A Robust Kalman Filter Based Data Fusion Method for Traffic Speed Estimation

The applications of wireless sensor network in urban intelligent transportation system (ITS) were lucubrated, and an ARM9 SoC (system-on-chip) embedded sensor node was developed for urban traffic information collection and data transmission and reception. Together with the appropriate software programmed and intelligent control model for the urban traffic system built, the real time traffic data could be collected and processed for information distribution, and macro and scale coordination for ITS control within a city range through wireless sensor network that consists of this newly designed sensor nodes. Related algorithm for calculating the space occupancy and the congestion expectation for ITS purpose is presented, and the vehicle speed model is illustrated. Simulation results show that this novel ITS system based on the newly designed SoC embedded sensor nodes is practical and feasible. In addition, this system is also characterized at higher cost-performance, flexibility and control efficiency comparing to those ITS systems based on the Global Position Systems.

Taiwan is a highly informational country, and a robust traffic network is not only critical to the national economy, but is also an important infrastructure for economic development. This paper aims to integrate government open data and global positioning system (GPS) technology to build an instant image-based traffic assistant agent with user-friendly interfaces, thus providing more convenient real-time traffic information for users and relevant government units. The proposed system is expected to overcome the difficulty of accurately distinguishing traffic information and to solve the problem of some road sections not providing instant information. Taking the New Taipei City Government traffic open data as an example, the proposed system can display information pages at an optimal size on smartphones and other computer devices, and integrate database analysis to instantly view traffic information. Users can enter the system without downloading the application and can access the cross-platform services using device browsers. The proposed system also provides a user reporting mechanism, which informs vehicle drivers on congested road sections about road conditions. Comparison and analysis of the system with similar applications shows that although they have similar functions, the proposed system offers more practicability, better information accessibility, excellent user experience, and approximately the optimal balance (a kind of symmetry) of the important items of the interface design.

The paper presents a model of the emission load in the vicinity of a monitored road in relation to the real traffic input data. It describes a simple method of the emission load estimating. In Addition to the modeling method itself, the paper describes particular methodologies of the real data conversion and processing. Discussed are traffic intensities of the heavy trucks over 12 tons of weight. The model uses as its input real traffic data files from intelligent traffic systems (ITS) localized by the monitored roads. More specifically, data from selected highway toll gates were used in this work. At the end, particular and final, results are presented in graphs as examples.

Traffic information system may produce massive and complex traffic data with the process of collecting real-time original GPS (Global Positioning System) data, matching positions to a map and generating traffic flow information, which brings great markets for even-worse traffic condition in China. Howerver, several issues would occur when we reuse these massive traffic data for history data mining applying on-hand database management tools or traditional data processing apporaches, such as massive storage, high performance processing, open interface. Big Data system usually includes data sets with sizes beyond the ability of commonly-used software tools to capture, manage, and process the data within a tolerable elapsed time. With this difficulty and the advantage of Big Data, we schemed RTIC-C system to handle sensemaking over large quantities of traffic data based on cloud computing technique. RTIC-C designs a distributed data management service to support large scale of data storage, a parallel distributed computing framework for diverse kinds of mining applications based on Map-Reduce mechanism, a restful Web services interface to support third-party mining applications. Experiments on a massive traffic data sets showed that RTIC-C achieves considerable performance comparing with traditional traffic data mining applications.

Formalizing computational intensity of big traffic data understanding and analysis for parallel computing

Data missing remains a difficult and important problem in the transportation information system, which seriously restricts the application of the intelligent transportation system (ITS), dominatingly on traffic monitoring, e.g., traffic data collection, traffic state estimation, and traffic control. Numerous traffic data imputation methods had been proposed in the last decade. However, lacking of sufficient temporal variation characteristic analysis as well as spatial correlation measurements leads to limited completion precision, and poses a major challenge for an ITS. Leveraging the low-rank nature and the spatial-temporal correlation of traffic network data, this paper proposes a novel approach to reconstruct the missing traffic data based on low-rank matrix factorization, which elaborates the potential implications of the traffic matrix by decomposed factor matrices. To further exploit the temporal evolvement characteristics and the spatial similarity of road links, we design a time-series constraint and an adaptive Laplacian regularization spatial constraint to explore the local relationship with road links. The experimental results on six real-world traffic data sets show that our approach outperforms the other methods and can successfully reconstruct the road traffic data precisely for various structural loss modes.

