scispace - formally typeset
Search or ask a question

Showing papers in "International Journal of Intelligent Transportation Systems Research in 2021"


Journal ArticleDOI
TL;DR: In this article, the authors investigated the impact of multi-class heavy duty vehicles (HDVs) on the speed and flow rates of each highway lane under platooning conditions and proposed recommendations to mitigate the adverse impacts of multiple-class HDVs on the highways to enhance the speed.
Abstract: Heavy-Duty Vehicles (HDVs) on highways are among the major passengers and freight traffic carriers that occupy any space available on the roadway. The movement of HDVs under the mixed traffic environment causes higher levels of interaction between vehicles due to their physical and operational characteristics. Besides, the HDVs operating at less than their desired speed on the highway lanes cause a mixed traffic platoon formation. The primary purpose of the study is to investigate the impact of multi-class HDVs on the speed and flow rates of each highway lane under platooning conditions. In this study, traffic data was collected using an Infra-Red (IR) sensor-based device at six highway sections in India. The simultaneous equations approach is used to model the traffic speeds for determining the Dynamic Passenger Car Unit (DPCU). The speed-flow plots are established for Median Lane (ML) and Kerb Lane (KL), a minute before the arrival of HDVs (state A) and a minute after the arrival of HDVs (state B) at the IR sensor detection point, to quantify the impacts of HDVs on the speed and traffic flow rate. The study findings reveal that the speed and flow in ML and KL reduce significantly due to the influence of multi-class HDVs in the general traffic mix. Also, the speed and flow rate in ML and KL decreased with an increase in the percentage of multi-class HDVs. However, this effect was found to be comparatively higher in the ML than that in the KL. Finally, this study sets out recommendations to mitigate the adverse impacts of multi-class HDVs on the highways to enhance the speed and flow rate.

15 citations


Journal ArticleDOI
TL;DR: The analysis shows that the proposed controller with its tuning technique outperforms the other classical ones like PID.
Abstract: In this paper, a comprehensive Model-Predictive-Control (MPC) controller that enables effective complex track maneuvering for Self-Driving Cars (SDC) is proposed. The paper presents the full design details and the implementation stages of the proposed SDC-MPC. The controller receives several input signals such as an accurate car position measurement from the localization module of the SDC measured in global map coordinates, the instantaneous vehicle speed, as well as, the reference trajectory from the path planner of the SDC. Then, the SDC-MPC generates a steering (angle) command to the SDC in addition to a throttle (speed/brake) command. The proposed cost function of the SDC-MPC (which is one of the main contributions of this paper) is very comprehensive and is composed of several terms. Each term has its own sub-objective that contributes to the overall optimization problem. The main goal is to find a solution that can satisfy the purposes of these terms according to their weights (contribution) in the combined objective (cost) function. Extensive simulation studies in complex tracks with many sharp turns have been carried out to evaluate the performance of the proposed controller at different speeds. The analysis shows that the proposed controller with its tuning technique outperforms the other classical ones like PID. The usefulness and the shortcomings of the proposed controller are also discussed in details.

14 citations


Journal ArticleDOI
TL;DR: An intelligent optimization algorithm of adaptive ant colony and particle swarm optimization is proposed that has fast convergence speed, strong optimization ability, and can obtain better optimization results and has some advantages in solving vehicle routing problem.
Abstract: Aiming at vehicle routing problem and combining the advantages of ant colony and particle swarm optimization, an intelligent optimization algorithm of adaptive ant colony and particle swarm optimization is proposed. Through the simulation of ant colony and bird swarm intelligence mechanism, the particle swarm algorithm and the ant colony algorithm heuristic strategy are combined, and different search strategies are used in different stages of the algorithm. The adaptive adjustment is adopted, and the feedback information is obtained by dynamic interaction with the environment, thus speeding up the convergence speed, improving the learning ability, avoiding the local optimum, getting the best solution and improving the efficiency. The simulation experiment shows that the algorithm has fast convergence speed, strong optimization ability, and can obtain better optimization results. It has some advantages in solving vehicle routing problem.

