Application of Intelligent Data Mining Method for Traffic Forecasting

2011 ◽  
Vol 84-85 ◽  
pp. 405-409
Author(s):  
Wei He ◽  
Jie Xiong
Keyword(s):  
Data Mining ◽  
Intelligent Transportation Systems ◽  
Traffic Management ◽  
Pso Algorithm ◽  
Transportation Systems ◽  
Support Vector ◽  
Self Organizing Map ◽  
Traffic Forecasting ◽  
Mining Model ◽  
The Impact

Potential knowledge useful for traffic management optimization is hidden in a huge amount of data. Previous works use the prior data pattern labels to train the artificial neural network to attain the intelligent data mining models. The performance of the models suffers from the experts’ experience. To relieve the impact of the human factor, a new hybrid intelligent data mining model is proposed in this work based on self-organizing map (SOM) and support vector machine (SVM). The SOM was firstly used to capture the clustering information of the database through an unsupervised manner. Then the identified samples were treated as input to train the SVM. To optimize the SVM model, the particle swarm optimization (PSO) algorithm was employed to tune the SVM parameters and hence the satisfactory SVM data mining model was obtained. 2000 practical data sets from the Intelligent Transportation Systems (ITS) were applied to the validation of the proposed mining model. The analysis results show that the proposed method can extract the underlying rules of the testing data and can predict the future traffic state with the accuracy beyond 97%. Hence, the new SOM-PSO-SVM data mining model can provide practical application for the ITS.

scholarly journals A Temporal Directed Graph Convolution Network for Traffic Forecasting Using Taxi Trajectory Data

2021 ◽  
Vol 10 (9) ◽  
pp. 624
Author(s):  
Kaiqi Chen ◽  
Min Deng ◽  
Yan Shi
Keyword(s):  
Traffic Flow ◽  
Directed Graph ◽  
Intelligent Transportation Systems ◽  
Traffic Management ◽  
A Priori ◽  
Transportation Systems ◽  
Superior Performance ◽  
Trajectory Data ◽  
Temporal Dependence ◽  
Traffic Forecasting

Traffic forecasting plays a vital role in intelligent transportation systems and is of great significance for traffic management. The main issue of traffic forecasting is how to model spatial and temporal dependence. Current state-of-the-art methods tend to apply deep learning models; these methods are unexplainable and ignore the a priori characteristics of traffic flow. To address these issues, a temporal directed graph convolution network (T-DGCN) is proposed. A directed graph is first constructed to model the movement characteristics of vehicles, and based on this, a directed graph convolution operator is used to capture spatial dependence. For temporal dependence, we couple a keyframe sequence and transformer to learn the tendencies and periodicities of traffic flow. Using a real-world dataset, we confirm the superior performance of the T-DGCN through comparative experiments. Moreover, a detailed discussion is presented to provide the path of reasoning from the data to the model design to the conclusions.

Multiple-Interval Freeway Traffic Flow Forecasting

1996 ◽  
Vol 1554 (1) ◽  
pp. 136-141 ◽  
Author(s):  
Brian L. Smith ◽  
Michael J. Demetsky
Keyword(s):  
Traffic Flow ◽  
Nonparametric Regression ◽  
Intelligent Transportation Systems ◽  
Traffic Management ◽  
Past Research ◽  
Transportation Systems ◽  
Forecasting Model ◽  
Freeway Traffic ◽  
Traffic Forecasting ◽  
Traffic Flow Forecasting

Freeway traffic flow forecasting will play an important role in intelligent transportation systems. The TRB Committee on Freeway Operations has included freeway flow forecasting in its 1995 research program. Much of the past research in traffic flow forecasting has addressed short-term, single-interval predictions. Such limited forecasting models will not support the development of the longer-term operational strategies needed for such events as hazardous material incidents. A multiple-interval freeway traffic flow forecasting model has been developed that predicts traffic volumes in 15-min intervals for several hours into the future. The nonparametric regression modeling technique was chosen for the multiple-interval freeway traffic flow forecasting problem. The technique possesses a number of attractive qualities for traffic forecasting. It is intuitive and uses a data base of past conditions to generate forecasts. It can also be implemented as a generic algorithm and is easily calibrated at field locations, suiting it for wide-scale deployment. The model was applied at two sites on the Capital Beltway monitored by the Northern Virginia Traffic Management System. The nonparametric regression forecasting model produced accurate short- and long-term volume estimates at both sites.

scholarly journals Measurement of Uncertainty Costs with Dynamic Traffic Simulations

