Average Travel Time Research Articles

Optimizing the geometry of transportation networks in the presence of congestion.

Urban transport systems are gaining in importance, as an increasing share of the global population lives in cities and mobility-based carbon emissions must be reduced to mitigate climate change and improve air quality and citizens' health. As a result, public transport systems are prone to congestion, raising the question of how to optimize them to cope with this challenge. In this paper, we analyze the optimal design of urban transport networks to minimize the average travel time in monocentric as well as in polycentric cities. We suggest an elementary model for congestion and introduce a numerical method to determine the optimal shape among a set of predefined geometries considering different models for the behavior of individual travelers. We map out the optimal shape of fundamental network geometries with a focus on the impact of congestion.

Real-time estimation of multi-class path travel times using multi-source traffic data

In practice, most of the intelligent transportation systems provide average travel times of all vehicles on selected paths in real time on a regular basis. However, path travel times of different vehicles could vary widely under different traffic conditions. There is a need to consider the differences in vehicle classes for path travel time estimation. This paper proposes a novel modeling framework that considers variance–covariance relationships between vehicle classes for real-time estimation of multi-class path travel times with use of multi-source traffic data collected from various types of sensors. The proposed methodology is examined with a case study of a selected urban expressway in Hong Kong with data obtained from multiple sources. The path travel time estimates by vehicle class are validated and the results demonstrate the merits and performance of the proposed framework.

Balancing Economic Sustainability with Densification: A Case Study of Dhaka

Economically sustainable urban residential neighborhoods are characterized by adequate provision of physical infrastructure including transport facilities and utility services. The built urban fabric of residential areas of Dhaka has been undergoing densification operation over the past decades without considering the physical infrastructure capacity of these areas in terms of accessibility and provision of transportation and utility services. This intervention eventually exerted pressure on the existing infrastructure and caused negative externalities like traffic congestion, pollution, and water clogging. Thus, this paper aims to investigate the impact of densification on residential areas of Dhaka through the lens of economic sustainability. Seven residential areas from Old and New Dhaka that underwent various degreesof densification were selected as the study areas. Primary data was collected through a random sampling household questionnaire survey, fieldwork, and informal qualitative interviews with the residents and officials. Various published literature, newspaper articles, plans, and reports from government archives, Capital Development Authority (RAJUK), Dhaka South City Corporation (DSCC), and Dhaka North City Corporation (DNCC) provided the secondary data. The analysis is carried out in two parts. In the firstpart the impact of densification on accessibility to transportation facilities and utility services is analyzed in terms of availability of the services, distance to the bus stops, average travel time, modal choice, and residents’ satisfaction level. The second part explores the relationship between density and aspects of economic sustainability through Pearson’s correlation test. The findings revealed that public transportation is more accessible in lower-density areas than the higher-density residential areas owing to the road network pattern. A significant service delivery gap except for water supply was observed regarding the provision and quality of gas, electricity, sewerage, and garbage disposal services across all the study areas. Overall, density was found to have a negative association with the accessibility to physical infrastructures indicating that high-density residential areas of Dhaka do not have increased access to public transport and utility services which is contrary to the expected benefits of high-density living. A comprehensive density planning with an integrated sustainable transport plan needs to be formulated where viable public transport like Bus Rapid Transit (BRTs) systems and waterways may mitigate the situation from further worsening.

Study on the optimal allocation of public service facilities from the perspective of living circle—A case study of Xiangyang High-tech Zone, China

The equitable allocation of public service facilities is directly related to the healthy development and socially just functioning of cities. Traditional location-allocation models mostly take travel distance and facility construction cost as the decision-making objectives, with relatively single optimization objectives, and are not sufficiently adaptable to reality. The introduction of the accessibility analysis and the concept of equalization of public services diversify the objectives of urban public service facility optimization decisions. The construction of the circle of life is based on residents' behavior and helps to improve its adaptability in the configuration of public services. This study evaluates the accessibility of eight types of public service facilities in Xiangyang High-tech Zone, China, from a Living Circle perspective, based on the Gaussian Two-step Floating Catchment Area (G2SFCA) method. We integrate the advantages of the Minimum Facility Point (MFP) model, Maximum Covering Location Problem (MCLP) model, and P-Median model to address the equity and efficiency issues in facility configuration, and seek the optimal layout scheme under the fairness objective. Results showed that after using the improved location-allocation models, the maximum travel time for residents was reduced from 76 ​min to 13 ​min, and the average travel time was reduced from 19 ​min to 8 ​min. Additionally, the coverage rate of the facilities increased from an average of 57% to 97%, and the spatial layout of facilities was more rational. The research results contributed to the study of spatial problems and spatial equity in facility allocation.

