Traffic Congestion Information Research Articles

Understanding shared bike usages toward metros with fewer physical road separations

Physical road separations are normally considered cyclist-friendly, but whether they are unfriendly to the combination of bike-share (BS) and metros is seldom investigated since they might affect the cycling’s flexibility and convenience to cross streets and reach the destination. Although integrating BS and metro is thought to mitigate traffic congestion, how traffic congestion affects the usage of integration remains unknown. This study, conducted in Suzhou, China, examines new factors (road separation and traffic congestion) alongside well-studied factors influencing BS and metro integration. The survey revealed increased BS usage frequency after a new metro’s opening. Variables such as road separations, traffic congestion information, road network density, and proximity to metros are considered. They are processed in a selected area considering cyclable network and Thiessen Polygon corresponding to the selected metro stations. An ordered probit model is established to investigate significant factors. It is found that as more columns of road separations exist, the cyclists are less likely to use BS towards metros, regardless of whether they are cycling weekends or weekdays. Interestingly, after the new metro opened and a new metro hub was formed, proximity to the new metro hub is associated with lower BS transfer demand. A higher congestion level promotes more cycling toward the metro system on weekdays as well as higher parking fees. This indicates that the combination of BS and metro could attract former motor vehicle users and this finding could be instructive for urban planners and road designers.

Dynamic Traveling Route Planning Method for Intelligent Transportation Using Incremental Learning-Based Hybrid Deep Learning Prediction Model with Fine-Tuning

Abstract Predicting the most favorable traveling routes for Vehicles plays an influential role in Intelligent Transportation Systems (ITS). Shortest Traveling Routes with high congestion grievously affect the driving comfort level of VANET users in populated cities. As a result, increase in journey time and traveling cost. Predicting the most favorable traveling routes with less congestion is imperative to minimize the driving inconveniences. A major downside of existing traveling route prediction models is to continuously learn the real-time road congestion data with static benchmarking datasets. However, learning the new information with already learned data is a cumbersome task. The main idea of this paper is to utilize incremental learning on the Hybrid Learning-based traffic Congestion and Timing Prediction (HL-CTP) to select realistic, congestion-free, and shortest traveling routes for the vehicles. The proposed HL-CTP model is decomposed into three steps: dataset construction, incremental and hybrid prediction model, and route selection. Firstly, the HL-CTP constructs a novel Traffic and Timing Dataset (TTD) using historical traffic congestion information. The incremental learning method updates the novel real-time data continuously with the TDD during prediction to optimize the performance efficiency of the hybrid prediction model closer to real-time. Secondly, the hybrid prediction model with various deep learning models performs better by taking the route prediction decision based on the best sub-predictor results. Finally, the HL-CTP selects the most favorable vehicle routes selected using traffic congestion, timing, and uncertain environmental information and enhances the comfort level of VANET users. In the simulation, the proposed HL-CTP demonstrates superior performance in terms of Mean Square Error (MSE), Mean Absolute Error (MAE), and Root Mean Square Error (RMSE).

Aberrant Driving Behavior Prediction for Urban Bus Drivers in Taiwan Using Heart Rate Variability and Various Machine Learning Approaches: A Pilot Study

Objective: Aberrant driving behavior (ADB) decreases road safety and is particularly relevant for urban bus drivers, who are required to drive daily shifts of considerable duration. Although numerous frameworks based on human physiological features have been applied to predict ADB, the research remains at an early stage. This study used heart rate variability (HRV) parameters to establish ADB occurrence prediction models with various machine learning approaches. Methods: Twelve Taiwanese urban bus drivers were recruited for four consecutive days of naturalistic driving data collection (from their routine routes) between March and April 2020; driving behaviors and physiological signals were obtained from provided devices. Weather and traffic congestion information was determined from public data, while sleep quality and professional driving experience were self-reported. To develop the ADB prediction model, several machine learning models—logistic regression, random forest, naive Bayes, support vector machine, and gated recurrent unit (GRU)—were trained and 10-fold cross-validated by using the testing data. Results: Most drivers with ADB reported deficient sleep quality (≤80%), with significantly higher mean scores on the Karolinska Sleepiness Scale and driver behavior questionnaire subcategory of lapses and errors than drivers without ADB. Next, HRV indices significantly differed between the measurement of a pre-ADB event and a baseline. The accuracy of the GRU models ranged from 78.84% ± 1.49% to 89.57% ± 1.31%. Conclusion: Drivers with ADB tend to have inadequate sleep quality, which may increase their fatigue levels and impair driving performance. The established time-series models can be considered for ADB occurrence prediction among urban bus drivers.

