Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Method for recognizing outlier traffic data

A traffic data and outlier data technology, applied in the field of identifying outlier traffic data, can solve the problems of vague model points and inability to reflect the essence of the real system.

Inactive Publication Date: 2009-09-02
SOUTHEAST UNIV
View PDF3 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Technical problem: Abnormal traffic data can make the main points of the built model blurred, and cannot reflect the essence of the real system. The present invention provides a method for identifying abnormal traffic data based on density, which can effectively detect boundary and internal distances. group data, which outperforms statistically based outlier detection methods

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
  • Method for recognizing outlier traffic data
  • Method for recognizing outlier traffic data
  • Method for recognizing outlier traffic data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] Example 1: Traffic Flow Modeling

[0039] Expressway traffic flow is usually described by average vehicle speed, arrival rate, and density. The relationship between arrival rate and density can be described by a graph, which is called the basic graph of traffic flow. Errors in detection equipment or transmission equipment, and unexpected traffic events may cause abnormal changes in traffic flow data. Whether it is sampling errors or outlier data generated by abnormal traffic events, the characteristics of the model will become blurred and cannot truly reflect the system. inner law. Therefore, it is necessary to find out and remove outlier data before building a model to reduce the influence of outlier data and improve the accuracy and reliability of the built model.

[0040] At present, 709 pieces of traffic flow data of Nanjing Lukou Airport Expressway have been collected, and the sampling period is 1 minute. A model between arrival rate and density is proposed to be ...

Embodiment 2

[0042] Embodiment 2: Application of road surface roughness test

[0043] Pavement roughness is an important index of pavement surface function, which not only reflects the driving comfort of the pavement, but also reflects the health of the pavement from the side. The international roughness index IRI (International Roughness Index) has been widely adopted by countries all over the world. It is defined as the ratio of the total displacement (unit m) of the standard body suspension to the driving distance (unit km), and the unit is m / km. There are currently 8,000 IRI samples, and the data is collected every one meter. It is tested with a road surface roughness test vehicle imported from Australia.

[0044] Use the density-based detection method LOF to find specific samples, let k start from 50 as the initial value, increase with a step size of 10, and calculate the local abnormal factors of all samples. Then the average local outlier factor of all samples is calculated. Here,...

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

A method for identifying outlier traffic data, characterized in that the method first collects traffic data, calculates the average local outlier factor of the data, and then uses one of the following two criteria to judge the outlier data: the highest average local outlier factor m data is outlier data, or the data whose average local outlier factor is greater than a given threshold is outlier data, and finally delete or correct the identified outlier data by filtering method, or analyze the hidden information contained in the outlier data . This method can effectively detect the outlier data in the boundary and inside, and its effect is better than the outlier detection method based on statistics.

Description

technical field [0001] The invention proposes a method for identifying outlier traffic data, relates to the quality control of traffic data collected by an intelligent traffic system, and belongs to the technical field of intelligent information processing in an intelligent traffic system. Background technique [0002] Traffic data plays an important role in the intelligent transportation system. One of the core technologies of the intelligent transportation system (ITS) is the real-time estimation and prediction technology of traffic parameters. Factors, there are usually samples of common behaviors that do not follow the data model in the collected traffic data set, and these abnormal points are outlier data. When the collected traffic data is used for modeling, these outliers are not representative and cannot effectively model and describe the system. In order to improve the accuracy and reliability of dynamic traffic information and ensure the effect of traffic models, ...

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 Patents(China)
IPC IPC(8): G08G1/01
Inventor 陈淑燕王炜瞿高峰
Owner SOUTHEAST UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
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