Traffic Data Research Articles

An AI-driven Approach to Traffic Congestion Prediction in Port Harcourt City Using Naïve Bayes

Four important intersections Location Junction, Rumuokoro Junction, GRA Junction, and Rumuokwuta Junction will be the focus of this study's investigation into the persistent problem of traffic congestion in Port Harcourt, Nigeria. In order to provide insights for improved traffic management, the project also aims to construct a predictive model that forecasts traffic congestion on certain routes using the Naïve Bayes algorithm. The study used both exploratory and descriptive research techniques to gather information about Port Harcourt's traffic congestion. Field surveys were carried out at the four intersections between 7 a.m. and 7 p.m. to collect traffic counts and vehicle footage. The investigation also included data from Rivers State Command, a division of the Federal Road Safety Corps (FRSC). Using this data to find patterns and trends in traffic flow, a Naïve Bayes algorithm was developed to classify and predict the degree of traffic congestion. With a 97% accuracy rate, the algorithm accurately classified 1164 out of 1200 traffic data points, predicting traffic congestion. The predictive algorithm used bar charts to show the traffic conditions; tall, moderate, and tiny bars, respectively, indicated high, medium, and low traffic congestion. The model's efficacy in real-time traffic forecasting was reinforced by the close match between the forecasts and observed traffic patterns. According to the study's findings, the Naïve Bayes algorithm can accurately forecast traffic congestion and provides road users and urban planners with useful information. The model can greatly enhance road efficiency by lowering travel times, relieving congestion, and improving traffic management on Port Harcourt's major arteries by accurately predicting traffic conditions.

Adaptive Classification of VPN and Non-VPN IoT Traffic Data Using CNN with Spatio-temporal Features

Adaptive Classification of VPN and Non-VPN IoT Traffic Data Using CNN with Spatio-temporal Features

A Small-Scale Object Detection Algorithm in Intelligent Transportation Scenarios

In response to the problem of poor detection ability of object detection models for small-scale targets in intelligent transportation scenarios, a fusion method is proposed to enhance the features of small-scale targets, starting from feature utilization and fusion methods. The algorithm is based on the YOLOv4 tiny framework and enhances the utilization of shallow and mid-level features on the basis of Feature Pyramid Network (FPN), improving the detection accuracy of small and medium-sized targets. In view of the problem that the background of the intelligent traffic scene image is cluttered, and there is more redundant information, the Convolutional Block Attention Module (CBAM) is used to improve the attention of the model to the traffic target. To address the problem of data imbalance and prior bounding box adaptation in custom traffic data sets that expand traffic images in COCO and VOC, we propose a Copy-Paste method with an improved generation method and a K-means algorithm with improved distance measurement to enhance the model’s detection ability for corresponding categories. Comparative experiments were conducted on a customized 260-thousand traffic data set containing public traffic images, and the results showed that compared to YOLOv4 tiny, the proposed algorithm improved mAP by 4.9% while still ensuring the real-time performance of the model.

Traffic count data analysis using mixtures of Kato–Jones distributions

Abstract We discuss the modelling of traffic count data that show the variation of traffic volume within a day. For the modelling, we apply mixtures of Kato–Jones distributions in which each component is unimodal and affords a wide range of skewness and kurtosis. We consider two methods for parameter estimation, namely, a modified method of moments and the maximum-likelihood method. These methods were seen to be useful for fitting the proposed mixtures to our data. As a result, the variation in traffic volume was classified into the morning and evening traffic whose distributions have different shapes, particularly different degrees of skewness and kurtosis.

Exploring the use of satellite Earth observation active wildland fire hotspot data via open access web platforms

ABSTRACT Globally, managing wildland fire is increasing in complexity. Satellite Earth Observation (EO) data, specifically active fire ‘hotspot’ data, is often used to inform wildland fire management. This study explores hotspot data usage via web traffic data (‘user counts’) for the FIRMS, GWIS and EFFIS web portals between September 2019 and April 2023. Global active fire data use is characterized by multi-month periods of relatively low, stable user counts, interspersed with periodic spikes (4.1x median monthly activity) of activity broadly aligned with the North American / European fire season (late summer-fall). Users from the Americas (45%) and Europe (36%) dominate web traffic. We also examined correlative relationships between web page user counts and environmental and social variables at multiple spatial scales. Globally, the strongest relationships were found between user counts and the total number of fires, total burned area, number of fire disaster events; country population levels and internet proliferation. Notably, at a country level, the strongest (and weakest) relationships between weekly user counts and fire activity were found in a diverse range of countries suggesting that a variety of hotspot data use situations exist and further investigation is needed to better understand EO active fire data usage.

Penanganan Simpang tak Bersinya: Studi Jalan Simpang Haji Rais Kota Tangerang Selatan

The intersection of Jalan H. Rais is where 3 (three) roads meet, namely Jalan H. Jamat Gang Rais, Jalan Puspitek Segment 1, and Jalan Puspitek Segment 2. This intersection often experiences long queues due to inadequate intersection capacity so that it cannot accommodate the volume of vehicles during morning and evening rush hours. The research method used was a direct survey method at the research location to collect traffic data at the H. Rais intersection and the surrounding roads. The research results found that the average length of the queue before handling during peak hours on weekdays was 168.52 m and delays were 35,471 with an intersection service level (LOS) D, while the average length of the queue before handling during peak hours on holidays was 119 .82 m and a delay of 33.52 with a level of service (LOS) D. H. Rais intersection performance for the next 5 years, before handling becomes worse with the result that the average queue length during weekday peak hours is 219, 64 m and a delay of 49,137 with an intersection service level (LOS) E, while the average queue length during holiday peak hours is 218.28 m and a delay of 43,635 with an intersection service level (LOS) E. Handling that needs to be done at the intersection H. Rais road in short-term scenario 1 is by providing road equipment facilities and assignment of traffic officers, and in short-term scenario 2 by widening the bend radius to a minimum of 7.8 m and widening the H. Jamat Gang Rais road to 6 m, while The treatment carried out at the H. Rais intersection in the long term is to change the Puspitek road type to 4/2-T with a width of 6 m per direction.