Efficient MCC Self Driven Car Using Dynamic Priority Based Resource Allocation Algorithm

Abstract: Smart vehicles are equipped with a variety of sensing devices that provide a variety of multimedia applications and services related to smart driving assistance, weather forecasting, traffic congestion information, road safety alarms, and a variety of entertainment and comfort-related applications in an intelligent transportation system. Due to their limited computational capacity and storage capabilities, these smart cars generate a tremendous volume of multimedia-related data that requires quick and real-time processing, which can't be completely handled by independent on-board computer systems. As a result, changing the underpinning networking and computing architectures was required to handle such multimedia applications and services

Designing an intelligent emergency response system to minimize the impacts of traffic incidents: a new approximation queuing model

ABSTRACT A road traffic accident is an unexpected, irregular activity on the road network that sources a high excess demand relative to the reduced road capacity, resulting in traffic congestion and delays for travellers. The emergency response agencies need to shortly discover, respond to, and clear road traffic accidents in order to decrease the impacts of incidents on traffic congestion. To create an intelligent incident management response system for road networks, real-time data on traffic volumes and accident rates can be used in a queuing model for the allocation/relocation of available resources in response to incidents. In this study, a new queuing-based formulation is proposed for determining the positioning of emergency response units. The greatest benefit of the proposed dynamic model is a reduction in the time it takes response teams to clear accidents, remove debris on the roadway, and restore the normal traffic network. The analysis of actual accident data from New York City demonstrated that the proposed dynamic allocation strategy can contribute to reducing the total waiting time caused by accidents on roads instead of simply minimizing the average response times. The obtained results from testing the presented model revealed that the average costs in terms of the response time and the average delay reduced by 45% and 38%, in comparison to the static deployment model, respectively. HIGHLIGHTS A queuing model by characterizing the traffic congestion information is proposed. A dynamic policy of allocating response units using a queue system is studied. We study the advantages of our non-myopic model over the alternative myopic case. We show the effectiveness of the model by testing it on New York city incident data. The proposed dispatching strategy reduces the response time and the average delay.

Flow control oriented forwarding and caching in cache-enabled networks

The cache-enabled network architecture is very promising to improve the efficiency of content distribution and reduce the network congestion. In this paper, we propose a maximizing weighted throughput (MWT) algorithm for joint request forwarding, cache placement and flow control to dynamically optimize network performance. Specifically, a dual queue system that includes requests and data is established to retrieve the global content demands and traffic congestion information. In order to improve throughput performance as well as stabilize the queue, we formulate the flow-level throughput and design the request-level control policy by optimizing the throughput function and Lyapunov drift. The request forwarding policy adaptively allocates request forwarding rates for every link according to the differences among adjacent request queue backlogs. A novel cache priority function and a threshold-based request-dropping policy are used in the caching policy and flow control respectively to alleviate network overload. In addition, we prove the MWT algorithm achieves throughput near-optimal performance, and testify the dual queue system is stable by deducing the upper bound of the all queue backlogs. The experimental results verify the MWT algorithm stability and demonstrate the superiority of the MWT algorithm, compared to the state-of-the-art caching algorithms which are combined with back-pressure algorithm.

Impact of Singapore's COVID-19 confinement on atmospheric CO2 fluxes at neighborhood scale

Singapore entered a two-month partial lockdown in Apr. 2020 to curb the spread of COVID-19. The imposed measures in addition to contain the virus spread, cut the emissions of greenhouse gases as many economic activities stopped across the city. The advice of stay-at-home changed the pattern of carbon dioxide (CO2) emissions within the community. To examine how CO2 emissions responded to the COVID-19 measures at neighborhood scale, anonymized mobility data released by Google and Apple, and traffic congestion information from TomTom were used to track daily and diurnal changes in emissions related to driving, cooking and metabolic breathing in a residential neighborhood of Singapore, in which the anthropogenic and biogenic fluxes of CO2 have been widely characterized. During the lockdown, traffic emissions dropped 41%, but emissions from cooking and metabolic breathing increased 21% and 20%, respectively. The uptake of CO2 by vegetation was not able to offset these emissions, and after adding the biogenic contribution from soil and plants, a net reduction of 24% was found. During the following six months the city got its pace back, with the rate of CO2 emissions reaching similar or slightly higher levels than those predicted before the pandemic crisis. Unfortunately, the stark drop in emissions was just a temporary relief, which reduced only 3.5% the annual CO2 flux over the studied neighborhood.

