Let Trajectories Speak Out the Traffic Bottlenecks

Traffic bottlenecks are a set of road segments that have an unacceptable level of traffic caused by a poor balance between road capacity and traffic volume. A huge volume of trajectory data which captures realtime traffic conditions in road networks provides promising new opportunities to identify the traffic bottlenecks. In this paper, we define this problem as trajectory-driven traffic bottleneck identification : Given a road network R , a trajectory database T , find a representative set of seed edges of size K of traffic bottlenecks that influence the highest number of road segments not in the seed set. We show that this problem is NP-hard and propose a framework to find the traffic bottlenecks as follows. First, a traffic spread model is defined which represents changes in traffic volume for each road segment over time. Then, the traffic diffusion probability between two connected segments and the residual ratio of traffic volume for each segment can be computed using historical trajectory data. We then propose two different algorithmic approaches to solve the problem. The first one is a best-first algorithm BF , with an approximation ratio of 1-1/ e . To further accelerate the identification process in larger datasets, we also propose a sampling-based greedy algorithm SG . Finally, comprehensive experiments using three different datasets compare and contrast various solutions, and provide insights into important efficiency and effectiveness trade-offs among the respective methods.

Urban morphogenesis analysis based on geohistorical road data

Road networks result from a subtle balance between geographical coverage and rapid access to strategic points. An understanding of their structure is fundamental when it comes to evaluating and improving territorial accessibility. This study is designed to provide insight into the progressive structuring of territorial patterns by analyzing the evolution of road networks. Studying road network morphogenesis requires geohistorical data, provided here by historical maps from which earlier road networks can be digitized. A hypergraph is constructed from these networks by combining road segments into “ways” on the basis of a method for defining the continuity of road segments. Next, indicators are computed for these ways based on topological and geometrical features. The road patterns of three cities in the Burgundy Franche-Comte region of France (Dijon, Besançon, and Pontarlier) at three historical periods (the 18th, 19th, and twentieth centuries) are then analyzed. In this manner, their topological features and centrality characteristics can be compared from snapshots at different times and places. The innovative method proposed in this paper helps us to read features of the road patterns accurately and to make simple interpretations. It can be applied to any territory for which data is available. The results highlight the underlying structure of the three cities, reveal information about the history and the functioning of the networks, and give preliminary insights into the morphogenesis of those cities. Prospectively this work aims to identify the mechanisms that drive change in road networks. Detecting stability or variation in indicators over time can help in identifying similar behavior, despite geographic and cultural distances, as well as evolution mechanisms linked to specificities of each city. The study of road network morphogenesis can make a major contribution to understanding how road network structure affects accessibility and mobility.

Application and Evaluation of a Non-Accident-Based Approach to Road Safety Analysis Based on Infrastructure-Related Human Factors

Too often the identification of critical road sites is made by “accident-based” methods that consider the occurred accidents’ number. Nevertheless, such a procedure may encounter some difficulties when an agency does not have reliable and complete crash data at the site level (e.g., accidents contributing factors not clear or approximate accident location) or when crashes are underreported. Furthermore, relying on accident data means waiting for them to occur with the related consequences (possible deaths and injuries). A non-accident-based approach has been proposed by PIARC. This approach involves the application of the Human Factors Evaluation Tool (HFET), which is based on the principles of Human Factors (HF). The HFET can be applied to road segments by on-site inspections and provides a numerical performance measure named Human Factors Scores (HFS). This paper analyses which relationship exists between the results of the standard accident-based methods and those obtainable with HFET, based on the analysis of self-explaining and ergonomic features of the infrastructure. The study carried out for this purpose considered 23 km of two-way two-lane roads in Italy. A good correspondence was obtained, meaning that high risky road segments identified by the HFS correspond to road segments already burdened by a high number of accidents. The results demonstrated that the HFET allows for identifying of road segments requiring safety improvements even if accident data are unavailable. It allows for improving a proactive NSS, avoiding waiting for accidents to occur.

