Highway Data Research Articles

Predicting freeway non-recurring congestion via a spatio-temporal deep learning approach

Freeway unexpected events, such as car crashes, result in non-recurring congestion, which does not follow repetitive patterns in space and/or time and increases the challenge of freeway management. Existing prediction approaches of Freeway Non-recurring Congestion (FNC) are either qualitative with information loss or single-step quantitative for a short period. To address these limitations, this paper develops a quantitative, interpretability-enhanced, and spatial-temporal approach using a 2-Encoder-Decoder Model with an Attention Layer (Att-2ED) for FNC prediction. The model leverages Long Short-Term Memory (LSTM) and Multilayer Perceptron (MLP) as two encoders to process time-series speed profiles and static crash features independently. It also employs an LSTM-based decoder to generate a spatio-temporal sequence output and an attention mechanism to prioritise the weights of input sequences at each time step. The model has been trained and tested using real-world freeway data. The proposed model demonstrates superior performance in predicting traffic conditions across both spatial and temporal dimensions compared to existing benchmarks, achieving a Mean Absolute Error (MAE) of 3.74 for 15-minute-ahead predictions. Its effectiveness is further underscored through a comparative analysis of prediction accuracy across various congestion levels and crash severities. For instance, the MAE ranges from 2.77 to 7.00 for severe crashes and from 2.68 to 6.47 for peak-hour crashes, with prediction horizons spanning from 5 min to 60 min ahead. Moreover, the attention mechanisms incorporated in the model provide interpretability-enhanced predictions, highlighting the significance of the last 10-min input in the prediction.

Estimating the Expected Change in Safety for a Potential Application of Three Intelligent Transportation System Treatments

This paper documents and illustrates a practice-ready procedure for estimating changes in crash frequency for specific application circumstances for three intelligent transportation system treatments—Closed Circuit Television Cameras (CCTV), Dynamic Message Signs (DMS), and Road Weather Information Systems (RWIS). The procedure will allow an agency to directly evaluate the change in safety that may be associated with a contemplated treatment. In effect, the approach mimics the application of a Crash Modification Function (CMFunction) in that each potential application will, in principle, have its own Crash Modification Factor (CMF). The procedure uses an empirical Bayes framework with safety performance functions (SPFs) for treatment and non-treatment reference sites. The paper also presents those SPFs, which were developed from Pennsylvania freeway data. In principle, this cross-sectional approach can be applied, as it has been, for other safety treatments where safety effects vary with application circumstance and where that variability cannot be captured with conventional before–after studies.

Koopman theory meets graph convolutional network: Learning the complex dynamics of non-stationary highway traffic flow for spatiotemporal prediction

Reliable and accurate traffic flow prediction is crucial for the construction and operation of smart highways, supporting scientific traffic management and planning. However, accurately predicting spatiotemporal traffic flow in non-stationary and unprecedented traffic patterns scenarios, such as holidays and adverse weather conditions, remains a challenging task. Considering that (1) Koopman theory effectively captures the underlying time-variant dynamics of the non-stationary temporal sequence (2) Graph convolutional network (GCN) effectively extracts complex spatial dependencies, combining the strengths of both is a promising solution. Therefore, this paper proposes a spatiotemporal prediction network that integrates Koopman theory and GCN, named KoopGCN, for predicting non-stationary and inexperienced highway traffic flow. KoopGCN decomposes the input into time-invariant and time-variant components based on Fast Fourier Transform. The dual engine block consisting of KoopGCN InvarEngine and KoopGCN VarEngine is designed to predict two types of components separately. And the dual engine block also passes the residual to the next block for modeling. The experiment is conducted on real monitored highway data in Ningde City, Fujian Province, China. The results indicate that even if there is a significant distribution difference between the training and testing sets, KoopGCN can achieve accurate prediction, significantly outperforms state-of-the-art baselines.