12 citations


Journal ArticleDOI
TL;DR: An architecture system consisting of a set of algorithms to manage electric vehicle charging plans in terms of minimizing journey time, including waiting and charging time at charging stations (CS).
Abstract: The fixed public charging stations (FCS) network is challenged by widespread of electric vehicle (EV) uses. Therefore, there is exploitation of the many parks spread over the territory of a smart city by means of mobile charging stations (MCS). That can be set up or moved anywhere as needed. This allows for the rapid expansion of the charging infrastructure. In this work, we propose an architecture system consisting of a set of algorithms to manage electric vehicle charging plans in terms of minimizing journey time, including waiting and charging time at charging stations (CS). Thus, During the CS selection decision, the system takes into consideration the amount of sufficient energy for the EV to reach the specified CS, the remaining amount of energy in stock if the selected CS is the MCS type, the CS Real-time status, and the first-come-first-served policy based on providing charge seats in CS. Moreover, the dynamically system regulates each FCS at its peak time of its MCS operation, ensuring a semi-permanent equilibrium in electrical grid usage and reducing congestion by changing the flow of vehicles that are directed towards FCSs for charging. The evaluation results demonstrate, in the context of the Helsinki City scenario, the effectiveness of the proposed system and algorithms, in terms of achieving the above-mentioned objectives.

11 citations


Journal ArticleDOI
TL;DR: In this article, a fuzzy countermeasure system is developed to improve train safety against known and unknown cyber-attacks on the railway line, which can reveal false positive and false negative warnings.
Abstract: With the advancement of modern rail transport systems, high-speed railways’ safety and reliability is improved enormously due to proper intelligent traffic management systems. The automatic train control and operating system receive the train location beacons and the railway line’s essential information through various channels, such as Balise wirelessly. However, this technology is vulnerable to cyber-physical attacks. This article aims to investigate the existing cyber attacks on Balise that can result a physical turmoil. Due to the limitations and constraints of the railway infrastructures, the attacks and failure detection methods are proposed based on machine learning. Also, a fuzzy countermeasure system is developed to improve train safety against known and unknown cyber-attacks. The simulation results show 92% accuracy in the proposed successful attacks detection system. Moreover, a small amount of false-positive and false-negative warnings can be also revealed employing the proposed scheme. The proposed method does not require change railway infrastructure.

10 citations


Journal ArticleDOI
TL;DR: The study proposes a novel approach to include average daily traffic (ADT) and average spot speed (AS) in the accident prediction model for a rural highway, offering a better estimate of accidents for a multilane divided rural highway.
Abstract: The aim of this study is to assess the safety of multi-lane rural highway in India. This paper shows the application of a generalized linear modeling technique for the analysis of road accidents on the Indian National Highway. Speed, traffic flow and road characteristics data on four-lane dived rural highway in Dahod are analyzed. The study proposes a novel approach to include average daily traffic (ADT) and average spot speed (AS) in the accident prediction model for a rural highway. The model has been developed for accidents per km as a dependent variable and significant variables such as Junction density, village settlement nearby, ADT, AS as independent variables. The findings from the model offer a better estimate of accidents for a multilane divided rural highway. Statistical Models cannot fully reflect the characteristics of each section due to the heterogeneous nature of road accidents, so the association rule mining technique has been used to identify accident spots as it can deal with the heterogeneous nature of accidents. Accident spots have been assessed by correlating various attributes to the severity of the accident (fatal, non-fatal). This research will help to improve road safety on rural highways.

9 citations


Journal ArticleDOI
TL;DR: It is suggested that adopting the Bayesian network framework with other computational intelligence approaches would have a positive impact towards achieving the Sustainable Development Goals in terms of road safety.
Abstract: Investigating the cost-implications of road traffic collision factors is an important endeavour that has a direct impact on the economy, transport policies, cities and nations around the world. A Bayesian network framework model was developed using real-life road traffic collision data and expert knowledge to assess the cost of road traffic collisions. Findings of this study suggest that the framework is a promising approach for assessing the cost-implications associated with road traffic collisions. Moreover, adopting this framework with other computational intelligence approaches would have a positive impact towards achieving the Sustainable Development Goals in terms of road safety.

8 citations


Journal ArticleDOI
TL;DR: A segment-based micro-level geospatial-based approach to find the interaction between the frequency of pedestrian crashes and roadside land uses in rural roads showed that residential, commercial, governmental, institutional, utility, and religious land uses have various decisive impacts on the increase of pedestrian crash frequency.
Abstract: Pedestrians are one of the most vulnerable road users that are prone to injury and death. Various factors have been incorporated into transportation systems in order to improve pedestrian safety in recent studies. The main objective of this study is to develop a segment-based micro-level geospatial-based approach to find the interaction between the frequency of pedestrian crashes and roadside land uses in rural roads. The proposed approach uses geospatial functions for extracting contributing factors and two different lengths of road segments as analysis units to reduce the randomness of the crash locations. These spatial factors are used to estimate the number of pedestrian crashes in each segment using four count-based regression models, including Poisson, negative binomial (NB) regression models, and their zero-inflated extensions. The latest four-year reporting crashes and land use data for a four-lane divided rural multilane in Guilan province, Iran, were tested to illustrate the models' accuracy and performance in the proposed approach. Modeling results highlighted the superiority of the Poisson regression model and its zero-inflated extension for two different strategies of segment length. Moreover, the results showed that residential, commercial, governmental, institutional, utility, and religious land uses have various decisive impacts on the increase of pedestrian crash frequency. This information could be used in long-term transportation systems planning, which would lead to an improvement in pedestrian safety levels.