Urban traffic situation information is the basis of effective traffic guidance and traffic control. In order to promote communication and practical applications of traffic information, then can provide full, accurate, real time and sufficient traffic information service to public, government and correlative enterprises, in this paper, the authors proposed the dynamic traffic information collection and processing methods of intelligent transportation systems (ITS) common information platform (CIP) based on floating car technology. According to the characteristics of the ITS CIP data collection, they were required large scale, accurate and dynamic data collecting. A complete set of dynamic traffic information processing methods based on floating car technology were studied, including road data storage by two queues, error data elimination by taximeter, map matching by region dividing method and boundary rectangle, and traffic condition calculation by circle queues and A* algorithm. The application of the methods in the ITS CIP of Guangzhou City proved that the methods were quite effective and valuable to be popularized.

Traffic flow prediction is an important part of intelligent transportation system (ITS). Accurate traffic flow prediction information can provide reliable reference for traffic management decision-makers, effectively reduce traffic congestion, reduce vehicle exhaust pollution, save energy and facilitate the travel of the people. Most of the existing traffic flow prediction models simplify the traffic flow change process into a linear and stable process and ignore the influence of weather conditions on traffic flow, which will lead to large prediction deviation. In order to improve the accuracy of traffic flow prediction, this paper proposes an ensemble learning method based on ET and AdaBoost for fusing traffic and meteorological data under the non-stationary environment to predict the changes of traffic flow. The experiment is based on real traffic and meteorological data, and the results show that the proposed ensemble method is superior to the baseline methods.

Vehicle arrival time is one of the most important factors of intelligent transportation systems (ITS). Accurate transit travel information is important because it attracts additional customers and increases the satisfaction of transit users. A passenger waiting for a train or bus, a person waiting for a cab, a customer waiting for a courier to come to his/her home to pickup or deliver a package, a business office waiting for a truck for goods and a home user waiting for his/her shipment for which he/she did online shopping are a few examples of how important vehicle arrival time is in different areas of life. Most companies are investing a lot of money to improve their systems for better, faster and reliable customer service. As the cost of ITS components have decreased, the automatic vehicle location (AVL) system, which is one component of ITS, has become more widely used. Many transit agencies use an AVL system to track their vehicles in real-time. Tracking systems technology was made possible by the integration of three technologies: global positioning system (GPS), global system for mobile communication (GSM) and the geographic information system (GIS). This project shows detailed research in the area of automatic vehicle location and implements a low cost vehicle tracking system using GPS and GPRS. The system reads the current position, speed and direction using GPS, the data is sent via GPRS service from a GSM network to a server using TCP/IP protocol and the server saves this information to the database on a regular time interval. The web-based application then uses this data and calculates the approximate arrival time. The system allows a user to view the present position of the vehicle using Google Maps and calculates the arrival time. Also, bus location can be monitored in real time by route supervisors. This will allow supervisors to make better service adjustment decisions because they will be able to see how the route is operating. The test bed was a bus route running in the downtown of Toronto.

For providing drivers with robust traffic information and Optimizing the energy management of Hybrid Electric Vehicles (HEVs), it is important to predict traffic information accurately with past traffic information. As acquisition of the traffic information have been easier by the development of Intelligent Transportation System (ITS), active study on traffic prediction is currently underway. Multi-Layer Perceptron (MLP) model have been widely utilized for predicting traffic information since it is appropriate to represent the non-linear characteristics inherent in traffic prediction. However, the MLP model doesn't reflect local dependencies of traffic data and is prone to noise in traffic data. Convolutional Neural Networks (CNN) based model, on the other hand, can capture the local dependencies of traffic data and is less prone to disturbance in data. In this paper, we use temporal data and speed data collected on main roads in Seoul, South Korea to construct traffic prediction models. The speed data which are collected by every 5 minutes are provided by Ministry of Land, Infrastructure and Transport in South Korea. We construct the CNN based model and two MLP models which predict traffic speed and compare performance of the prediction models in this paper. The comparison results show that the CNN based model's prediction performance is higher than the prediction performance of the other two MLP models.

