scholarly journals Expressway Traffic Flow Missing Data Repair Method Based on Coupled Matrix-Tensor Factorizations

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Hui Jiang ◽  
Hongxing Deng
Keyword(s):  
Missing Data ◽  
Traffic Flow ◽  
Traffic Management ◽  
Flow Data ◽  
Data Types ◽  
Management Planning ◽  
Repair Method ◽  
Alternating Direction ◽  
Data Rates ◽  
Tensor Factorizations

Traffic flow data is the basis of traffic management, planning, control, and other forms of implementation. Once missing, it will directly affect the monitoring and prediction of expressway traffic status. Regarding this, this paper proposes a repair method for the traffic flow missing data of expressway, combined with the idea of coupled matrix-tensor factorizations (CMTF), to couple the auxiliary traffic flow data into the main traffic flow data and to construct the coupling matrix-tensor expression of traffic flow data, and the alternating direction multiplier algorithm is used to realize the repair of missing traffic flow data. Combined with the measured data of expressway traffic flow, the experimental results show that, under different missing data types and missing rates, the proposed method outperforms the methods lacking auxiliary traffic flow data and achieves a good repair effect, especially for high miss data rates.

scholarly journals An adaptive k nearest neighbour method for imputation of missing traffic data based on two similarity

2020 ◽  
Vol 54 (2) ◽  
pp. 59-73
Author(s):  
Yang Wang ◽  
Yu Xiao ◽  
Jianhui Lai ◽  
Yanyan Chen
Keyword(s):  
Missing Data ◽  
Traffic Flow ◽  
Intelligent Transportation Systems ◽  
Domain Knowledge ◽  
Rapid Development ◽  
Transportation Systems ◽  
Nearest Neighbour ◽  
Flow Data ◽  
Fundamental Parameters ◽  
Determination Of Parameters

Traffic flow is one of the fundamental parameters for traffic analysis and planning. With the rapid development of intelligent transportation systems, a large number of various detectors have been deployed in urban roads and, consequently, huge amount of data relating to the traffic flow are accumulatively available now. However, the traffic flow data detected through various detectors are often degraded due to the presence of a number of missing data, which can even lead to erroneous analysis and decision if no appropriate process is carried out. To remedy this issue, great research efforts have been made and subsequently various imputation techniques have been successively proposed in recent years, among which the k nearest neighbour algorithm (kNN) has received a great popularity as it is easy to implement and impute the missing data effectively. In the work presented in this paper, we firstly analyse the stochastic effect of traffic flow, to which the suffering of the kNN algorithm can be attributed. This motivates us to make an improvement, while eliminating the requirement to predefine parameters. Such a parameter-free algorithm has been realized by introducing a new similarity metric which is combined with the conventional metric so as to avoid the parameter setting, which is often determined with the requirement of adequate domain knowledge. Unlike the conventional version of the kNN algorithm, the proposed algorithm employs the multivariate linear regression model to estimate the weights for the final output, based on a set of data, which is smoothed by a Wavelet technique. A series of experiments have been performed, based on a set of traffic flow data reported from serval different countries, to examine the adaptive determination of parameters and the smoothing effect. Additional experiments have been conducted to evaluate the competent performance for the proposed algorithm by comparing to a number of widely-used imputing algorithms.

scholarly journals Spatial—Temporal Traffic Flow Data Restoration and Prediction Method Based on the Tensor Decomposition

2021 ◽  
Vol 11 (19) ◽  
pp. 9220
Author(s):  
Jiahe Yan ◽  
Honghui Li ◽  
Yanhui Bai ◽  
Yingli Lin
Keyword(s):  
Missing Data ◽  
Traffic Flow ◽  
Prediction Accuracy ◽  
Tensor Decomposition ◽  
Prediction Algorithm ◽  
Flow Data ◽  
Cp Decomposition ◽  
Data Completion ◽  
Mode Characteristics ◽  
Multi Mode

As an important part of urban big data, traffic flow data play a critical role in traffic management and emergency response. Traffic flow data contain multi-mode characteristics, which need to be deeply mined. To make full use of multi-mode characteristics, we use a 3-order tensor to represent the traffic flow data, considering “temporal-spatial-periodic” characteristics. To recover the missing data of traffic flow, we propose the Missing Data Completion Algorithm Based on Residual Value Tensor Decomposition (MDCA-RVTD), which combines linear regression, univariate spline, and CP decomposition. Then, we predict the future traffic flow data by using the proposed Traffic Flow Prediction Algorithm Based on Data Completion Strategy (TFPA-DCS). The experimental results show that recovering the missing data is helpful in improving the prediction accuracy. Additionally, the prediction accuracy of the proposed Algorithm is better than gray model and traditional tensor CP decomposition method.