Arterial highways of the foot of the American raccoon (Procyon lotor)

The vascular system is one of the integrating systems of the human and animal body. The course and branching of the vessels of various areas of the body follows general patterns. However, the variability of the vascular bed is quite high even within a single species of animal. The lack of data on both the topography and the peculiarities of arterial branching makes it difficult to carry out diagnostic and therapeutic manipulations. In addition, the data obtained during the study significantly enrich the available information on the comparative anatomy of the vascular bed. The purpose of the study is to study the main arterial arteries of the American raccoon foot area, to give them a morphometric characteristic. The research was carried out on 4 corpses of an American raccoon, delivered to the Department of Animal Anatomy of the St. Petersburg State University of Veterinary Medicine from veterinary clinics. Classical methods were chosen as research methods: fine anatomical dissection, morphometry, photographing and vasorentgenography. During the study, it was found that two arterial highways are distinguished on the foot of the American raccoon. The dorsal trunk is represented by the dorsal artery of the foot, the plantar trunk is represented by the middle plantar artery. The dorsal artery of the foot passes into the arc artery – the first anastomosis that unites the vessels of the two highways. The middle plantar artery gives rise to the second and third plantar metatarsal arteries and participates in the formation of a deep plantar arch, which is the second major anastomosis of the foot area. Axial and non-axial finger arteries also form collateral blood flow. Analyzing the obtained morphometric data of arterial highways, it follows to conclude that the plantar surface highways have the largest diameter. Thus, the diameter of the middle plantar artery is 1.72 times higher than the same parameter of the dorsal artery of the foot. The largest total diameter is characteristic of the arteries located in the metatarsal region, the smallest in the area of the metatarsal.

Innovative Energy Approach for Design and Sizing of Electric Vehicle Charging Infrastructure

In Italy, the availability of service areas (SAs) equipped with charging stations (CSs) for electric vehicles (EVs) on highways is limited in comparison to the total number of service areas. The scope of this work is to create a prototype and show a different approach to assessing the number of inlets required on highways. The proposed method estimates the energy requirements for the future electric fleet on highways. It is based on an energy conversion that starts with the fuel sold in the highway network and ends with the number of charging inlets. A proposed benchmark method estimates energy requirements for the electric fleet using consolidated values and statistics about refueling attitudes, with factors for range correction and winter conditions. The results depend on assumptions about future car distribution, with varying numbers of required inlets. The analysis revealed that vehicle traffic is a critical factor in determining the number of required charging inlets, with significant variance between different SAs. This study highlights the necessity of incorporating factors like weather, car charging power, and the future EV range into these estimations. The findings are useful for planning EV charging infrastructure, especially along major traffic routes and in urban areas with high-range vehicles relying on High-Power DC (HPDC) charging. The model’s applicability to urban scenarios can be improved by considering the proportion of energy recharged at the destination. A key limitation is the lack of detailed origin–destination (OD) highway data, leading to some uncertainty in the calculated range ratio coefficient and underscoring the need for future research to refine this model.

Effective Road Accident Monitoring and Alert System

Indian roads are undoubtedly the most dangerous in the world. In 2015, around 1, 46,133 people were killed on Indian roads, states Ministry of Road Transport and Highways data. This translates in to 11 deaths per 100,000 people or one life snuffed out every 3.6 minutes. To reduce these alarming figures, the ministry of road and transport has earmarked Rs. 11,000 core to fix the ‘black spots’ or accident prone areas on the national highways yet the accidents are increasing on daily basics. Its only due to the unavailability of information about the road of our area or that we travelling. to overcome this scenarios we are going to developing a web portal, with the help of this portal every public can find out the accident prone region when they are travelling. In this portal we have administrator they may be handled by the road safety depart of our nation. Under that we have police station, they have the authority to add the road and routes of each district and they can add the accident zone with geo location. Try are the one who monitor the system when some accidents are happens. They can add accident information to the system regarding how the accidents are happens how many where killed, they status of each accidents, type of accidents. When it’s happen etc these are details can be added by the police station. When traffic safety department login to the system they can view all the information about the accident details of each zones. When a public is travelling through any accident zone our system will gather the geo location and monitor with our accident zone when they enter any accident zone radius that is 1 km the system immediately send the notification that to the user that they are entering into a accident zone and they also view the percussion measurements that needed to follow in that route. Through this portal we can truly reduce the accidents and we can save lot of life’s.