7 citations


Journal ArticleDOI
TL;DR: For among passengers who remained active, regular commuters had similar travel patterns over the study period, whereas infrequent travelers significantly increased their use of the railway system.
Abstract: To better understand long-term patterns of human mobility, this study examines changes in travel behavior at the individual level based on yearly activity profiles using 3 years of longitudinal smart card data collected in Shizuoka, Japan. We first characterize spatiotemporal patterns of railway usage by k-means clustering, and then investigate variation in cluster membership with time. For among passengers who remained active, regular commuters had similar travel patterns over the study period, whereas infrequent travelers significantly increased their use of the railway system. The evolution of cluster assignment is analyzed and discussed.

7 citations


Journal ArticleDOI
TL;DR: There is an urgent need to develop an integrated analysis framework to evaluate the impact of these novel systems on road capacity and safety in function of different market penetration levels of AVs and CAVs.
Abstract: Smart roads, AV and CAV are emerging technologies that represent the new paradigm of mobility. To support the public and private road operators better prepare themselves to implement these technologies in their respective existing or planned infrastructures, there is an urgent need to develop an integrated analysis framework to evaluate the impact of these novel systems on road capacity and safety in function of different market penetration levels of AVs and CAVs. The research focuses on novel smart road geometric design and review criteria based on the performance of AVs and CAVs. The case study of one of the first planned smart roads in Italy has been analysed.

7 citations


Journal ArticleDOI
TL;DR: This work uses a long short-term memory (LSTM) network to analyze sequential sensor data to predict the car speed of the next time interval on the freeway and demonstrates that the proposed method for traffic speed prediction has achieved high accuracy.
Abstract: To successfully deploy an intelligent transportation system, it is essential to construct an effective method of traffic speed prediction. Recently, due to the advancements in sensor technology, traffic data have experienced explosive growth. It is therefore a challenge to construct an efficient model with highly accurate predictions. To improve the accuracy and the efficiency of short-term traffic predictions, we propose a prediction model based on deep learning approaches. We use a long short-term memory (LSTM) network to analyze sequential sensor data to predict the car speed of the next time interval on the freeway. Unlike the traditional model that only considers the changes in traffic speed which is used to derive the temporal and spatial features from the prediction road section, we mainly consider the features of the number of the most representative car types and the traffic speed variation of the front road segment that is ahead of the prediction road segment in addition to the number of cars, the road occupancy, and the traffic speed latency to successfully learn and capture the hidden patterns from the sensor data so as to improve the prediction accuracy. To the best of our knowledge, very few investigations have been conducted to consider the correlation between car speed and car type for a prediction model. Moreover, our extensive experiments demonstrate that the proposed method for traffic speed prediction has achieved high accuracy.

Journal ArticleDOI
TL;DR: The results of offline evaluations confirm that the proposed system can detect all target stop lines without any false detections, at a reasonable speed, to contribute to the realization of intelligent vehicles on community roads.
Abstract: In this study, a system for detecting stop lines on roads with damaged paint is developed to enhance a digital map localization system. Existing methods to detect stop lines focus on features such as straight edges and adequate size; however, these methods are not suitable to be used in rural areas because the paint of stop lines on the roads is damaged sometimes. In addition, lane marks, which are focused on by other existing methods, are often not present on actual roads in rural areas. Thus, to enable the detection of stop lines in the absence of conditions necessary for using the abovementioned features, we focus on pieces of faint features of damaged stop lines. First, we extract the positive and negative edges from an inverse perspective mapped image of the camera input by using a Sobel filter. Next, we verify the pairs of positive and negative edges from the trinarized edge image by confirming the width between both edges. Subsequently, we detect the candidates of stop lines by analyzing the distribution of the line segments extracted by the Hough transformation. In addition, we combine the data of the estimated driving distance and the result of detection of the preceding vehicles with the proposed system to prevent false detections in terms of bicycle crossing lanes and preceding vehicles. The damaged stop lines are detected eventually using these processes. To evaluate the performance of the proposed method, we collect driving data on actual public roads. The results of offline evaluations confirm that the proposed system can detect all target stop lines without any false detections, at a reasonable speed. The findings of this study are expected to contribute to the realization of intelligent vehicles on community roads.

