticity in the fitting of traffic data, which cannot be effectively matched with anomaly detectors; abnormal score

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
  • Traffic sequence data anomaly detection method and system based on non-parametric modeling
  • Traffic sequence data anomaly detection method and system based on non-parametric modeling

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] The core of traffic sequence data anomaly detection is to use the past data set to accurately predict the future observation data, and then evaluate the anomaly degree of the data by comparing the error between the observed value and the actual value, and finally give its anomaly score. Therefore, reasonable prediction of future observations and appropriate anomaly scores are the keys to the effectiveness of anomaly detection by modeling fit data.

[0044] Based on this, according to an embodiment of the present invention, a method for detecting anomalies in traffic sequence data based on non-parametric modeling is disclosed, including the following steps:

[0045] (1) Obtain the traffic flow data and working day schedule data of the set road section;

[0046] Specifically, the traffic flow data includes: the traffic flow of a certain road at a fixed time interval. For example: 16:00~16:05 a ditch road;

[0047] The weekday schedule data includes: traffic flow data fo...

Embodiment 2

[0071] According to an embodiment of the present invention, a traffic sequence data anomaly detection system based on non-parametric modeling is disclosed, including:

[0072] The data acquisition module is used to acquire the traffic flow data and the working day schedule data of the set road section;

[0073] The data classification module is used to put the traffic flow data of the same working day together to form multiple subsequence data classified by different working days;

[0074] The standardized residual module is used to model each subsequence data, and each subsequence model is fitted to the traffic flow data of each day by a linear fitting method; at the same time, the difference between the subsequence model and the real data is eliminated Variance; get the standardized residual curve;

[0075] The data anomaly judging module is used to obtain the abnormal score of the traffic sequence data at each moment by using the EXPOSE anomaly detection method based on th...

Embodiment 3

[0078] According to an embodiment of the present invention, a terminal device is disclosed, including a server, the server includes a memory, a processor, and a computer program stored on the memory and operable on the processor, when the processor executes the program The non-parametric modeling-based anomaly detection method for traffic sequence data in Embodiment 1 is realized. For the sake of brevity, details are not repeated here.

[0079] It should be understood that in this embodiment, the processor can be a central processing unit CPU, and the processor can also be other general-purpose processors, digital signal processors DSP, application specific integrated circuits ASIC, off-the-shelf programmable gate array FPGA or other programmable logic devices , discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor, or the processor may be any conventional processor, or the like.

[0080] The memory ...

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 traffic sequence data anomaly detection method and system based on non-parametric modeling. The method comprises the following steps: acquiring traffic flow data and workday schedule data of a set road section; putting the traffic flow data of the same workday together to form a plurality of sub-sequence data classified according to different workdays; carrying out modeling on each piece of sub-sequence data, and carrying out fitting on each sub-sequence model and traffic flow data of each day through a linear fitting method; meanwhile, eliminating the heterovariance between the sub-sequence model and real data; obtaining a standardized residual error curve; and on the basis of the standardized residual curve, obtaining a traffic sequence data anomaly score at each moment by using an EXPOSE anomaly detection method, and then judging traffic sequence anomaly data. According to the method, a large amount of sequence data can be rapidly processed, and the accuracy of traffic data anomaly detection is high.

Description

technical field [0001] The invention relates to the technical field of traffic data anomaly detection, in particular to a non-parametric modeling-based traffic sequence data anomaly detection method and system. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] In the past few decades, with the rapid development of science and technology, people's travel needs have increased. Among them, automobiles, as the most common and convenient means of transportation, have experienced explosive growth in both quantity and quality. With the substantial growth of traffic flow, it has brought huge challenges to urban road traffic, resulting in traffic congestion, accidents and other abnormal situations, which have brought great inconvenience and risks to people's lives. Therefore, using efficient anomaly detection to manage traffic congestion has become...

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): G08G1/01
CPCG08G1/0104G08G1/0125
Inventor 林宏坤耿仁康魏婷孙斌宋若琳季圣震张宸恺徐海宸王中源隋江浩瓮卓文
Owner UNIV OF JINAN
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