Urban road travel time prediction based on gated recurrent unit using internet data

AbstractTraffic congestion has been aggravated in many cities, which not only negatively affects the traffic efficiency, but also exacerbates the related social problems. Accurate prediction of urban road travel times plays a crucial role in assisting traffic management and alleviating the derived problems caused by traffic congestion. This study aims to propose an innovative Gated Recurrent Unit (GRU)‐based model for vehicle travel time prediction on urban road networks using the Internet vehicle travel time data. The Internet data used in the paper represents the real‐world average vehicle travel times on urban road networks, avoiding the privacy issue and the computational challenge in individual trajectory data. Before presenting the model, a data imputation method based on time series to reconstruct the missing data, and a time‐series data similarity evaluation method for road link classification are developed. The road‐category‐based model helps balance the computational efficiency and the prediction accuracy. Finally, the modelling framework is tested on a road network in Xuhui District, Shanghai. By comparing its performance with different models, it is concluded that the GRU‐based model considering road link categories is more efficient and more accurate in urban road travel time prediction.

Timetable synchronization of the last several trains at night in an urban rail transit network

To improve passenger accessibility and reduce the travel time cost at night, this paper aims to optimize the synchronization of the last several trains’ timetables on each line of an urban rail transit (URT) network. A space-time network is constructed to describe the train flow and passenger flow in the URT network, based on which an integer programming model is formulated. To effectively solve the proposed model, we decompose the problem into two levels and propose an iterative algorithm. In the upper level, an adaptive large neighbourhood search (ALNS) method is developed to generate new train timetables in the URT network, which are then evaluated by the passenger flow problem in the lower level, and the optimization-evaluation iteration continues until the termination conditions are met. The method and algorithm are applied to a large-scale instance using data for the Wuhan URT network at night, which involve 9 urban rail transit lines and over 119,000 passengers, and the results show that the number of inaccessible passengers is reduced by 27.53%, and the average travel time cost is reduced by 2.70%, compared with the original timetable. Then, the experimental results on a small-scale instance show that the proposed algorithm can find a near-optimal solution in a short time, which illustrates the effectiveness and efficiency of the ALNS method.

Spreading Dynamics of Capital Flow Transfer in Complex Financial Networks.

The financial system, a complex network, operates primarily through the exchange of capital, where the role of information is critical. This study utilizes the transfer entropy method to examine the strength and direction of information flow among different capital flow time series and investigate the community structure within the transfer networks. Moreover, the spreading dynamics of the capital flow transfer networks are observed, and the importance and traveling time of each node are explored. The results imply a dominant role for the food and drink industry within the Chinese market, with increased attention towards the computer industry starting in 2014. The community structure of the capital flow transfer networks significantly differs from those constructed from stock prices, with the main sector predominantly encompassing industry leaders favored by primary funds with robust capital flow connections. The average traveling time from sectors such as food and drink, coal, and utilities to other sectors is the shortest, and the dynamic flow between these sectors displays a significant role. These findings highlight that comprehension of information flow and community structure within the financial system can offer valuable insights into market dynamics and help to identify key sectors and companies.

Multiple intersections traffic signal control based on cooperative multi-agent reinforcement learning

For the multi-agent traffic signal controls, the traffic signal at each intersection is controlled by an independent agent. Since the control policy for each agent is dynamic, when the traffic scale is large, the adjustment of the agent's policy brings non-stationary effects over surrounding intersections, leading to the instability of the overall system. Therefore, there is the necessity to eliminate this non-stationarity effect to stabilize the multi-agent system. A collaborative multi-agent reinforcement learning method is proposed in this work to enable the system to overcome the instability problem through a collaborative mechanism. Decentralized learning with limited communication is used to reduce the communication latency between agents. The Shapley value reward function is applied to comprehensively calculate the contribution of each agent to avoid the influence of reward function coefficient variation, thereby reducing unstable factors. The Kullback-Leibler divergence is then used to distinguish the current and historical policies, and the loss function is optimized to eliminate the environmental non-stationarity. Experimental results demonstrate that the average travel time and its standard deviation are reduced by using the Shapley value reward function and optimized loss function, respectively, and this work provides an alternative for traffic signal controls on multiple intersections.