2008 ◽  
Vol 2085 (1) ◽  
pp. 67-75 ◽  
Author(s):  
Fabrice Marchal ◽  
André de Palma
Keyword(s):  
Intelligent Transportation Systems ◽  
Traffic Management ◽  
Transportation Systems ◽  
Adjustment Process ◽  
Dynamic Traffic ◽  
Factors Affecting ◽  
Travel Costs ◽  
Order Of Magnitude ◽  
Utility Loss ◽  
The Impact

Nonrecurrent congestion in transportation networks occurs as a consequence of stochastic factors affecting demand and supply. Intelligent transportation systems such as advanced traveler information systems and advanced traffic management systems are designed to reduce the impacts of nonrecurrent congestion by providing information to a fraction of users or by controlling the variability of traffic flows. For these reasons, the design of these systems requires a reliable forecast of nonrecurrent congestion. A new method is proposed to measure the impacts of nonrecurrent congestion on travel costs by taking risk aversion into account. The traffic model is based on the dynamic traffic simulation model METROPOLIS. Incidents are generated randomly by reducing the capacity of the network. Users can instantaneously adapt to the unexpected travel conditions or can also change their behavior through a day-to-day adjustment process. Comparisons with incident-free simulations provide a benchmark for potential travel time savings that can be brought about by a state-of-the-art information system. The impact of variable travel conditions is measured by describing the willingness to pay to avoid risky or unreliable journeys. Indeed, for risk-averse drivers, any uncertainty corresponds to a utility loss. This utility loss is computed for several levels of network disruption. The main result of the study is that the utility loss due to uncertainty is of the same order of magnitude as the total travel costs.

scholarly journals Robust Filtering Techniques for RTK Positioning in Harsh Propagation Environments

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1250
Author(s):  
Daniel Medina ◽  
Haoqing Li ◽  
Jordi Vilà-Valls ◽  
Pau Closas
Keyword(s):  
Intelligent Transportation Systems ◽  
Robust Statistics ◽  
Real Data ◽  
Transportation Systems ◽  
Global Navigation Satellite Systems ◽  
Mixed Integer ◽  
Robust Filtering ◽  
Precise Positioning ◽  
The Impact ◽  
Filtering Techniques

Global navigation satellite systems (GNSSs) play a key role in intelligent transportation systems such as autonomous driving or unmanned systems navigation. In such applications, it is fundamental to ensure a reliable precise positioning solution able to operate in harsh propagation conditions such as urban environments and under multipath and other disturbances. Exploiting carrier phase observations allows for precise positioning solutions at the complexity cost of resolving integer phase ambiguities, a procedure that is particularly affected by non-nominal conditions. This limits the applicability of conventional filtering techniques in challenging scenarios, and new robust solutions must be accounted for. This contribution deals with real-time kinematic (RTK) positioning and the design of robust filtering solutions for the associated mixed integer- and real-valued estimation problem. Families of Kalman filter (KF) approaches based on robust statistics and variational inference are explored, such as the generalized M-based KF or the variational-based KF, aiming to mitigate the impact of outliers or non-nominal measurement behaviors. The performance assessment under harsh propagation conditions is realized using a simulated scenario and real data from a measurement campaign. The proposed robust filtering solutions are shown to offer excellent resilience against outlying observations, with the variational-based KF showcasing the overall best performance in terms of Gaussian efficiency and robustness.

scholarly journals An Advanced Deep Learning Approach for Multi-Object Counting in Urban Vehicular Environments

2021 ◽  
Vol 13 (12) ◽  
pp. 306
Author(s):  
Ahmed Dirir ◽  
Henry Ignatious ◽  
Hesham Elsayed ◽  
Manzoor Khan ◽  
Mohammed Adib ◽  
...  
Keyword(s):  
Deep Learning ◽  
Intelligent Transportation Systems ◽  
Smart Cities ◽  
Weather Conditions ◽  
Research Area ◽  
Transportation Systems ◽  
Detection Accuracy ◽  
Adverse Weather ◽  
Object Counting ◽  
The Impact

Object counting is an active research area that gained more attention in the past few years. In smart cities, vehicle counting plays a crucial role in urban planning and management of the Intelligent Transportation Systems (ITS). Several approaches have been proposed in the literature to address this problem. However, the resulting detection accuracy is still not adequate. This paper proposes an efficient approach that uses deep learning concepts and correlation filters for multi-object counting and tracking. The performance of the proposed system is evaluated using a dataset consisting of 16 videos with different features to examine the impact of object density, image quality, angle of view, and speed of motion towards system accuracy. Performance evaluation exhibits promising results in normal traffic scenarios and adverse weather conditions. Moreover, the proposed approach outperforms the performance of two recent approaches from the literature.

