A highly efficient framework for outlier detection in urban traffic flow
Abstract The outliers in traffic flow represent the anomalies or emergencies in the road. The detection and research of outliers will help to reveal the mechanism of such events. Aiming at the problem of outlier detection in urban traffic flow, this paper innovatively proposes a highly efficient tra...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-12-01
|
| Series: | IET Intelligent Transport Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/itr2.12109 |
| _version_ | 1828010600878309376 |
|---|---|
| author | Xing Wang Ruihao Zeng Fumin Zou Faliang Huang Biao Jin |
| author_facet | Xing Wang Ruihao Zeng Fumin Zou Faliang Huang Biao Jin |
| author_sort | Xing Wang |
| collection | DOAJ |
| description | Abstract The outliers in traffic flow represent the anomalies or emergencies in the road. The detection and research of outliers will help to reveal the mechanism of such events. Aiming at the problem of outlier detection in urban traffic flow, this paper innovatively proposes a highly efficient traffic outlier detection framework based on the study of road traffic flow patterns. The main research works are as follows: (1) data pre‐processing, the road traffic flow matrix of the roads is calculated based on the collected GPS data, the non‐negative matrix factorisation algorithm is chosen to reduce the dimension of the matrix. (2) Road traffic flow pattern extraction, the fuzzy C‐means clustering algorithm with the Optimal k‐cluster centre (K‐FCM) is adopted to cluster the roads with the same road traffic flow pattern. (3) Outlier detection model training and evaluation, kernel density estimation is introduced to fit the probability density of roads traffic flow matrices which are used to train the back propagation neural network based on particle swarm optimisation to obtain the outlier detection and evaluation model, and a threshold is introduced to optimise the precision and recall of the model. The experimental results show that: the average precision and recall of the proposed method in this paper are 95.38% and 96.23%, respectively, and the average detection time is 28.4 seconds. The method has high accuracy, high efficiency and good practical significance. |
| first_indexed | 2024-04-10T09:02:30Z |
| format | Article |
| id | doaj.art-abd991d7eded4fec8feffdd7a42a5e3a |
| institution | Directory Open Access Journal |
| issn | 1751-956X 1751-9578 |
| language | English |
| last_indexed | 2024-04-10T09:02:30Z |
| publishDate | 2021-12-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Intelligent Transport Systems |
| spelling | doaj.art-abd991d7eded4fec8feffdd7a42a5e3a2023-02-21T11:46:46ZengWileyIET Intelligent Transport Systems1751-956X1751-95782021-12-0115121494150710.1049/itr2.12109A highly efficient framework for outlier detection in urban traffic flowXing Wang0Ruihao Zeng1Fumin Zou2Faliang Huang3Biao Jin4College of Computer and Cyber Security Fujian Normal University Fuzhou ChinaInternational College of Chinese Studies Fujian Normal University Fuzhou ChinaFujian Key Laboratory of Automotive Electronic and Electrical Drive Technology Fujian University of Technology Fuzhou ChinaSchool of Computer and Information Engineering Nanning Normal University Nanning ChinaCollege of Computer and Cyber Security Fujian Normal University Fuzhou ChinaAbstract The outliers in traffic flow represent the anomalies or emergencies in the road. The detection and research of outliers will help to reveal the mechanism of such events. Aiming at the problem of outlier detection in urban traffic flow, this paper innovatively proposes a highly efficient traffic outlier detection framework based on the study of road traffic flow patterns. The main research works are as follows: (1) data pre‐processing, the road traffic flow matrix of the roads is calculated based on the collected GPS data, the non‐negative matrix factorisation algorithm is chosen to reduce the dimension of the matrix. (2) Road traffic flow pattern extraction, the fuzzy C‐means clustering algorithm with the Optimal k‐cluster centre (K‐FCM) is adopted to cluster the roads with the same road traffic flow pattern. (3) Outlier detection model training and evaluation, kernel density estimation is introduced to fit the probability density of roads traffic flow matrices which are used to train the back propagation neural network based on particle swarm optimisation to obtain the outlier detection and evaluation model, and a threshold is introduced to optimise the precision and recall of the model. The experimental results show that: the average precision and recall of the proposed method in this paper are 95.38% and 96.23%, respectively, and the average detection time is 28.4 seconds. The method has high accuracy, high efficiency and good practical significance.https://doi.org/10.1049/itr2.12109Outlier detectionRoad traffic flow patternNonnegative matrix factorization (NMF)K‐FCM clustering algorithmPSO‐BP neural networkAlgebra |
| spellingShingle | Xing Wang Ruihao Zeng Fumin Zou Faliang Huang Biao Jin A highly efficient framework for outlier detection in urban traffic flow IET Intelligent Transport Systems Outlier detection Road traffic flow pattern Nonnegative matrix factorization (NMF) K‐FCM clustering algorithm PSO‐BP neural network Algebra |
| title | A highly efficient framework for outlier detection in urban traffic flow |
| title_full | A highly efficient framework for outlier detection in urban traffic flow |
| title_fullStr | A highly efficient framework for outlier detection in urban traffic flow |
| title_full_unstemmed | A highly efficient framework for outlier detection in urban traffic flow |
| title_short | A highly efficient framework for outlier detection in urban traffic flow |
| title_sort | highly efficient framework for outlier detection in urban traffic flow |
| topic | Outlier detection Road traffic flow pattern Nonnegative matrix factorization (NMF) K‐FCM clustering algorithm PSO‐BP neural network Algebra |
| url | https://doi.org/10.1049/itr2.12109 |
| work_keys_str_mv | AT xingwang ahighlyefficientframeworkforoutlierdetectioninurbantrafficflow AT ruihaozeng ahighlyefficientframeworkforoutlierdetectioninurbantrafficflow AT fuminzou ahighlyefficientframeworkforoutlierdetectioninurbantrafficflow AT falianghuang ahighlyefficientframeworkforoutlierdetectioninurbantrafficflow AT biaojin ahighlyefficientframeworkforoutlierdetectioninurbantrafficflow AT xingwang highlyefficientframeworkforoutlierdetectioninurbantrafficflow AT ruihaozeng highlyefficientframeworkforoutlierdetectioninurbantrafficflow AT fuminzou highlyefficientframeworkforoutlierdetectioninurbantrafficflow AT falianghuang highlyefficientframeworkforoutlierdetectioninurbantrafficflow AT biaojin highlyefficientframeworkforoutlierdetectioninurbantrafficflow |