An Effective Resource Allocation Strategy for Three-Layer Networks

The unbalance of resource allocation often confines the traffic capacity of network. The limitation of network resources highlights the necessity of rational allocation of network resources. In this paper, a resource allocation strategy based on node degree is proposed for three-layer network with different speed physical layers. Through simulation comparison, the traffic capacity of proposed strategy is about 1.5 times that of the average allocation strategy, and the reduction rate of total load can reach more than 60%. In addition, assigning appropriate delivery capacity to nodes reduces the average traveling time. Finally, through the proposed load-related indicators, the traffic load distribution comparison can be intuitively obtained.

Cyber-physical system assisted platooning method using dynamic correlation of destination vectors in urban roads

Economic losses due to delays in traffic congestion is serious social problems. Platooning has recently been attracting attentions from many researchers to alleviate traffic jams, especially in highway. On highways, platooning can have positive effects, such as running at a constant speed with multiple vehicles which leads to fuel-efficient driving, reducing air resistance and so on. However, the impacts of platooning in urban roads have not been addressed in detail since traffic lights may break the platoons. In this paper, we propose a platooning method using L2 norm and cosine similarity to form platoon with highly similar routes. Also, we investigate the sorting method within a platoon according to each vehicle’s straightness to eliminate Head of Line blocking at intersections and improve throughput at intersections. We propose a Cyber-Physical System approach to control platoon collaboratively in urban roads. Computer simulation results confirmed that the proposed method shortens the average travel time by 34.31%. This paper also shows the validity of forming platoon based on destination vectors and sorting vehicles within a platoon.

FairLight: Fairness-Aware Autonomous Traffic Signal Control With Hierarchical Action Space

Although Reinforcement Learning (RL) approaches are promising in autonomous Traffic Signal Control (TSC), they often suffer from the unfairness problem that causes extremely long waiting time at intersections for partial vehicles. This is mainly because traditional RL methods focus on optimizing the overall traffic performance, while the fairness of individual vehicles is neglected. To address this problem, we propose a novel RL-based method named FairLight for the fair and efficient control of traffic with variable phase duration. Inspired by the concept of User Satisfaction Index (USI) proposed in the transportation field, we introduce a fairness index in the design of key RL elements, which specially considers the travel quality (e.g., fairness). Based on our proposed hierarchical action space method, FairLight can accurately allocate the duration of traffic lights for selected phases. Experimental results obtained from various well-known traffic benchmarks show that, compared with state-of-the-art RL-based TSC methods, FairLight can not only achieve better fairness performance, but also improve the control quality from the perspectives of the average travel time of vehicles and RL convergence speed.

Diffusion of connected and autonomous vehicles concerning mode choice, policy interventions and sustainability impacts: A system dynamics modelling study

Connected and autonomous vehicles (CAV) have seen a rapid development over the past decade. However, wide diffusion of high level CAVs is still decades to come, and will depend on many technological, policy and public acceptance factors. Merging a traditional Bass Diffusion Model with a discrete choice model in a system dynamics approach, this study modelled CAV diffusion from 2020 to 2070 in the UK, considering mode choices of CAV private car, CAV car/ride sharing and CAV bus, their possible impacts on road network performance and sustainability, and the feedback of these impacts to CAV diffusion. Results of this study suggest that without interventions CAV diffusion will start to increase rapidly from 2035, and reach market saturation of 98% in around 2057. CAV diffusion will lead to reductions in average travel time, average travel cost, carbon emission and traffic accident. Training campaign, which prepares the general public to be ready for CAVs, is more effective in accelerating CAV diffusion than marketing campaign, which mainly targets the innovators and early adopters. Promoting shared CAVs and CAV public transport can contribute to more sustainable and more affordable mobility with CAVs, although this may lead to smaller CAV market size in terms of CAV sale, and the market size may reduce at a higher rate than sustainability enhancement.