Deriving Traffic-Performance Measures and Levels of Service from Second-Order Statistical Features of Spatiotemporal Traffic Contour Maps

2003 ◽  
Vol 1858 (1) ◽  
pp. 148-157 ◽  
Author(s):  
Sherif Ishak
Keyword(s):  
Intelligent Transportation Systems ◽  
Traffic Management ◽  
Performance Monitoring ◽  
Transportation Systems ◽  
Second Order ◽  
Level Of Service ◽  
Large Set ◽  
Contour Map ◽  
Contour Maps ◽  
Statistical Measures

Little information has been successfully extracted from the wealth of data collected by intelligent transportation systems. Such information is needed for the efficiency of operations and management functions of traffic-management centers. A new set of second-order statistical measures derived from texture characterization techniques in the field of digital image analysis is presented. The main objective is to improve the data-analysis tools used in performance-monitoring systems and assessment of level of service. The new measures can extract properties such as smoothness, homogeneity, regularity, and randomness in traffic operations directly from constructed spatiotemporal traffic contour maps. To avoid information redundancy, a correlation matrix was examined for nearly 14,000 15-min speed contour maps generated for a 3.4-mi freeway section over a period of 5 weekdays. The result was a set of three second-order measures: angular second moment, contrast, and entropy. Each measure was analyzed to examine its sensitivity to various traffic conditions, expressed by the overall speed mean of each contour map. The study also presented a tentative approach, similar to the conventional one used in the Highway Capacity Manual, to evaluate the level of service for each contour map. The new set of level-of-service criteria can be applied in real time by using a stand-alone module that was developed in the study. The module can be readily implemented online and allows traffic-management center operators to tune a large set of related parameters.

Smart Traffic Management for Collision Avoidance Using V2V

2021 ◽  
Vol 11 (1) ◽  
pp. 01-07
Author(s):  
V. Naren Thiruvalar ◽  
E. Vimal
Keyword(s):  
Intelligent Transportation Systems ◽  
Traffic Congestion ◽  
Traffic Management ◽  
Emergency Situation ◽  
Transportation Systems ◽  
Pollution Monitoring ◽  
Inappropriate Use ◽  
V2v Communication ◽  
Use Of Resources ◽  
Smart Traffic

The main objective of this project is to connect the vehicles together and avoid accidents by using V2V Communication. The vehicles are to be connected together by means of DSRC algorithm which is used for transceiving alert messages among the connected vehicles, in case of any emergency situation such as accidents. The Vehicle-to-Vehicle (V2V) and Vehicle-to- Infrastructure (V2I) technologies are specific cases of IoT and key enablers for Intelligent Transportation Systems (ITS). V2V and V2I have been widely used to solve different problems associated with transportation in cities, in which the most important is traffic congestion. A high percentage of congestion is usually presented by the inappropriate use of resources in vehicular infrastructure. In addition, the integration of traffic congestion in decision making for vehicular traffic is a challenge due to its high dynamic behaviour. An increase in the infrastructure growth is a possible solution but turns out to be costly in terms of both time and effort. Various applications that target transport efficiency could make use of the vast information collected by vehicles: safety, traffic management, pollution monitoring, tourist information, etc.

An 802.11p Compliant System Prototype Supporting Road Safety and Traffic Management Applications

2014 ◽  
Vol 3 (1) ◽  
pp. 1-17 ◽  
Author(s):  
Helen C. Leligou ◽  
Periklis Chatzimisios ◽  
Lambros Sarakis ◽  
Theofanis Orphanoudakis ◽  
Panagiotis Karkazis ◽  
...  
Keyword(s):  
Intelligent Transportation Systems ◽  
Road Safety ◽  
Traffic Management ◽  
Life Quality ◽  
Road Transport ◽  
Transportation Systems ◽  
Ieee 802.11P ◽  
Practical Implementation ◽  
Communication Devices ◽  
The Right

During the last decades Intelligent Transportation Systems (ITS) have been attracting the interest of an increasing number of researchers, engineers and entrepreneurs, as well as citizens and civil authorities, since they can contribute towards improving road transport safety and efficiency and ameliorate environmental conditions and life quality. Emerging technologies yield miniaturized sensing, processing and communication devices that enable a high degree of integration and open the way for a large number of smart applications that can exploit automated fusion of information and enable efficient decisions by collecting, processing and communicating a large number of data in real-time. The cornerstone of these applications is the realization of an opportunistic wireless communication system between vehicles as well as between vehicles and infrastructure over which the right piece of information reaches the right location on time. In this paper, the authors present the design and implementation of representative safety and traffic management applications. Specifically the authors discuss the hardware and software requirements presenting a use case based on the NEC Linkbird-MX platform, which supports IEEE 802.11p based communications. The authors show how the functionality of IEEE 802.11p can be exploited to build efficient road safety and traffic management applications over mobile opportunistic systems and discuss practical implementation issues.

Sign in / Sign up

Export Citation Format

Share Document