Journal ArticleDOI
TL;DR: In this article, the authors examined travel behaviors in five major Vietnamese cities (Hanoi, Hai Phong, Da Nang, Ho Chi Minh City (HCMC), and Can Tho) and compared the impact of improved public transport on mode choice, emissions, and traffic safety.
Abstract: Motorcycles dominate current transport activities in Vietnamese cities; however, historical data show that bikes and public transport were popular as recently as 30 years ago. Because the transport infrastructure in Vietnamese cities makes it unsafe for cycling and inconvenient for public transport, many cyclists and public transport users switch to private motorized vehicles, particularly motorcycles, as soon as they can afford to make the change. The preference for motorcycles in Vietnamese cities has resulted in an increased risk of road traffic accidents and a degradation of air quality. Reducing the share of motorcycles on Vietnamese roads by improving public transport would be expected not only to improve public safety but also to have a positive impact on the environment and public health. However, efforts to improve the public transport have not yet been properly integrated into the local government system in every city. As the result, each city has different outcomes in mitigating the motorcycle-related challenges. This study examines travel behaviors in five major Vietnamese cities—Hanoi, Hai Phong, Da Nang, Ho Chi Minh City (HCMC), and Can Tho—and compares the impact of improved public transport on mode choice, emissions, and traffic safety. It is found that improving public transport would result in an 21.11 percent reduction in transport emissions by 2030 in Hanoi, as well as reductions of 12.5 percent in Hai Phong, 17.37 percent in Da Nang, 9.75 percent in HCMC, and 15.21 percent in Can Tho. The differences in these percentages are due to the heterogeneous modal shifts among cities. The provision of improved public transport is also shown to reduce the risk of road traffic accidents. The risk of a traffic fatality in Hanoi decreases by 49.6 percent, while in Hai Phong, the reduction is 43.8 percent; the risk in Can Tho, Da Nang and HCMC decreases by 18.7 percent, 19.8 percent, and 26.3 percent, respectively. As public transport investment is beginning to be adapted to the city context, our results indicate that investment capital on improving the public transport system would partly contribute on reducing emissions and traffic accidents in Vietnamese cities.

Journal ArticleDOI
TL;DR: In this article, an improved path planning algorithm based on RRT algorithm is presented, where random points are generated using the circular sampling strategy and an extended random point rule based on cost function is designed to filter random points, and the B-spline curve is used to simplify and smooth the path.
Abstract: Recently, the path planning has become one of the key research hot issues in the field of autonomous vehicles, which has attracted the attention of more and more related researchers. When RRT (Rapidly-exploring Random Tree) algorithm is used for path planning in complex environment with a large number of random obstacles, the obtained path is twist and the algorithm cannot converge quickly, which cannot meet the requirements of autonomous vehicles’ path planning. This paper presents an improved path planning algorithm based on RRT algorithm. Firstly, random points are generated using the circular sampling strategy, which ensures the randomness of the original RRT algorithm and improves the sampling efficiency. Secondly, an extended random point rule based on cost function is designed to filter random points. Then consider the vehicle corner range when choosing the adjacent points, select the appropriate adjacent points. Finally, the B-spline curve is used to simplify and smooth the path. The experimental results show that the quality of the path planned by the improved RRT algorithm in this paper is significantly improved compared with the RRT algorithm and the B-RRT (Bidirectional RRT) algorithm. This can be seen from the four aspects of the time required to plan the path, mean curvature, mean square deviation of curvature and path length. Compared with the RRT algorithm, they are reduced by 55.3 %, 68.78 %, 55.41 % and 19.5 %; compared with the B-RRT algorithm, they are reduced by 29.5 %, 64.02 %, 39.51 % and 11.25 %. The algorithm will make the planned paths more suitable for autonomous vehicles to follow.

Journal ArticleDOI
TL;DR: The results indicated that the system that expressed the approach situation of other vehicles using color information improved the ease of understanding the approach situations.
Abstract: It is an essential issue to avoid traffic accidents at unsignalized intersections. A driver assistance system was proposed to assist drivers by presenting the approach information of other vehicles through peripheral vision with color information. Actual vehicle experiments with ten participants were performed to validate the effectiveness of the system with the analysis of driver behaviors and subjective evaluations. The results indicated that the system that expressed the approach situation of other vehicles using color information improved the ease of understanding the approach situation. Meanwhile, the total observing time of the display and the number of times of viewing the display were successfully reduced, and the risk of collision with other vehicles was low when the information was provided through the peripheral vision.

