Search

The increasing number of vehicles that was not accompanied by an adequate road infrastructure readiness causes traffic jams. Traffic jams often occur repeatedly every day, especially at certain times, such as when people are going to and from work. The same traffic jams can also occur at the beginning or the end of the week; this usually repeats every week. As a result, if the congestion dataset is known, the repeating traffic congestion for daily and weekly congestion can be anticipated. In this study, traffic congestion predictions are modeled using the Neural Network Algorithm based on traffic congestion data collected within 24 hours for one to two weeks. The parameters used in optimizing Neural Network performance are learning rate, momentum, and epochs (training cycles). Based on these experiments, the Neural Network Algorithm successfully modeled traffic density patterns which are recurring congestion patterns, with quite good results. [ABSTRACT FROM AUTHOR]

Today, urban congestion is worsening in many countries as a result of population growth, economic growth, private car ownership, urbanization, housing development, and employment opportunities. It is very important to understand what factors cause this traffic congestion. Thus, this paper discussed on how travel demand strategies contribute to traffic congestion in Kuala Lumpur, Malaysia. Using a causal loop diagram (CLD), a hypothetical framework was developed to represent the causality of connected variables in four subsectors: transport demand, transport supply, transport system, and modal share in traffic congestion based on various reports from government agencies and existing literature reviews. A conceptual structure of CLD allows the modeler to understand the dynamic relationship between variables found in the complex transportation systems. The CLD will be used as a basis for developing a dynamic simulation model in future work. [ABSTRACT FROM AUTHOR]

The Mahuvan toll plaza is one of the toll plazas on National Highway-44 in the state of Uttar Pradesh, India. It also happens to be the busiest of the toll plazas in the state. This paper examines the present causes of traffic congestion and proposes remedies to alleviate the situation. MTC (Manual Toll Collection) and ETC (Electronic Toll Collection) are the two charging systems that are responsible for the majority of the delays and queues. This toll plaza has a mixed lane system, which means that both MTC and ETC cars can pass via the same lane at the same time. Aside from that, some more reasons of traffic congestion were discovered with the use of the data collected and a visual on-site assessment. Taking all of these factors into consideration, this study proposes a variety of solutions to these issues. Based on the traffic volumes, it was discovered that the toll booth capacity and the type of toll service had an impact on the operation of the traffic flow and the efficiency of the toll plaza. Several recommended designs for varied traffic conditions and toll plaza setups have been proposed in light of the problems that have been discovered at the Mahuvan Toll Site. It is hoped that this research would be valuable in management and decision-making situations. [ABSTRACT FROM AUTHOR]

Adequate planning and management for freight transport are essential for attaining sustainable development in both transport and economy sectors alike. Locating and evaluating the optimal routes that minimize travel times and hence fuel consumption for delivery trucks are vital tasks to achieve such development. The central aim of this paper is to boost fresh food truck-based transport within the city of Al-Najaf (Iraq) by tackling the travel time reliability issue resulting from urban road congestion. Accordingly, two objectives need to be accomplished; first, to determine the fastest route for fresh produce (vegetables and fruits) delivery trucks traveling between the city's fresh food wholesale center and its southern entrance; second, to investigate the impacts of road traffic congestion on the optimal location for the least-time route. The methodology involves employing a passenger car equipped with a digital camera to conduct the required travel time and delay surveys using the floating car driving technique along the street network of Al-Najaf city. The collective length of the arterial and collector streets that have been surveyed is about 400 km. Six travel time runs have been carried out for each segment per direction at three traffic stream conditions; morning peak, off-peak, and free-flow conditions. A total of 3168 single travel time runs have been conducted. The ESRI ArcGIS (10.8.1) software is employed to digitize and model the network streets and thus conduct the required route-specific network analyses. A real case study that involves modeling and investigating the routes and driving times used by fresh food truck drivers traveling between Al-Najaf fresh food wholesale center and the city's southern entrance has been analyzed. The route analyses revealed that the ArcGIS-based fastest route can achieve a saving in driving time up to 25 minutes (66%) compared with other actual routes currently used by truck drivers. Furthermore, the analysis also revealed how the location of the resultant fastest route is highly influenced by traffic congestion. [ABSTRACT FROM AUTHOR]

The rise in vehicle use as a means of transportation contributes to transportation problems occurring in big cities, including traffic congestion. This paper aims to provide insight into the prediction of traffic congestion by collecting the vehicle speed, the total number of vehicles, and time-based on two pre-recorded videos of congestion and non-congestion scenario for 30 seconds. The methodology used in this experiment uses OpenCV-Python to calculate and collect speed and the total number of vehicles in which these data will then be processed and analysed by using Orange with the help of machine learning (ML) techniques. ML techniques used are Decision Tree, Naive Bayes, Random Forest, and Support Vector Machine (SVM). This experiment's results illustrate that the ML technique that shows the best and most accurate for congestion prediction is Naive Bayes at 94.29%. Meanwhile, Decision Tree at 82.86%, Random Forest at 80%, and the lowest accuracy is SVM at only 20% for congestion prediction. All data processed are from a set of training data, where the correct classification has been determined beforehand. This study contributes to the effectiveness and accuracy of the method's congestion prediction, which can be used as a platform for future research to improve traffic congestion predictions. [ABSTRACT FROM AUTHOR]

Traffic congestion is a formidable problem that is affecting the routine lives of people worldwide. A number of traffic control schemes have been introduced but still the problem is same. Virtual Traffic Light is one of the schemes introduced as a solution to traffic management at intersections. By selecting the right way in a distributed fashion at an intersection through Vehicle-to-Vehicle Communications. Through this scheme, we can manage the traffic at an intersection in a self-organized manner. Another factor for traffic is Travel behavior, It has become a significant research area due to its specific features for road safety support, human life safety support, and pillar for reducing traffic congestion environment. Hence, many methods and applications have been deployed to preserve and encourage Travel Behavior Modeling (TBM). The motivation behind this paper about a high level of traffic congestion which makes many other issues like high fuel consumption, wasted money and time delay, resulted in significant economic and productivity losses. TBM is one of the significant solutions for modeling travel behavior. The definition, characteristics, and classification of Travel Behavior Modeling are introduced. Addressing monitoring travel behavior is a challenging and time- demanding task that requires data sources for processing and analysis of travel behavior. Recently, several solutions were identified to address the challenges and issues of modeling travel behavior. Travel behavior Modeling, Virtual Traffic Lights and Novel Framework for Road Traffic Management is reviewed in this study. The research directions in the field are also introduced based on opportunities. Furthermore, research challenges are investigated, such as data security, adaptability, internet connectivity, and natural disaster. [ABSTRACT FROM AUTHOR]

Rail-based Mass Rapid Transit System are has been widely accepted mode of transportation system as a solution for traffic jam and environmental pollution associated problems which faced by all of the metro cities and developing countries in the word. Metro rail projects are escalating in a good manner in India to avoid the traffic congestions and to provide the comfort riding to the publics. The metro rails are being used in cities like New Delhi, Chennai, Mumbai and Kolkata and is also under the expansion and up gradation of rail projects are carried out for the better operations. Cities like Bangalore, Chennai and Hyderabad is under the constructive works. Planning and scheduling of the construction activities are the prime task, for this project management plays a vital role to accomplish the task in a smooth manner. The project management model is not only satisfied the completion of the project and also to finish the project in stipulated time, greater efficiency and economy. In this project work the study has been carried out for need of metro rail system and utilization of Microsoft project software for handling and managing the construction activities. [ABSTRACT FROM AUTHOR]