The Quality Control and Evaluation of Road Traffic Flow Data

2013 ◽  
Vol 838-841 ◽  
pp. 2092-2097 ◽  
Author(s):  
Yuan Li Gu ◽  
Yun Nan Ma ◽  
Ju Wei Li
Keyword(s):  
Quality Control ◽  
Data Quality ◽  
Traffic Flow ◽  
Traffic Management ◽  
Road Traffic ◽  
Flow Data ◽  
Data Quality Control ◽  
Failure Data ◽  
Traffic Management System ◽  
First Time

Dynamic traffic data quality evaluation can provide reliable data support for the traffic management system. This paper aim at three kinds of common failure data, put forward the traffic flow data quality control methods and process. First time evaluate the data quality in three stages, and each stage respectively for all kinds of ITS detector, and builds the six index system. Finally take Beijing as an example to analyze and verify the method of this paper.

scholarly journals Formation of the Traffic Flow Rate under the Influence of Traffic Flow Concentration in Time at Controlled Intersections in Tyumen, Russian Federation

2021 ◽  
Vol 13 (15) ◽  
pp. 8324
Author(s):  
Viacheslav Morozov ◽  
Sergei Iarkov
Keyword(s):  
Traffic Flow ◽  
Flow Rate ◽  
Traffic Congestion ◽  
Traffic Management ◽  
System Analysis ◽  
Motor Vehicle ◽  
Experimental Studies ◽  
Transport Systems ◽  
Experiment Planning ◽  
Traffic Light

Present experience shows that it is impossible to solve the problem of traffic congestion without intelligent transport systems. Traffic management in many cities uses the data of detectors installed at controlled intersections. Further, to assess the traffic situation, the data on the traffic flow rate and its concentration are compared. Latest scientific studies propose a transition from spatial to temporal concentration. Therefore, the purpose of this work is to establish the regularities of the influence of traffic flow concentration in time on traffic flow rate at controlled city intersections. The methodological basis of this study was a systemic approach. Theoretical and experimental studies were based on the existing provisions of system analysis, traffic flow theory, experiment planning, impulses, probabilities, and mathematical statistics. Experimental data were obtained and processed using modern equipment and software: Traficam video detectors, SPECTR traffic light controller, Traficam Data Tool, SPECTR 2.0, AutoCad 2017, and STATISTICA 10. In the course of this study, the authors analyzed the dynamics of changes in the level of motorization, the structure of the motor vehicle fleet, and the dynamics of changes in the number of controlled intersections. As a result of theoretical studies, a hypothesis was put forward that the investigated process is described by a two-factor quadratic multiplicative model. Experimental studies determined the parameters of the developed model depending on the directions of traffic flow, and confirmed its adequacy according to Fisher’s criterion with a probability of at least 0.9. The results obtained can be used to control traffic flows at controlled city intersections.

Traffic Flow Data Collection and Signal Control System Based on Internet of Things and Cloud Computing

2013 ◽  
Vol 846-847 ◽  
pp. 1608-1611 ◽  
Author(s):  
Hui Jie Ding
Keyword(s):  
Cloud Computing ◽  
Control System ◽  
Data Collection ◽  
Internet Of Things ◽  
Traffic Flow ◽  
Signal Control ◽  
Traffic Signal Control ◽  
Flow Data ◽  
Traffic Jam ◽  
Sensing Data

As more and more cars are in service, the traffic jam becomes a serious problem in our society. At the same time, more and more sensors make the cars more and more intelligent, and this promotes the development of Internet of things. Real time monitoring the cars will produce massive sensing data, the Cloud computing gives us a good manner to solve this problem. In this paper, we propose a traffic flow data collection and traffic signal control system based on Internet of things and the Cloud computing. The proposed system contains two main parts, sensing data collection and traffic status control subsystem.

scholarly journals Road Traffic Analysis Using Computer Vision

2021 ◽  
Vol 9 (8) ◽  
pp. 2002-2006
Author(s):  
Needhi U. Gaonkar
Keyword(s):  
Computer Vision ◽  
Traffic Flow ◽  
Traffic Management ◽  
Road Traffic ◽  
Vehicle Detection ◽  
Traffic Analysis ◽  
Transportation Systems ◽  
Visual Object ◽  
Highway Traffic ◽  
Analysis System

Abstract: Traffic analysis plays an important role in a transportation system for traffic management. Traffic analysis system using computer vision project paper proposes the video based data for vehicle detection and counting systems based on the computer vision. In most Transportation Systems cameras are installed in fixed locations. Vehicle detection is the most important requirement in traffic analysis part. Vehicle detection, tracking, classification and counting is very useful for people and government for traffic flow, highway monitoring, traffic planning. Vehicle analysis will supply with information about traffic flow, traffic summit times on road. The motivation of visual object detection is to track the vehicle position and then tracking in successive frames is to detect and connect target vehicles for frames. Recognising vehicles in an ongoing video is useful for traffic analysis. Recognizing what kind of vehicle in an ongoing video is helpful for traffic analysing. this system can classify the vehicle into bicycle, bus, truck, car and motorcycle. In this system I have used a video-based vehicle counting method in a highway traffic video capture using cctv camera. Project presents the analysis of tracking-by-detection approach which includes detection by YOLO(You Only Look Once) and tracking by SORT(simple online and realtime tracking) algorithm. Keywords: Vehicle detection, Vehicle tracking, Vehicle counting, YOLO, SORT, Analysis, Kalman filter, Hungarian algorithm.

Sign in / Sign up

Export Citation Format

Share Document