Journal ArticleDOI
TL;DR: This work proposes a BSD model that objects are detected in consecutive time intervals in the BSD system, and illustrates that the multi-sensor fusion detection accuracy in theBSD system is augmented compared to a single sensor B SD system.
Abstract: Sensors are the quintessential part of Blind Spot Detection (BSD) systems, which have a profound effect on the performance of the system. Every sensor has its unique deficiencies that can deteriorate the performance of the system under grievous circumstances. Hence, making vital tasks in BSD such as object detection arduous. Indeed, previous studies have demonstrated that data fusion techniques can diminish the adverse effects of sensors and improve detection accuracy in the BSD system. One of the main advantages of data fusion is to improve detection accuracy and reduce the processing time by multiple sensors cooperation. We propose a BSD model that objects are detected in consecutive time intervals in the BSD system. Then, association techniques are employed for multi-sensor fusion since all sensors data are not ordinarily ready for fusion simultaneously. It should be noted that the orthodox approach in data association techniques in BSD often includes a global nearest neighbor, joint probabilistic data association, and multiple hypothesis tests. We simulate and compare these techniques by tracking multiple targets and multi-sensor fusion using virtual data in MATLAB. Furthermore, we illustrate that our multi-sensor fusion detection accuracy in the BSD system is augmented compared to a single sensor BSD system.

Journal ArticleDOI
TL;DR: This paper proposes a method for predicting the PDR with consideration of packet collisions, including the influence of hidden nodes, by using the positions and number of vehicles.
Abstract: Recently, vehicle-to-vehicle communication has been envisaged to be one of the technologies for realizing highly safe connected and automated driving. One of the approaches for predicting the radio environment is the use of a measurement-based spectrum database, which stores various pieces of information on the radio environment of data received and collected by vehicles; however, prediction of an accurate packet delivery ratio (PDR) with consideration of packet collisions is difficult if the vehicle density changes after the generation of PDR maps. This paper proposes a method for predicting the PDR with consideration of packet collisions, including the influence of hidden nodes, by using the positions and number of vehicles.

Journal ArticleDOI
TL;DR: A new SA estimation model considering driving-relevant objects and the relationship between parameters was developed and it was found that unscheduled TO led to maneuver error and glance behavior differed from individuals.
Abstract: In semi-autonomous vehicles (SAE level 3) that requires drivers to takeover (TO) the control in critical situations, a system needs to judge if the driver have enough situational awareness (SA) for manual driving. We previously developed a SA estimation system that only used driver’s glance data. For deeper understanding of driver’s SA, the system needs to evaluate the relevancy between driver’s glance and surrounding vehicle and obstacles. In this study, we thus developed a new SA estimation model considering driving-relevant objects and investigated the relationship between parameters. We performed TO experiments in a driving simulator to observe driver’s behavior in different position of surrounding vehicles and TO performance such as the smoothness of steering control. We adopted support vector machine to classify obtained dataset into safe and dangerous TO, and the result showed 83% accuracy in leave-one-out cross validation. We found that unscheduled TO led to maneuver error and glance behavior differed from individuals.

Journal ArticleDOI
TL;DR: In this paper, the authors used Long Short Term Memory (LSTM) with Levenberg-Marquardt (LM) algorithm to predict the rear end collision risk with optimized weight by combining Long Short-Term Memory (LSM) and Backpropagation Neural Network (BNN).
Abstract: The Almost 1.3 million casualties are reported round a calendar year due to road accidents. Advanced collision avoidance systems play major role in predicting the collision risk to avoid accidents. The existing deep learning algorithms are unable to predict the crash risk efficiently. In the existing system, Long Short Term Memory algorithm is used to predict the crash risk where weights are not optimized. The objective is to predict the rear end collision risk with optimized weight by combining Long Short Term Memory(LSTM) with Levenberg–Marquardt (LM) algorithms. The proposed algorithm predicts the collision risk considering vehicle, driver related factors, and temporal dependencies. Next Generation Simulation Project (NGSIM) dataset is used to evaluate the proposed model. The performance of the proposed system is compared with the performance of Long Short Term Memory and Back Propagation Neural Network. 95.6% of accuracy is achieved by LM-LSTM based Time series Deep Network Model. The prediction accuracy has been improved considerably than the existing algorithms. There is the drastic improvement in minimization of false alarm and missed alarm rate. The main advantage of the proposed system is that it will present warning at the time of high collision risk and it helps drivers to prevent from accident.