Multi-channel feature fusion attention Dehazing network.

Haze is a typical weather phenomena that has a significant negative impact on transportation safety, particularly in the port, highways, and airport runway areas. A multi-scale U-shaped dehazing network is proposed in this research, which is based on our multi-channel feature fusion attention structure. With the help of the feature fusion attention techniques, the model can focus on the intriguing locations with higher haze concentration area. In conjunction with UNet, it can achieve multi-scale feature reuse and residual learning, allowing it to fully utilize the feature information of each layer for image restoration. Experimental resulsts show that our technique performs well on a variety of test datasets. On highway data sets, the PSNR / SSIM / L∞ error performance over the novel technique is increased by 0.52% / 0.5% / 30.84%, 4.68% / 0.78% / 26.19% and 13.84% / 9.05% / 55.57% respectively, when compared to DehazeFormer, MIRNetv2, and FSDGN methods. The findings suggest that our proposed method performs better on image dehazing, especially in terms of L∞ error performance.

A novel spatio-temporal generative inference network for predicting the long-term highway traffic speed

Accurately predicting the highway traffic speed can reduce traffic accidents and transit time, which is of great significance to highway management. Three essential elements should be considered in the long-term highway traffic speed prediction: (1) adaptability to speed fluctuation, (2) exploring the spatio-temporal correlation effectively, and (3) prediction of non-error propagation. This paper proposes a novel spatio-temporal generative inference network (STGIN) driven by data and long-term prediction. STGIN consists of three parts; semantic enhancement, spatio-temporal correlation extraction block (ST-Block), and generative inference. Semantic enhancement is first used to model the contextual semantics of traffic speed, improving the adaptability to speed fluctuations. The ST-Block is then used to extract the spatio-temporal correlations of the highway network. Finally, generative inference is used to pay attention to the correlation between historical- and target-sequences to generate the target hidden outputs rather than a dynamic step-by-step decoding way; it avoids long-term prediction error propagation in the spatial and temporal dimensions. The evaluation experiments use the monitoring data of highway in Yinchuan City, Ningxia Province, China. For long-term highway speed prediction, the experimental results demonstrate that the performance of the proposed method is better than that of the baseline methods.

Statistical Models of Interactions between Vehicles during Overtaking Maneuvers

A practical challenge facing the adoption of self-driving vehicles is the complex influence of the lateral dimension in vehicle traffic. This phenomenon has received little attention in the literature and few quantitative descriptions of interactions between vehicles are available for model validation. This paper proposes an analysis of the kinematic variables describing vehicle interactions on both axes during overtaking maneuvers using linear as well as nonlinear and nonparametric models based on real-world highway data. The principal findings are as follows: (a) a mutual influence between pairs of vehicles, especially at small lateral separation distances; (b) the higher the longitudinal velocity, the greater the lateral distances, no doubt to avoid collisions; and (c) lateral accelerations that tend to narrow lateral distance are associated with longitudinal accelerations that tend to widen it. These results are consistent across the different models applied and also with previous studies.

Impact of event encoding and dissimilarity measures on traffic crash characterization based on sequence of events

Crash sequence analysis has been shown in prior studies to be useful for characterizing crashes and identifying safety countermeasures. Sequence analysis is highly domain-specific, but its various techniques have not been evaluated for adaptation to crash sequences. This paper evaluates the impact of encoding and dissimilarity measures on crash sequence analysis and clustering. Sequence data of interstate highway, single-vehicle crashes in the United States, from 2016 to 2018, were studied. Two encoding schemes and five optimal matching based dissimilarity measures were compared by evaluating the sequence clustering results. The five dissimilarity measures were categorized into two groups based on correlations between dissimilarity matrices. The optimal dissimilarity measure and encoding scheme were identified based on the agreements with a benchmark crash categorization. The transition-rate-based, localized optimal matching dissimilarity and consolidated encoding scheme had the highest agreement with the benchmark. Evaluation results indicate that the selection of dissimilarity measure and encoding scheme determines the results of sequence clustering and crash characterization. A dissimilarity measure that considers the relationships between events and domain context tends to perform well in crash sequence clustering. An encoding scheme that consolidates similar events naturally takes domain context into consideration.