Survey and Design Consistency Evaluation in Two-Lane Rural Road Segments

The present research proposes a time and cost-effective methodology to survey and perform a design consistency evaluation in two-lane rural road segments. The implementation of the proposed methodology carried out in Central Greece and more particularly along the national road Volos-Karditsa, from the local community Mikrothives up to the entrance of the Volos municipal unit. The road survey methodology, the process of creating the terrain model as well as the cross-check between the designed road with the requirements included in the Greek Road Design Guidelines Manual-Chapter X, are analytically presented. Similar checks are also performed for the sight distance throughout the road segments aiming to enable the rehabilitation of existing rural roads and enhance their safety level. The design of the road was followed by the execution of an experiment with the participation of a motorcycle rider aiming at the recording of his trajectory throughout the road which was then compared with its geometry. The experiment carried out by exploiting an instrumented vehicle and GPS technology. Several conclusions were drawn regarding the encroachment of the centerline and the deviation from the theoretical trajectory in the middle of the travelled way. Subsequently, the proposed methodology provides a reliable and simple solution of surveying and evaluating a 2-lane rural road in safety terms.

Flyover Development Risk Analysis: Review of The Construction Phase Efforts to Minimize Environmental Impact

The increase of road segments are needed to overcome traffic congestion in Special Capital Region of Jakarta. Flyover is one of the efforts made to add road segments. The construction of flyovers will change the initial landscape and initial environmental tone. This change affects environmental, social, and economic conditions. All risks in construction activity must be managed to minimize their negative impact. Risks management starts with risk analysis by identification significant impact. This research aims to analyze the risks arising from the construction of flyovers. This analysis was carried out on the Becakayu flyover, which only began operating in 2017. Environmental risk is calculated based on parameters of opportunity, magnitude, level, frequency, and sensitivity of risks that may arise. Based on the results of the analysis, it was found that the construction of flyovers had a moderate risk to the environment during the construction phase. To minimize the risks that may arise, it is necessary to manage the risks that may arise through the construction process that meets the standards, the use of well-maintained equipment, the use of hazard signs, and the measurement of environmental quality during the construction phase.

The Influence Of Traffic Control Devices And Road Geometric Characteristics On Traffic Crushes Of Rular Two Lane Road

Traffic accidents worldwide are among the most alarming phenomena because they cost billions of dollars due to death rates and property damage. In Ethiopia, the accident fatality rate is becoming one of the most serious problems. Specifically, in rural highways where in there are problems with traffic control device enforcement and geometric deficiencies. Gedeo zone faces a similar problem that is considered a hot issue on-road crash. This study focused on the influence of traffic control devices and geometric characteristic related to road crashes. The data collection method was a purposive sampling technique considering both primary and secondary data collection system. Direct field observations were conducted, such as field survey and recording of the existing road geometric elements to figure out which geometric element contributory to traffic crashes. The data collected from the police traffic was categorized by clustering the road into different road segments composed of the same geometric characteristics. The severity of the accident analyzed and identified the hazardous road sections (black spot area). The relationships of accident crash established between the influence of traffic control access devices and geometric elements on the crash reduction at the identified accident-prone areas. Further, the study used ANN modeling through engineering software MATLAB to analyze the weight age of crashes on specified road segments concerning geometric road characteristics. Hence, the gradient carriageway width, super-elevation, cross slope, gradient, sight distance number of the horizontal curve, number of vertical curves, and AADT are the major factors for the occurrence of both fatal and injury at the blackspot segment along the rural highway.