Journal ArticleDOI
TL;DR: The staggered conservative scheme applied on a staggered grid was implemented to solve the second-order Payne-Whitham equation and the shape and propagation speed of numerical jamitons are shown to confirm the analytical formulas.
Abstract: Traffic jams that appear without distinguishable reason is called phantom traffic jam. To study this phenomenon, macroscopic modelling using the second-order Payne-Whitham equation was adopted. In this article, the staggered conservative scheme applied on a staggered grid was implemented to solve the equation. Using this scheme, different behavior of a perturbed equilibrium solution was simulated; it might either decay or grow, depending on the critical threshold parameter. When unstable, a small perturbation was amplified into a local peak of high traffic density. This type of traveling wave is called a jamiton. On a circular road of a certain length and with a fixed number of vehicles, the growing process of these traveling jamiton waves was simulated. The shape and propagation speed of these numerical jamitons are shown to confirm the analytical formulas. A good understanding of this phenomenon may support decision-makers and engineers to determine the judicious selection of speed limits of a certain road section.

Journal ArticleDOI
TL;DR: The results showed that safe driving skills are more affected by occipital lobe volume than the conventional cognitive tests such as MMSE and FAB.
Abstract: This study analyzed the impact of the health condition of elderly drivers on their driving behavior. We obtained drive recorder data and health check data including cognitive function and magnetic resonance imaging data from drivers older than 70 years of age and living in the Chugei area in Kochi Prefecture, Japan, and performed discriminant analysis. The results showed that safe driving skills are more affected by occipital lobe volume than the conventional cognitive tests such as MMSE and FAB.

Journal ArticleDOI
TL;DR: The performance of the proposed Advanced Time-Space Discterization (AdTSD) method was evaluated with real field data and compared with existing approaches and results show that AdTSD approach was able to perform better than historical average approach with an advantage up to 11% and 5% compared to Base Time Space Discretization (B TSD) approach.
Abstract: Travel time is a variable that varies over both time and space. Hence, an ideal formulation should be able to capture its evolution over time and space. A mathematical representation capturing such variations was formulated from first principles, using the concept of conservation of vehicles. The availability of position and speed data obtained from GPS enabled buses provide motivation to rewrite the conservation equation in terms of speed alone. As the number of vehicles is discrete, the speed-based equation was discretized using Godunov scheme and used in the prediction scheme that was based on the Kalman filter. With a limited fleet size having an average headway of 30 min, availability of travel time data at small interval that satisfy the requirement of stability of numerical solution possess a big challenge. To address this issue, a continuous speed fill matrix spatially and temporally was developed with the help of historic data and used in this study. The performance of the proposed Advanced Time-Space Discterization (AdTSD) method was evaluated with real field data and compared with existing approaches. Results show that AdTSD approach was able to perform better than historical average approach with an advantage up to 11% and 5% compared to Base Time Space Discretization (BTSD) approach. Also, from the results it was observed that the maximum deviation in prediction was in the range of 2–3 min when it is predicted 10 km ahead and the error is close to zero when it is predicted a section ahead i.e. when the bus is close to a bus stop, indicating that the prediction accuracy achieved is suitable for real field implementation.

Journal ArticleDOI
TL;DR: The proposed Density Based Coordinated Vehicle Rerouting, coined as “DB-Corouting” algorithm is simulated through “SUMO’ and “Open Street Map” and the necessary finding ensures the effectiveness of the proposed solution in terms of selected metrics.
Abstract: Congestion control is a widely accepted domain in Intelligent Transportation System. Two approaches are commonly used to address the issue: either by controlling the traffic signals or by re-routing the vehicles in a congested state. However, the objective is to minimize the average travel time of the vehicles in a given road scenario. Choosing shortest path could be a solution. But the vehicles, following the shortest path, may face congestion if the decision is done in an un-coordinated manner. This could be due to non-inclusion of crucial decision parameter(s) and lack of cooperative decision on the decisive parameters of the concerned traffic scenario. There are efforts to include the density of the road segments within decision variables. The novelty of the proposed solution is to address the adaptive nature of the density parameter and considers effectively in the solution proposal. The solution considers the effect of density in a nearby road segment is more than the rare one. The introduction of the adaptive nature of this decision variable models the real road network more accurately and subsequent solution is more effective. Exhaustive experimentation has been done, considering various use cases. The proposed Density Based Coordinated Vehicle Rerouting, coined as “DB-Corouting” algorithm is simulated through “SUMO” and “Open Street Map” and the necessary finding ensures the effectiveness of the proposed solution in terms of selected metrics such as average traveling time, average waiting time, Traffic satisfaction Index etc.. The proposed solution outperforms the comparable solutions in terms of the selected metrics and always offers an efficient solution irrespective of traffic distribution.