Big data classification based on improved parallel k-nearest neighbor

In response to the rapid growth of many sorts of information, highway data has continued to evolve in the direction of big data in terms of scale, type, and structure, exhibiting characteristics of multi-source heterogeneous data. The k-nearest neighbor (KNN) join has received a lot of interest in recent years due to its wide range of applications. Processing KNN joins is time-consuming and inefficient due to the quadratic structure of the join method . As the number of applications dealing with vast amounts of data develops, KNN joins get more sophisticated. The authors seek to save money on computer resources by leveraging a large number of threads and multiprocessors. Six popular datasets are used to apply the method and evaluate the sequential and parallel performance of the KNN technique. These datasets are used to compare the sequential and parallel performance of the KNN method. When compared to a matching multi-core solution, the final implementation saves computing resources. It has been optimized to utilize as little RAM as possible, allowing it to manage high-resolution photo data without sacrificing efficiency. The authors will use the technique they presented using Spark Radoop. Our performance research validates the supplied method’s efficacy and scalability.

Multi-Vehicle Conflict Management With Status and Intent Sharing Under Time Delays

This paper discusses conflict analysis for multiple vehicles possessing different automation levels. Two different classes of cooperation, enabled by vehicle-to-everything (V2X) communication, are considered: status-sharing and intent-sharing. Status sharing allows vehicles to exchange their instantaneous states with each other (e.g., current velocity and position), whereas intent sharing also enables information exchange regarding the future motion of vehicles (e.g., velocity and acceleration bounds). We consider two types of time delays, one in vehicle dynamics and the other in V2X communication. Using reachability theory, our conflict analysis framework interprets the information encoded in the wireless messages pertaining to the two different cooperation classes by means of conflict charts. These charts allow for efficient and reliable on-board decision making and control design for a connected automated ego vehicle which interacts with multiple connected remote vehicles when carrying out different maneuvers. We quantify the effects of time delays in a mixed-autonomy traffic environment and unveil the benefits of intent information. Utilizing real highway data, we use numerical simulations to validate the extended conflict management framework.

Conflict Analysis for Cooperative Maneuvering With Status and Intent Sharing via V2X Communication

In this paper, we establish the concept of conflict analysis and demonstrate its applicability to aid the decision making of vehicles at different levels of automation and cooperation. In particular, we assume that the participating vehicles are equipped with vehicle-to-everything (V2X) communication and study cooperative maneuvers under status sharing and intent sharing. Conflict-free maneuvering strategies are developed and communication requirements for such strategies are determined. To demonstrate the developed framework, we investigate a scenario with an ego vehicle merging to a main road while another vehicle is approaching on that road. The results are demonstrated by both experimental data using real vehicles on a test track and simulations based on real highway data.

Variability of Glacier Velocity and the Influencing Factors in the Muztag-Kongur Mountains, Eastern Pamir Plateau