Aircraft taxi time prediction: Feature importance and their implications

Taxiing remains a major bottleneck at many airports. Recently, several approaches to allocating efficient routes for taxiing aircraft have been proposed. The routing algorithms underpinning these approaches rely on accurate prediction of the time taken to traverse each segment of the taxiways. Many features impact on taxi time, including the route taken, aircraft category, operational mode of the airport, traffic congestion information, and local weather conditions. Working with real-world data for several international airports, we compare multiple prediction models and investigate the impact of these features, drawing conclusions on the most important features for accurately modelling taxi times. We show that high accuracy can be achieved with a small subset of the features consisting of those generally important across all airports (departure/arrival, distance, total turns, average speed and numbers of recent aircraft), and a small number of features specific to particular target airports. Moving from all features to this small subset results in less than a 1 percentage-point drop in movements correctly predicted within 1, 3 and 5 min.

Enhanced Traffic Management System using Artificial Intelligent Congestion Control

The smart city proposed by government is providing better infrastructure with possible automated device. Every smart city proposes to provide smart transport through automated traffic management .The peak hours face the congestion road and many traffic irregularities. The congested road aids in poor Travel experience, environmental pollution and health hazards by vehicular fuel. The solution to aforesaid issues leads to traffic Automation in urban communities. To implement the traffic automation need access to real time traffic congestion information, best possible route and alternate strategy with online traffic information applicable to specific traffic stream. An more suitable site visitors manipulate and MF has been mentioned to finish short information transmission and their corresponding motion performed via artificial intelligence. The VANET scenario, congestion manage algorithm executed through mobile agent controller uniformly organizes the traffic glide by way of heading off the congestion at the smart visitors zone ,The law-enforcement bodies ,the fire opponents and the clinical and/or paramedical teams consciousness on elevated quantity of crime in addition to lifestyles losses through site visitors irregularities. The benefits of adopting the internet of things(iot)provide a new prospect for intelligent site visitors improvement.

Blockchain-based secured event-information sharing protocol in internet of vehicles for smart cities

An intelligent transportation system is an advanced application that aims to provide traffic congestion information, road accidents, emergency information to other vehicles, etc. In the traditional transportation systems, the road-side unit (RSU) acts as a central authority and plays an important role to maintain everything in the networks. To solve single point of failure, as well as to achieve data immutability, blockchain-based decentralized vehicular ad-hoc networks is very essential and important. In order to share critical information among all the road-side units, we design a blockchain-based decentralized vehicular ad-hoc network that supports data immutability property. We have also designed an authentication protocol for the vehicle’s user and a consensus mechanism to validate transactions. Besides, a smart contract mechanism has also been proposed. Informal security analysis confirms anonymity property with other security requirements. We have also calculated and discussed communication, computation, and storage overhead of the proposed scheme.

Robust ambulance base allocation strategy with social media and traffic congestion information

At present, traffic congestion has become a major problem in many metropolitan areas globally, affecting the economy and social conditions in these areas. Of special concern, the response time of ambulances has increased, causing the death or disability of patients during emergencies. Various ambulance allocation strategies have been developed to locate a base that can achieve coverage of the demand point within a prescribed time or distance frame. However, real-time ambulance deployment is required to determine the number of ambulance and their bases. In particular, the dynamic relocation of an ambulance base is complicated, and each relocation does not guarantee that the next period will change again, thus increasing the workloads of the ambulance crew and potentially reducing their capability of responding to an emergency call. Furthermore, these models only considered covering all demand points but lacked the ability to consider uncertain factors, such as traffic congestion, patient conditions, public events, and population movement. Therefore, this study focused on formulating a covering model based on traffic congestion from web-based services and social media analysis, using the Markov-chain traffic speed assignment to allocate ambulance bases and trade-off the number of ambulance facilities between the current period and next period while considering the number of ambulance vehicles. Moreover, the proposed model was demonstrated using a case study of Bangkok emergency medical services. According to the results, obtained through collecting data on social media and traffic speed, the average traveling time of an ambulance can be improved by more than 70% with the trade-off between different periods if several emergency calls are received.