Taxi Global Positioning System Data in Urban Road Network: A Methodology to Identify Key Road Clusters Based on Travel Speed–Traffic Volume Correlation

Urban traffic congestion is one of the urban diseases that needs to be solved urgently. Research has already found that a few road segments can significantly influence the overall operation of the road network. Traditional congestion mitigation strategies mainly focus on the topological structure and the transport performance of each single key road segment. However, the propagation characteristics of congestion indicate that the interaction between road segments and the correlation between travel speed and traffic volume should also be considered. The definition is proposed for “key road cluster” as a group of road segments with strong correlation and spatial compactness. A methodology is proposed to identify key road clusters in the network and understand the operating characteristics of key road clusters. Considering the correlation between travel speed and traffic volume, a unidirectional-weighted correlation network is constructed. The community detection algorithm is applied to partition road segments into key road clusters. Three indexes are used to evaluate and describe the characteristic of these road clusters, including sensitivity, importance, and IS. A case study is carried out using taxi GPS data of Shanghai, China, from May 1 to 17, 2019. A total of 44 key road clusters are identified in the road network. According to their spatial distribution patterns, these key road clusters can be classified into three types—along with network skeletons, around transportation hubs, and near bridges. The methodology unveils the mechanism of congestion formation and propagation, which can offer significant support for traffic management.

Adapting the WEPP hillslope model to predict unpaved road soil erosion in southern China

Process-based erosion models are efficient tools that can be used to predict where and when erosion occurs. On unpaved roads that have been recognized as important sediment sources, soil loss along road segments should be precisely predicted. This study was performed using the hillslope version of the Water Erosion Prediction Project (WEPP) to estimate soil loss from 20 typical road segments in the red soil region of South China. Terrestrial laser scanning (TLS)-measured soil losses were used to validate the model simulations. The results showed that the WEPP model could reasonably predict the total soil loss in relatively short (less than 100 m) and gentle (slope gradient lower than 10%) road segments. In contrast, the WEPP-simulated soil loss was underestimated for long or steep road segments. Detailed outputs along roads revealed that most of the peak soil loss rates could not be adequately calculated. The linear critical shear stress and the sediment equilibrium theory in the WEPP model for soil detachment simulation might be responsible for the underestimation. Additionally, the lack of upslope flow and the curved road tortuosity were found to be connected to the relatively low efficiency of the model outputs. Nevertheless, the WEPP simulation could accurately fit the trend of soil loss variation along road segments despite underestimation. Furthermore, the simulated results could provide a reliable prediction of the maximum soil loss positions. Therefore, the WEPP model could be adopted to evaluate the erosion risk of unpaved roads in the red soil region of South China.

Predicting Traffic Congestion Evolution: A Deep Meta Learning Approach

Many efforts are devoted to predicting congestion evolution using propagation patterns that are mined from historical traffic data. However, the prediction quality is limited to the intrinsic properties that are present in the mined patterns. In addition, these mined patterns frequently fail to sufficiently capture many realistic characteristics of true congestion evolution (e.g., asymmetric transitivity, local proximity). In this paper, we propose a representation learning framework to characterize and predict congestion evolution between any pair of road segments (connected via single or multiple paths). Specifically, we build dynamic attributed networks (DAN) to incorporate both dynamic and static impact factors while preserving dynamic topological structures. We propose a Deep Meta Learning Model (DMLM) for learning representations of road segments which support accurate prediction of congestion evolution. DMLM relies on matrix factorization techniques and meta-LSTM modules to exploit temporal correlations at multiple scales, and employ meta-Attention modules to merge heterogeneous features while learning the time-varying impacts of both dynamic and static features. Compared to all state-of-the-art methods, our framework achieves significantly better prediction performance on two congestion evolution behaviors (propagation and decay) when evaluated using real-world dataset.

A spatial decision support system for traffic accident prevention in different weather conditions

Natural conditions play an important role as determinants and cocreators of the spatiotemporal road traffic accident Hot Spot footprint; however, none of the modern commercial, or open-source, navigation systems currently provides it for the driver. Our findings, based on a spatiotemporal database recording 11 years of traffic accidents in Slovenia, proved that different weather conditions yield distinct spatial patterns of dangerous road segments. All potentially dangerous road segments were identified and incorporated into a mobile spatial decision support system (SLOCrashInfo), which raises awareness among drivers who are entering or leaving the predefined danger zones on the street network. It is expected that such systems could potentially increase road traffic safety in the future.