Glacier velocity is the key to understanding the nature of glaciers. Its variation plays an important role in glacier dynamics, mass balance, and climate change. The Muztag-Kongur Mountains are an important glacier region in the Eastern Pamir Plateau. Under the background of global warming, the glacier velocity variation has been widely considered, but details of the inter-annual and intra-annual changes have not been clear. In this study, we explored the inter-annual and intra-annual variations in the glacier velocity from 1990 to 2021, and the influencing factors, based on Landsat images, Inter-Mission Time Series of Land Ice Velocity and Elevation (ITS_LIVE), and Karakoram Highway (KKH) data product analysis. The results showed the following: (1) the glacier velocity has increased since 1990, and significant growth occurred in 1995–1996. (2) A transverse profile of two typical glaciers was used to analyze the monthly variation in glacier velocity during the year. The peaks of monthly velocity occurred in May and August. (3) Since 1990, the inter-annual precipitation has increased, and the temperature increase slowed down from 2000 to 2013. The trend of inter-annual glacier velocity variation was consistent with that of the precipitation. The glacier velocity peaked in 1996/1997 due to increased precipitation in 1995. The glacier velocity over the year was consistent with the monthly precipitation trends, which indicates that precipitation has a significant influence on the change in glacier velocity. (4) In addition to temperature and precipitation, the glacier velocity variation was moderately correlated with the glacier size (length and area) and weakly correlated with the slope. The spatial distribution of glaciers shows that the spatial heterogeneity of glaciers in the Muztag-Kongur Mountains is affected by the westerly circulation. The long-term glacier velocity variation research of the Muztag-Kongur Mountains will contribute to a better understanding of glacier dynamics within the context of climatic warming, and the different influencing factors were analyzed to further explain the glacier velocity variation.

Demonstrating efficiency through data connectivity between asset management systems and IM

The CoDEC (Connected Data for Effective Collaboration) project has developed standardised tools – an Asset Data Dictionary and associated Ontology – to support data integration between Building Information Modelling (BIM) and Asset Management Systems (AMS). CoDEC has also developed an OpenAPI (Application Protocol Interface) to enable automatic data connection between the two systems. Having developed the standardised process, the potential benefits offered for connecting and linking data have been shown in three pilot projects to demonstrate (1) how tunnel monitoring data can enrich BIM models of tunnels (2) how data from bridge sensors can be linked and visualised and (3) how highway data from a BIM model can be linked to GIS-based AMS for the operational phase. This paper describes the project outcomes.

Investigating factors affecting rural crash frequency at marginal areas around cities in Iran: a random parameter modeling approach

ABSTRACT A significant portion of rural crashes in Iran occur in the marginal areas around cities. Exclusive crash frequency models should be developed to identify the factors affecting the occurrence of crashes in these areas. In this study, the rural crash data of highways leading to the city of Isfahan were employed to develop a negative binomial (NB) model as a constant-parameter model, along with random effects negative binomial (RENB) and random parameters negative binomial (RPNB) models as the models based on the random parameter approach. The modeling results indicated the superiority of the RPNB model over the two other models. According to the findings of this study, the traffic volume of roads and the proportion of local and non-local vehicles, the proportion of longitudinal distance-limit violation, the way of controlling access points, and the access to rest areas affected the crash frequency in the marginal areas around cities.

Recognition Beyond Perception: Environmental Model Completion by Reasoning for Occluded Vehicles

It is widely assumed that considering vehicle interactions for trajectory prediction can significantly improve accuracy. All environmental sensors of an automated vehicle (AV) suffer from occlusion. Therefore, relevant vehicles can be occluded by others, especially in dense traffic situations, and remain invisible to the AV. Unobserved vehicles could lead to a drop in trajectory prediction accuracy and even to poor driving behavior. We propose an environmental model completion module that reconstructs unobserved vehicles in occluded areas only using trajectory information of interacting observed vehicles. We demonstrate the functionality of our approach in principle on a toy example and verify the benefit for an AV by improving trajectory prediction results in highly interactive scenes using the proposed module. To the best of our knowledge, we are the first to investigate such a problem on highway data. Reasoning for occluded vehicles is considered more challenging on the highway than in urban scenes since vehicle interactions and cooperation between vehicles are more subtle and nuanced.