Trusted Orchestration for Smart Decision-Making in Internet of Vehicles

Decision-making is of critical significance in Internet-of-Vehicles (IoV), where vehicles need to quickly make decisions in real-time when sharing or transferring the information. In addition, it is necessary to identify the significant factors of an entity while measuring its legitimacy or to record the real-time data generated by it. Traditional automated schemes in IoV are confronted by the issues related to real-time processing and the manner they respond, such as traffic congestion information, fastest route selection, and road accidental information. The exchange of accurate information among vehicles is critical, but the decision-making for IoV has still not been fully investigated in the literature. Further, the involvement of malicious devices in the network may disgrace the network performance by consuming network resources. In this paper, we propose a hybrid decision-making scheme in vehicular informatics for data transferring and processing through VIKOR and analytic hierarchy process (AHP) methods. The proposed model is scrutinized and verified rigorously through several sensing and decision-making metrics against a conventional solution. The simulation results depict that the proposed model leads to 93 percent competence in terms of decision-making, identification of legitimate sensors, and data alteration process when sharing the information through various sensors in IoV.

Dynamic Priority-Based Efficient Resource Allocation and Computing Framework for Vehicular Multimedia Cloud Computing

In intelligent transportation system, smart vehicles are equipped with a variety of sensing devices those offer various multimedia applications and services related to smart driving assistance, weather forecasting, traffic congestion information, road safety alarms, and many entertainment and comfort-related applications. These smart vehicles produce a massive amount of multimedia related data that required fast and real-time processing which cannot be fully handled by the standalone onboard computing devices due to their limited computational power and storage capacities. Therefore, handling such multimedia applications and services demanded changes in the underlaying networking and computing models. Recently, the integration of vehicles with cloud computing is emerged as a challenging computing paradigm. However, there are certain challenges related to multimedia contents processing, (i.e., resource cost, fast service response time, and quality of experience) that severely affect the performance of vehicular communication. Thus, in this paper, we propose an efficient resource allocation and computation framework for vehicular multimedia cloud computing to overcome the aforementioned challenges. The performance of the proposed scheme is evaluated in terms of quality of experience, service response time, and resource cost by using the Cloudsim simulator.

An Empirical Study of Additional Stopover Behaviors of Car Tourists Affecting by Traffic Congestion Information Using Mobile Probe Data

Car tourists may make some additional stopovers for sightseeing, meal, shopping, or leisure activities which is not originally planned, to avoid becoming involved in the traffic congestion occurring on the homeward route. The objective of this paper is to examine whether this induced stopover behavior exists and to empirically analyze the tendency of additional stopovers by departure time periods for homeward trip and level of traffic congestions. An analysis of route search data and GPS travel trajectory data collected by mobile car navigation application is conducted. The study results show car tourists tend to have additional stopovers when the departure time for homeward trip is early, and differences in the tendency of additional stopovers by congestion levels are observed, implying the impact of traffic congestion on additional stopover behaviors to some extent. The study results suggest the possibility of promoting additional stopovers in tourism areas for congestion avoidance by providing predicted near future traffic congestion and surrounding tourism information, which is beneficial to both tourism promotion and traffic congestion mitigation.

Real-Time Traffic Congestion Information from Tweets Using Supervised and Unsupervised Machine Learning Techniques

For many decades automated sensors, such as acoustic, optical, pneumatic, magnetic, inductive sensors and video-based image processing solutions were used for collecting data on traffic flow, speed, density, travel time etc. Using these data, the level of congestion is indirectly estimated. However, most of these sensors are costly and location-based. In addition, they cannot find the reason for congestion. To address these limitations, use of social media as a source of traffic information has been explored recently. Some of them, such as Twitter, are open source and popular throughout the world. Earlier studies that reported the use of Twitter feeds for traffic information are limited and used machine-learning techniques based on supervised learning, which needs labelled data that are difficult to obtain. Hence, this paper compares the unsupervised and supervised approaches to extract traffic-related tweets and develops a method to give the probability of level of congestion in real-time. The methods developed were applied to the tweets from Chennai city to extract the congestion information in real time, the results were validated through newspaper reports of heavy traffic congestion events. The obtained results showed a good correlation with the real congestion events.