Analisis Hasil Asian Para Track Championships 2023 Berdasarkan Kelas Cycling dan Jarak Lintasan 1000 Meter

Indonesia is one of the contesting countries from Southeast Asia that will take part in the 2023 Asian Para Track Championships in Malaysia. Indonesian cyclists competing in this championship are athletes with special needs. The sport classification for athletes with special needs is influenced by performance disorders in various sports at different levels, according to the athlete's condition. The purpose of this research is to find out the fastest time and the time difference recorded in this competition according to the class and category. From the data obtained, there is a significant difference between the fastest arriving class and the slower class. Researchers took CYCLE 5 and CYCLE 2 data to find out the difference between the fastest and the slower classes. The difference in the average travel time between the two classes is ∆t = 14,363 seconds. The CYCLE 5 class gets an average arrival time at the finish line of 71,074 seconds or 1 minute 11,074 seconds in a 1000 meter track distance. In other words, this class is the fastest of the other classes. The CYCLE 2 class gets an average arrival time at the finish line of 85,437 seconds or 1 minute 25,437 seconds in a 1000 meter track distance. In other words, this class is slower than the other classes.

Real-time Road Network Optimization with Coordinated Reinforcement Learning

Dynamic road network optimization has been used for improving traffic flow in an infrequent and localized manner. The development of intelligent systems and technology provides an opportunity to improve the frequency and scale of dynamic road network optimization. However, such improvements are hindered by the high computational complexity of the existing algorithms that generate the optimization plans. We present a novel solution that integrates machine learning and road network optimization. Our solution consists of two complementary parts. The first part is an efficient algorithm that uses reinforcement learning to find the best road network configurations at real-time. The second part is a dynamic routing mechanism, which helps connected vehicles adapt to the change of the road network. Our extensive experimental results demonstrate that the proposed solution can substantially reduce the average travel time in a variety of scenarios, whilst being computationally efficient and hence applicable to real-life situations.

Traffic efficiency and fairness optimisation for autonomous intersection management based on reinforcement learning

Autonomous Intersection Management (AIM) for high-level Connected and Automated Vehicles (CAVs) has evolved from rule-based to optimisation-based policies. However, at congested major-minor intersections, optimising solely for efficiency can negatively impact vehicle fairness. This study addresses this issue by proposing a deep reinforcement learning approach that optimises both traffic efficiency and fairness for AIM. In the modelled multi-objective Markov decision process, traffic fairness is measured by the difference between the crossing order and the approaching order of CAVs, while traffic efficiency is measured by average travel time. With unknown preferences of the objectives, Bellman optimality equation is generalised to obtain the optimal policies over the space of all possible preferences during the iterative training process. The effectiveness of the proposed method is evaluated in a simulated real-world intersection and compared with three benchmark policies, including the fairest policy for AIM: first-come-first-served. The learned policies perform best in reducing overall average vehicle delay, and demonstrate outstanding performance in balancing traffic fairness and efficiency.

Offset Optimization Model for Signalized Intersections Considering the Optimal Location Planning of Bus Stops

Existing offset optimization methods for signalized intersections are mainly focused on regular traffic flow, which cannot accommodate cars and public transit (e.g., Bus Rapid Transit (BRT)) simultaneously. This study proposes a delay prediction model to formulate the signal delay of BRT at intersections. The relation among the green wave bandwidth, signal timing plans, speed of the BRT vehicles, distance between the intersections, and the offset is also modeled. A combinatorial optimization model is then established, which takes the location planning of BRT stops and the offset of intersections at both directions along the artery as the decision variables. The proposed model is programmed with Mathematical Programming Language (AMPL) and solved efficiently by the Gurobi solver. The proposed optimization method is compared with seven different methods. The results show that the average BRT travel time is reduced by at least 19% and the green wave bandwidth is increased by around 30.2%. The importance of considering location planning of BRT stops when optimizing the offset is thereby verified.