Quantifying the photovoltaic potential of highways in China

Installing photovoltaic (PV) modules on highways is considered a promising way to support carbon neutrality in China. However, collecting the area of the highway, and precisely assessing the shadow area of the highway under complex terrain remain challenges. That severely hinders the assessment of highway PV potential.To address these challenges, a spatiotemporal model is developed in this study to estimate the annual solar PV potential on highways over the whole Chinese territory.First, the areas of different highway segments are calculated based on highway network and highway toll stations. Second, hourly shadow area on highways created by nearby terrain is estimated based on a digital elevation model (DEM). When calculating the highway PV potential, the solar irradiation received in these shadow areas is regarded as zero. Finally, the PV potential of all lanes and emergency lanes was estimated at the prefecture-level city scale using surface radiation data and radiation assessment models. Based on the highway data with a total mileage of 143,684 km at the end of 2020, the results show that the annual PV potential is 3,932 TW and that the corresponding installed capacity is 700.85 GW, which can generate clean electricity at a rate of up to 629.06 TWh. The annual PV potential of highways in the southeast is greater than that in the northwest owing to the higher highway density in the southeast. This study provides a reference basis for highway PV construction planning and suitably assessment in each region of China for PV highway development.

Spatial Structure and Development Patterns of Urban Traffic Flow Network in Less Developed Areas: A Sustainable Development Perspective

Sustainable development is a scientific development requirement for economic, social, and ecological development and is particularly important for less developed areas to achieve high quality development. Among them, the traffic flow network is a key contributor to economic activity and an inclusive society, as well as influencing the regional ecology, and is an important way to reflect the connection and structure of cities and towns. Based on the literature related to sustainable development, the article takes the passenger traffic data of highways, railways, and aviation of Inner Mongolia in 2021 as the sample and applies the complex network analysis method to analyze the traffic flow network structure and refine the spatial development patterns. The results show that: (1) The highway network is manifested as the connection between the central urban areas and surrounding banner counties and the connection between the adjacent banner counties. The railroad flow is extended and expanded by the railway line with core cities as the development axis. The internal and external connections of Hohhot are the general form of aviation network. The less developed areas under traffic flow network show obvious pointing of core cities and important node towns. (2) Each traffic flow network has the tendency of scale-free and small-world properties. The influence of key town nodes in the traffic flow network is relatively limited. (3) The town connection patterns under the highway, railway, and air flow networks are “single-core and multi-point”, “axis-spoke”, and “hub-spoke”, respectively. The multiple traffic flows support the development framework of towns in less developed areas. This paper also proposes strategies for the regional transport and urban pattern with complementary advantages and high quality and sustainable development in less developed areas.

A Multilevel Point Cloud Classification Method for Underground Tunnels Based on Three-Dimensional Moving LiDAR Measurements

Underground tunnel engineering requires complex systematic engineering. A tunnel requires internal measurements after the completion of shield construction to check the real construction quality of the tunnel and provide measurement data for the next tunnel project acceptance team. When measuring a tunnel’s internal construction and performing associated data analysis, it is necessary to accurately count the size and type information of the built tunnel internal structure. In this study, mobile three-dimensional laser scanning technology is used to collect a tunnel’s internal point cloud data, and many unordered point cloud data are collected. Thus, classifying the ground objects inside the tunnel automatically and accurately is a critical problem to be solved in a tunnel construction survey. Additionally, this study proposes a multilayer underground tunnel point cloud classification method that uses the hierarchical clustering structure to deal with the original tunnel point cloud. This method extracts the specific ground objects, such as tracks or roads, platforms, and pipelines, on the tunnel surface and inside the tunnel step by step. Concurrently, the accuracy of the projection plane and the accuracy of point cloud classification are introduced to evaluate the accuracy and finally calculate the statistics of ground object information in the tunnel. To verify the engineering practicability of this method, we first collected the point cloud data of a railway tunnel inside the tunnel using a rail car equipped with high-precision LiDAR and divided the data results into four sample areas for the classification test. To verify the algorithm’s robustness, we use the proposed method to test the highway tunnel data according to the same experimental process. Experiments show that this paper’s multilevel tunnel point cloud classification method can accurately extract these four types of ground objects. The average accuracy of the projection plane in each experimental area is not less than 91.49%, and the average accuracy of point cloud classification is not less than 92.63%. Compared with the other three types of classification methods in the same field, the method in this paper is more suitable for processing tunnel point cloud data and has the advantages of high classification accuracy, strong robustness, and a simple implementation process. The proposed method can also meet the real needs of underground tunnel internal construction surveys.