Intelligent acquisition model of traffic congestion information in the vehicle networking environment based on multi-sensor fusion

Aiming at the problems of low bandwidth, poor anti-interference ability and low-detection accuracy of traditional multi-path coherent vehicle network model, an intelligent acquisition model of traffic congestion information in vehicle network environment based on multi-features is proposed. The model clusters the traffic congestion information in the vehicle network and uses the multi-sensor fusion identification method to mine the traffic flow. In the vehicle networking environment, the vehicle traffic congestion information is analysed by information fusion theory, cross-fusion, text information, location information, image, audio, video and other information-aware technologies, and the coherent matching filter detector is used to realise the detection of traffic congestion information. And data collection, combined with knowledge base and database construction, is used to achieve intelligent collection and storage of traffic congestion information. The simulation results show that the model has high traffic congestion information acquisition accuracy and good feature matching ability, improves the intelligent acquisition ability, and detects the traffic congestion information in the vehicle network environment, thus guiding traffic scheduling.

Traffic flow forecasting for city logistics: a literature review and evaluation

This article presents a thorough literature review and evaluation of road traffic forecasting methods. More specifically, the literature review concerns the study of scientific articles, in order to draw conclusions on the best-applied methods and future directions of their implementation in city logistics. The algorithms (methods), through which the traffic forecast is carried out, are categorised and analysed, focusing on their potential implementation in freight transportation systems. It is beyond dispute that the proper use of traffic congestion information can significantly improve public confidence in road networks and reduce traffic congestion as well as its harmful environmental and social impacts. This analysis and the knowledge gained will be used in an on-going research project in order to support the application of traffic forecasting algorithms in the functionality of a vehicle routing and scheduling information system. This review is a useful tool for academia's and practitioners who study the adoption of traffic forecasting algorithms in IT solutions in order to schedule deliveries and routes in city logistics environment effectively.

Traffic flow forecasting for city logistics: a literature review and evaluation

This article presents a thorough literature review and evaluation of road traffic forecasting methods. More specifically, the literature review concerns the study of scientific articles, in order to draw conclusions on the best-applied methods and future directions of their implementation in city logistics. The algorithms (methods), through which the traffic forecast is carried out, are categorised and analysed, focusing on their potential implementation in freight transportation systems. It is beyond dispute that the proper use of traffic congestion information can significantly improve public confidence in road networks and reduce traffic congestion as well as its harmful environmental and social impacts. This analysis and the knowledge gained will be used in an on-going research project in order to support the application of traffic forecasting algorithms in the functionality of a vehicle routing and scheduling information system. This review is a useful tool for academia's and practitioners who study the adoption of traffic forecasting algorithms in IT solutions in order to schedule deliveries and routes in city logistics environment effectively.

Intelligent acquisition model of traffic congestion information in the vehicle networking environment based on multi-sensor fusion

Intelligent acquisition model of traffic congestion information in the vehicle networking environment based on multi-sensor fusion

Evaluating the Impact of Real-Time Mobility and Travel Time Reliability Information on Truck Drivers’ Routing Decisions

This study represents the first research to investigate the impacts of two critical determinants—level of congestion and travel time reliability—on routing decisions with two groups of truck drivers having different levels of awareness of the real-time and the historical traffic conditions on available routes. The research analyzed 14,538 global positioning system devices recording trips on the I-495 crossing through Maryland, Virginia, and Washington, DC, and 2,166 trips in the Dallas area, to explore how truck drivers make routing decisions based on real-time travel time and reliability information by applying a binary logistic regression model. Researchers found that for truck drivers who are not familiar with the historical traffic and travel time conditions on available routes, real-time congestion information is a significant factor in their routing decision-making process, while travel time reliability is not a major consideration. For frequent truck drivers who are familiar with the historical traffic and travel time conditions on available routes, travel time reliability is a significant factor in their routing decision-making process, and traffic congestion information is not a significant factor. These results bring more accuracy to travel time prediction and provide valuable insights into traffic management and reliability performance measures. Moreover, this research provides statistical evidence proving the potential value of delivering travel time reliability information to drivers, traffic management agencies, and navigation map developers.