Coupling and coordinated development of traffic accessibility and regional tourism economy

Based on the weighted average travel time, tourism economic potential, tourism economic connections and other indicators, this paper analyses the impacts of high-speed rail (HSR) on the accessibility of regional transport and tourism economic connections and explores the synergistic effect of accessibility and the tourism economic development through the coupling coordination degree evaluation model. The results indicate that the space-time compression effect brought by HSR enhanced traffic accessibility and tourism economic connections in the Chengdu-Chongqing economic circle, but the improvement was spatially unbalanced. The improvement of transportation conditions has led to a trend towards centralization in the economic connections of tourism, resulting in the formation of the Chengdu-Deyang-Mianyang-Leshan HSR tourism economic belt. The coupling coordination level of tourism accessibility and tourism economic connections in the Chengdu-Chongqing economic circle presents a basic coordinated state. HSR has improved the lagging status of regional tourism economic development, and enhanced the coupling coordination degree between tourism accessibility and tourism economy of Chengdu, Chongqing, and Deyang. To promote the coordinated development of regional tourism, the construction of the high-speed rail network should be further improved, the efficiency of the spatial movement of tourism elements should be strengthened, and the core cities should play a leading role in the tourism economy of the peripheral cities.

Measuring modal accessibility gap using gridded population and network map platform data

Few studies have calculated the magnitude of the modal accessibility gap between public and private transportation (MAG) by taking into account both population characteristics and time-varying characteristics. To incorporate the aforementioned characteristics, this study computed MAG within each population grid using the anticipated travel time between two grids in real time. Moreover, a representative case study focuses on the MAG in the urban area of Xi'an during three time periods. Research results indicate that the average travel time for private transportation in the study area is significantly lower than that of public transportation. Further, the subway line has an obvious impact on improving MAG. In addition, the development of public transportation in the peripheral regions lags behind that of the city center, and the subway network is inadequately serviced. As a result of utilizing the MAG method presented in this paper, the problem related to urban transportation planning can be addressed by incorporating both the population and time-varying factors. At the end of the paper, the limitations and future works are discussed.

The Application of Image Processing to Determine Lift Occupancy

Abstract Lifts have become an essential device to move people up and down tall buildings every day. However, sometimes the lift still stops even though it is already fully occupied, either with people or objects, and is not able to take in more passengers. This makes the amount of time used to get to a floor longer due to all the unnecessary delays. As a result, the primary emphasis of this research endeavour is placed on the application of image processing techniques, namely those that make use of the tracking system that uses Kalman filter, to track moving people and objects, to determine the occupancy of a lift. Kalman filter is applied to accurately track and determine whether it is a person or an object that is located within the bounding boxes. If it is a person, an estimate of the amount of space that an average human occupies in a given environment is determined. In contrast, if it is not a human, then the usage of the polygon function will be incorporated to estimate the percentage of space that is occupied by the items. This will be done in order to figure out how much space the objects take up. Through the use of the proposed system, the occupancy of the lift is determined by analyzing still images taken from a video that was recorded by a camera located within the lift. As a consequence of this, the average travel time for a lift user can be reduced with the reduction of unnecessary stops while it is fully occupied.

Exploring the main and interaction effects of traffic flow characteristics, roadway design and weather conditions on the real-time crash risk for urban roads with mixed logit model

The present study aims at investigating the main and interaction effects of contributing factors from multiple risk sources (i.e. traffic flow characteristics, roadway design and weather conditions) on the real-time crash risk for urban roads. A mixed logit model is used to characterise heterogeneity induced by unobservable factors, and result shows that the mixed logit model achieves better goodness-of-fit than the binary logit model. It is found that the multiple risk sources such as roadway design (i.e. length of road segment, road hierarchy), traffic flow characteristics (i.e. average speed, average travel time, congestion level), and weather conditions (i.e. wind speed) have significant effects on the real-time crash risk. Moreover, interactions between the multiple risk sources such as roadway design and traffic flow characteristics (i.e. SD of speed and length of road segment, road hierarchy and average travel time), traffic flow characteristics and weather conditions (i.e. average travel time, temperature and wind speed), and roadway design and weather conditions (i.e. length of road segment and wind speed) are found to be significantly correlated to the real-time crash risk. Such findings can be potentially used for the development of real-time management measures that could mitigate the high-risk situations of urban roads.