Vehicular ad hoc networks have been envisioned to be useful in road safety and commercial applications. In addition, in-vehicle capabilities could be used as a service to provide a variety of applications, for example, to provide real-time junction view of road intersections or to address traffic status for advanced traffic light control. In this work, the authors construct a cloud service over vehicular ad hoc networks to provide event data including capturing videos or Global Positioning System (GPS) data. Moreover, the authors integrate the GPS receiver and the navigation software equipped over On Board Unit to create a Geographic Information System digital map and to offer a traffic safety application. The hardware is implemented by Eeepad for integrating camera and GPS. Furthermore, the cyclic recording scheme has been addressed for data transmission and query. With the design, people can get real-time traffic information including traffic videos or geographical data in the cloud.

Vehicular ad hoc networks have been envisioned to be useful in road safety and commercial applications. In addition, in-vehicle capabilities could be used as a service to provide a variety of applications, for example, to provide real-time junction view of road intersections or to address traffic status for advanced traffic light control. In this work, the authors construct a cloud service over vehicular ad hoc networks to provide event data including capturing videos or Global Positioning System (GPS) data. Moreover, the authors integrate the GPS receiver and the navigation software equipped over On Board Unit to create a Geographic Information System digital map and to offer a traffic safety application. The hardware is implemented by Eeepad for integrating camera and GPS. Furthermore, the cyclic recording scheme has been addressed for data transmission and query. With the design, people can get real-time traffic information including traffic videos or geographical data in the cloud.

The loss of traffic state data is a common problem in intelligent transportation system. To improve the imputation accuracy and robustness of road traffic data, a novel generative adversarial network for the imputation of road network traffic data is proposed in this paper, i.e., GAE-GAN-LSTM. The spatiotemporal characteristics were extracted using a improved graph auto-encoder (GAE), followed by a generative adversarial network (GAN) to generate the complete spatiotemporal characteristics on the basis of the missing features. The internal structure of the generator was a long short-term memory network (LSTM), and the internal structure of the discriminator was a fully connected neural network (FCN). Finally, the traffic state data could be recovered by the decoder of GAE. The experimental results revealed that the performance of the proposed method was better than that of the other methods at any data loss ratio considered. The main innovations of the proposed method include two aspects. One, an improved GAE for the imputation of road network data was presented by redefining the loss function of GAE, which could effectively extract the potential spatiotemporal features of a road network. Two, the GAN was used to generate the spatiotemporal characteristics of the traffic state data by using the strong data generation ability of GAN.KeywordsData imputationGraph auto-encoderGenerative adversarial networkRoad traffic state data

The development of applications for advanced Intelligent Transportation Systems (ITS), is a growing research area, pushed especially by the need to mitigate problems related to transportation inefficiency, overuse and pollution, mainly caused by the increasing of traffic congestions in big cities. Nowadays, traffic related data coming from the road infrastructure, user's cars or mobile phones, is generated in unprecedent volume and speed. Therefore, ITS face new challenges, with respect to growing demand to process large volumes of traffic data in real-time, and extract value that can be immediately used for decision making. The work presented here, proposes a scalable architecture supported by Big Data technologies, capable of processing real-time traffic data captured from 349 inductive loop counters, placed in Slovenian road network. The main goal is to propose an approach which can be adopted by national road operators, capable of monitoring, in real-time, the current status of the road network. Traffic events need to be detected in real-time and require the collection of data from several fixed sensors. To deal with data volume and velocity challenges, a data stream management system was used, able to collect traffic data that arrives and process it on a continuous (24×7) basis. Results achieved, suggest that there's a great advantage in the adoption of a data stream management system, with respect to traditional database management systems, illustrated by practical examples, providing quantitative metrics about data processing performance.

In view of the problems existing in the current transportation industry, such as the isolated island of traffic business data information, the lack of fusion and collaboration of various traffic data and the insufficient collection of semantic information of traffic environment, this paper proposes to build an integrated platform of vehicle-road collaborative perception. Through the technology of device access, device management and device collaboration, the goal of unified access to multi-type, multi-protocol and multi-scene traffic environment sensing devices is realized. The digital map of all-factor traffic resources is constructed by using the technologies of ubiquitous communication network of vehicle networking, multi-sensor fusion, edge computing and semantic segmentation of computer vision images. It provides rich semantic data support for analyzing traffic problems, mastering traffic characteristics and predicting traffic development trends, and provides data interfaces and consistent analysis platforms for various existing traffic business platforms.