Journal ArticleDOI
TL;DR: The improved neural network model is established by applying the improved convolutional neural network (CNN) algorithm to the license plate recognition system and based on the improved activation function, and the relevant experimental results are obtained.
Abstract: With the continuous development of social economy, private cars have become more and more, and the traffic pressure is also increasing. To more accurately recognize vehicles violating traffic rules, the problem of recognition and optimization of license plate targets has become an urgent task with certain practical significance and guiding significance. In this paper, the license plate recognition (LPR) system is taken as the main research object, which is improved and optimized. Firstly, an improved neural network model is established by applying the improved convolutional neural network (CNN) algorithm to the license plate recognition system and based on the improved activation function, and the relevant experimental results are obtained; meanwhile compared with the traditional CNN model, the corresponding experimental results are obtained; finally, the experimental conclusions are obtained, i.e., the LPR system using improved CNN algorithm has better performance in recognizing license plate target and can more accurately recognize licence plates which are shielded. Therefore, the improved neural network model has great development potential in the application of the LPR system.

Journal ArticleDOI
TL;DR: The output of this paper indicate that the short action times increase the traffic control system performances despite more yellow signal duration, and results clearly shows that proposed method decreases the delay time.
Abstract: Adaptive traffic signal control is the control technique that adjusts the signal times according to traffic conditions and manages the traffic flow. Reinforcement learning is one of the best algorithms used for adaptive traffic signal controllers. Despite many successful studies about Reinforcement Learning based traffic control, there remains uncertainty about what the best actions to actualize adaptive traffic signal control. This paper seeks to understand the performance differences in different action durations for adaptive traffic management. Deep Q-Learning has been applied to a traffic environment for adaptive learning. This study evaluates five different action durations. Also, this study proposes a novel approach to the Deep Q-Learning based adaptive traffic control system for determine the best action. Our approach does not just aim to minimize delay time by waiting time during the red-light signal also aims to decrease delay time caused by vehicles slowing down when approaching the intersection and caused by the required time to accelerate after the green light signal. Thus the proposed strategy uses not just information of intersection also uses the data of adjacent intersection as an input. The performances of these methods are evaluated in real-time through the Simulation of Urban Mobility traffic simulator. The output of this paper indicate that the short action times increase the traffic control system performances despite more yellow signal duration. The results clearly shows that proposed method decreases the delay time.

Journal ArticleDOI
TL;DR: In this article, a lane-level vehicle counting system based on V2X communications and centimeter-level positioning technologies is proposed for traffic survey of ITS at a range of urban intersections.
Abstract: Accurate vehicles counting for all-weather in cities are an important part of traffic management in the application of Intelligent Transportation Systems (ITS). Vehicle counting is currently collected with computer vision and sensor network methods. However, these methods require expensive hardware to achieve real-time and anti-interference capability, and do not provide lane-level vehicle information for ITS traffic management. This paper presents a lane-level vehicle counting system that is based on V2X communications and centimeter-level positioning technologies. This system can be used to traffic survey of ITS at a range of urban intersections. For realizing lane-level counting, a lane determination method is designed with on-board units (OBUs) in this paper. The lane is identified by matching the vehicle positioning information with road information from the roadside unit (RSU). The RSU collects the vehicle counting information from OBUs in different instances. The counting information includes the vehicle location data, the vehicle status data, and the vehicle number of each lane in the range of intersections. Verification and analysis were performed by a hardware-in-the-loop simulation platform. The results showed an average vehicle counting accuracy rate (99.60%). The system enabled the collection of real-time statistics with low-power consumption and low latency, providing accurate data to ITS.

Journal ArticleDOI
TL;DR: It was observed that the driver’s reaction time could be significantly reduced when the right-turn timing assistance was provided with haptic and auditory interfaces alone or the combinations of haptic, auditory and visual interfaces, compared to the condition without assistance.
Abstract: Several driver assistance systems have been proposed to assist drivers to avoid collisions at intersections, by informing drivers about the existence of oncoming vehicles. However, drivers still need to judge the right-turn timing by themselves. This study proposed a right-turn timing assistance system. Different human machine interfaces of the system, including haptic, visual and auditory methods, were evaluated by analyzing the influences on driver behaviors in actual vehicle experiments. It was observed that the driver’s reaction time could be significantly reduced when the right-turn timing assistance was provided with haptic and auditory interfaces alone or the combinations of haptic, auditory and visual interfaces, compared to the condition without assistance. The meaning of right-turn timing assistance was significant easier for drivers to understand when it was presented with visual interface than auditory interface. Meanwhile, the post-encroachment time value was not smaller than 5 s when the assistance was presented with the haptic, visual and auditory interfaces together, which indicated a small risk of collision with the oncoming vehicles.

