• Transport Research
• Open Access close
• Procedia Computer Science close

Abstract Traffic congestion is the main problem faced by big cities, such as Jakarta. One approach to reduce congestion levels is to improve traffic management that regulates and controls the number of vehicles. To evaluate the impact of traffic management before direct implementation on the highway, traffic modeling can be carried out. Parameters in modeling traffic must be determined from a calibration process where the vehicle is accurately measured for its position and speed. This study aims to propose an efficient calibration procedure with accurate results, based on recorded vehicle movement in perspective view. First, the road image is projected using the Direct Linear Transformation (DLT) method, then the vehicle position is detected using the Background Subtraction and tracked using Mixture of Gaussian (MoG) to determine the vehicle speed. Finally, we develop a prototype of Automated Traffic Flow Monitoring based on Python programming. In the experiment results, the accuracy of vehicle position detection is evaluated based on the Euclidean distance. The average difference between the results of position detection with ground-truth is 12.07 pixels with a camera angle 40 °. The percentage of speed measurement accuracy using the DLT projection method is 96.14%.

Rapid development of metropolitan cities into smart cities and daily increased in number of vehicles on the roads causes increase in traffic maintenance challenges such as traffic congestion, accidents, dispatching of emergency vehicle and pollution. It will suffers people travel time, delay in response time of emergency vehicle such as ambulance, fire brigade, police etc., causes heavy loss or effects society in terms of wealth, emotions and security. The research work done in the area of Intelligent Transportation Systems and Traffic Management primarily focuses on determining effectively green light duration along with dispatching of emergency vehicle. In this research paper, the authors propose an algorithm which not only determines green light duration dynamically but also handles the emergency vehicle management efficiently. The objectives of the proposed algorithm are minimizing average waiting time. It always analysis the traffic situation at traffic intersection, along with continuous monitoring of emergency vehicle arrival at different lanes causes to optimize the waiting time of vehicle in lanes. It also deals with the deadlock and starvation condition, due to arrival of emergency vehicle in repeated interval of time in traffic intersection. The security level of emergency vehicle is in consideration during dispatching that assigned and verified by authorities to preserve security measures and society values. Here, the source of input on dynamic traffic condition is collected through Wireless Sensor Networks technology.

Abstract Traffic congestion is a major issue in urban cities leading to aggregated traffic. With the advancement in intelligent internet of vehicles, new technologies and protocols have been developed to predict the traffic congestion and utilize this traffic-related knowledge for congestion prediction and identification. This paper highlight the ML approach to identify traffic congestion based on multiple parameters such as hard delay constraints, the speed available through GSP vehicle trajectory. Here, we have used the Gaussian process in ML for prediction of traffic speed which uses 3 datasets i.e. training set, prediction set, and road sector data frame. ML can provide live traffic prediction in real-time, future traffic prediction and short-term traffic prediction on recent observation and historical data. In this paper using the data set, we have identified three different time slots for vehicle traffic congestion monitoring and evaluated the average speed of vehicles on the road sector during respective time slots.

Abstract In this paper we describe the privacy concerns, risks and protection mechanisms within the i-Tour project. The role of legislation for privacy in Europe and other global sectors is examined to describe a privacy protection model that complies with the immediate target of European deployment but that also looks forward to the re-use of the approach across a wider global territory and technical deployment range.

AbstractUsers of International Land Ports of Entries (LPOEs) at the US – Mexico border experience excessive wait times on a daily basis. This contributes to the increased transportation costs, and also generates health and environmental problems in border regions. Traffic simulation models are effective tools for evaluating passenger vehicle, pedestrian and commercial traffic operations. These tools can be used to assess various scenarios and visualize current traffic conditions. Results obtained from these tools should be taken into account in congestion relief decision making processes. The research team developed, calibrated and validated three traffic models of the Ysleta-Zaragoza LPOE using three different software packages (i.e., TransModeler, VISSIM, and Aimsun). This paper presents advantages and disadvantages of each tool when modeling international LPOEs. Results presented herein can be used by practitioners to decide which tool should to be used for modeling LPOEs at the U.S. – Mexico border.

Abstract This article describes the numerical methods of mathematical modeling of traffic flows to meet the challenges of optimizing the traffic light phases at signal-controlled road intersections. The flow of vehicles on multilane roads is described by Poisson process. The paper introduced, justified and calculated concept «effective number of lanes», characterized by a maximum flow of vehicles with different phases of traffic lights.

Abstract With the fast development of sharing economy and network, sharing bikes increasingly become more and more popular. Sharing bikes are devoted to solving the problem in the last trip. In order to realize the maximization of benefit, companies always invest a large number sharing bikes to enhance the occupation ratio of market. However, they don’t recovery the faulty bikes, thus causing traffic congestion and environmental pollution. This paper observes the cost of reverse logistic and customer satisfaction in significant regionals, then establishes a reverse logistic network for faulty sharing bikes. A Modified Genetic Simulated Annealing Algorithm(MGSA) is applied to solve this model. The computation results verify the effectiveness of the MGSA.

Abstract Carpooling is an emerging alternative transportation mode that is eco-friendly and sustainable as it enables commuters to save time, travel resource, reduce emission and traffic congestion. The procedure of carpooling consists of a number of steps namely (i) create a motive to carpool, (ii) communicate this motive with other interested agents, (iii) negotiate a plan with the interested agents, (iv) execute the agreed plans and (v) provide a feedback to all concerned agents. The state-of-the-art research work on agent-based modeling is limited to a number of technical and empirical studies that are unable to handle the complex agent behavior in terms of coordination, communication and negotiations. In this paper we present a conceptual design of an agent-based model (ABM) for the carpooling application that serves as a proof of concept. Our agent-based model for the carpooling application is a computational model that is used for simulating the interactions of autonomous agents and to analyze the effects of change in factors related to the infrastructure, behavior and cost. In our agent-based carpooling application we use agent profiles and social networks to initiate our agent communication model and then employ a route matching algorithm and a utility function to trigger the negotiation process between agents. We plan to, as a part of the future work, develop a prototype of our agent-based carpooling application on the basis of the work presented in this paper. Furthermore, we also intend to carry out a validation study of our results with real data.