Journal ArticleDOI
TL;DR: Wang et al. as discussed by the authors proposed a data-driven optimization framework by integrating the non-parametric learning algorithm and two-stage stochastic programming modeling technique to address the one-way station-based car-sharing relocation problem.
Abstract: To reduce the vehicle relocation rate considering relieving disequilibrium of the supply-demand ratios across regions for car-sharing systems, in this paper, we propose a data-driven optimization framework by integrating the non-parametric learning algorithm and two-stage stochastic programming modeling technique to address the one-way station-based car-sharing relocation problem. In contrast with the most existing work that deals with demand uncertainty using predefined probability distributions, the learning-based framework is capable of handling demand uncertainty by learning the intrinsic pattern from large-scale historical data and computing high quality solutions. To validate the performance of our proposed approach, we conduct a group of numerical experiments based on New York taxicab trip record data set. The experimental results show that our proposed data-driven approach outperforms the parametric approaches and deterministic model in terms of business profit, relocation rate, and value of stochastic solution (VSS). Most significantly, compared with the deterministic approach, the vehicle relocation rates are reduced by approximate 80%, 70% and 40% under small fleet size, medium fleet size and large fleet size, respectively. In addition, the VSS of our approach is more than 3 times higher than the one of Poisson distribution by average.

Journal ArticleDOI
TL;DR: In this paper, the authors investigated the impact of familiarity and complexity on the time to make an action decision during a takeover task in a highly automated driving scenario and found that the subjective complexity is a mediator variable between objective complexity/familiarity and the decision time.
Abstract: This paper shows, how objective complexity and familiarity impact the subjective complexity and the time to make an action decision during the takeover task in a highly automated driving scenario. In the next generation of highly automated driving the driver remains as fallback and has to take over the driving task whenever the system reaches a limit. It is thus highly important to develop an assistance system that supports the individual driver based on information about the drivers’ current cognitive state. The impact of familiarity and complexity (objective and subjective) on the time to make an action decision during a takeover is investigated. To produce replicable driving scenarios and manipulate the independent variables situation familiarity and objective complexity, a driving simulator is used. Results show that the familiarity with a traffic situation as well as the objective complexity of the environment significantly influence the subjective complexity and the time to make an action decision. Furthermore, it is shown that the subjective complexity is a mediator variable between objective complexity/familiarity and the time to make an action decision. Complexity and familiarity are thus important parameters that have to be considered in the development of highly automated driving systems. Based on the presented mediation effect, the opportunity of gathering the drivers’ subjective complexity and adapting cognitive assistance systems accordingly is opened up. The results of this study provide a solid basis that enables an individualization of the takeover by implementing useful cognitive modeling to individualize cognitive assistance systems for highly automated driving.

Journal ArticleDOI
TL;DR: This paper introduces Huangsha six import signal free roundabout in Dianjiang County of Chongqing as the research case, takes the traffic delay and queue length as the evaluation index, and two new optimization methods are proposed on the basis of the original methods, namely improved the signalization roundabout and the signalized intersection.
Abstract: The research on the organization of intersections has always been the key and difficult point of road optimization, especially for multi-leg intersections. Since the traffic flow direction and the number of conflict points of multi-leg intersection are more than that of ordinary intersection, the difficulty of organization and optimization increases accordingly. At present, the research on multi-leg intersections is not much or deep enough at home and abroad. In general, it is transformed into a roundabout when the traffic volume is small, and the signal lamp is set with the increase of traffic volume. However, the signalized roundabout is not applicable when the traffic flow at the signal roundabout increases to a certain extent. Therefore, this paper introduces Huangsha six import signal free roundabout in Dianjiang County of Chongqing as the research case, takes the traffic delay and queue length as the evaluation index, and two new optimization methods are proposed on the basis of the original methods, namely improved the signalized roundabout and the signalized intersection. To assess the feasibility of these methods, VISSIM is used for simulation comparison. The simulation results show that compared with the current traffic situation, the average delay time of vehicles in the signalized intersection optimization method is reduced by 9.3 s, the average queue length decreased by 3.7 m, and its indicators are better than the signalized roundabout. Therefore, the method of signalized intersection not only provides a good mirror for the reconstruction of multi-leg intersections, but also offers relevant theoretical and practical exploration.