A novel modelling framework for real-time prediction of path travel times using both traffic and weather data

The problems of path travel time predictions have been studied over decades. Traditional approaches to this challenge have relied on different traffic data. However, in metropolitan cities with frequent rainfall, there is a need to consider the weather effects on real-time prediction of path travel times. Hence, this research integrates traffic data with weather data, including rainfall intensity data and weather forecast data to consider the temporal relationships between weather data and path travel times. The proposed modelling framework is evaluated with data from a major expressway and an urban arterial road in Hong Kong. Results unequivocally demonstrate that incorporating weather data significantly boosts prediction accuracy. This study also examines the impact of different frequencies on weather data, as well as weather forecast correctness, on prediction accuracy. Finally, the applicability of the proposed modelling framework has been verified without and with the input of ground truth on path travel times.

Federated Learning-Based Traffic Flow Prediction Model in Intelligent Transportation Systems

The existing Intelligent Transportation System (ITS) achieves high success. As an essential component of ITS, Traffic Flow Prediction (TFP) has attracted tremendous attention. It is a critical but challenging task to improve the robust convergence and high accuracy of TFP in real-world scenarios. This study presents an optimized Federated Learning (FL)-based ChebNet model, FedproxChebNet, to realize the highly effective and accurate TFP. By selecting the best penalty constant in the proximal term to optimize the objective function, this model can achieve fast and stable convergence. Using the ChebNet model to aggregate neighbor nodes’ characteristics, more hidden information underlying the spatio-temporal traffic data can be taken into consideration for training the global and local models. All the superiority of the FedproxChebNet model makes it outperform other FL models with the Graph Convolutional Network (GCN), Graph Attention Network (GAT) and Spatio-Temporal Graph Convolutional Network (STGCN). We designed a series of experiments on various FL-based GNN model comparisons, parameter sensitivity tests, and on verifying the performance of FedproxChebNet with different heterogeneous systems with [Formula: see text], [Formula: see text] and [Formula: see text]. Based on four real-world data sets from the cognitive network, the experimental results demonstrate that the presented FedproxChebNet provides the best convergence and the highest accuracy in TFP, and achieves the best performance in a highly heterogeneous system ([Formula: see text]). Specifically, the accuracy of FedproxChebNet is at least improved by [Formula: see text] on PeMS07 than other FL-based GNN models. This proposed FedproxChebNet model may be preferable for different scenarios in ITS such as route planning, traffic congestion control and reversible lanes.

Spatiotemporal implicit neural representation as a generalized traffic data learner

Spatiotemporal Traffic Data (STTD) measures the complex dynamical behaviors of the multiscale transportation system. Existing methods aim to reconstruct STTD using low-dimensional models. However, they are limited to data-specific dimensions or source-dependent patterns, restricting them from unifying representations. Here, we present a novel paradigm to address the STTD learning problem by parameterizing STTD as an implicit neural representation. To discern the underlying dynamics in low-dimensional regimes, coordinate-based neural networks that can encode high-frequency structures are employed to directly map coordinates to traffic variables. To unravel the entangled spatial–temporal interactions, the variability is decomposed into separate processes. We further enable modeling in irregular spaces such as sensor graphs using spectral embedding. Through continuous representations, our approach enables the modeling of a variety of STTD with a unified input, thereby serving as a generalized learner of the underlying traffic dynamics. It is also shown that it can learn implicit low-rank priors and smoothness regularization from the data, making it versatile for learning different dominating data patterns. We validate its effectiveness through extensive experiments in real-world scenarios, showcasing applications from corridor to network scales. Empirical results not only indicate that our model has significant superiority over conventional low-rank models, but also highlight that the versatility of the approach extends to different data domains, output resolutions, and network topologies. Comprehensive model analyses provide further insight into the inductive bias of STTD. We anticipate that this pioneering modeling perspective could lay the foundation for universal representation of STTD in various real-world tasks. PyTorch implementations of this project is publicly available at:https://github.com/tongnie/traffic_dynamics.

Short-term freeway traffic speed multistep prediction using an iTransformer model

Accurate prediction of the freeway traffic speed is important for enhancing intelligent transportation management and assisting with route planning. Current traffic speed prediction studies usually neglect predictions extending to an hour or longer. Thus, to address this gap, the inverted Transformer (iTransformer) model is utilized to predict freeway speeds across intervals from 5 to 150 minutes. The iTransformer model provides a global view by encapsulating the entire time series from each detector into variate tokens, allowing it to capture the complex patterns and dependencies that change over time. Additionally, a multi-head attention mechanism is employed to identify short-term and long-term speed patterns. This study validates the prediction performance of iTransformer by using the traffic speed data from an interstate freeway in Minnesota, comparing it against traditional traffic prediction methods and two other Transformer models. Results indicate that the iTransformer model outperforms these benchmark approaches, particularly when predicting speed over 60 minutes for peak hour periods.

Exploration of the Traffic Safety of Battery Electric Vehicles: A Case Study of Tesla Vehicle-Involved Crashes in Pennsylvania, USA

After decades of efforts, the number of battery electric vehicles (BEV) has increased greatly around the world. Meanwhile, their unique technical features also bring many new traffic safety challenges. Using traffic crash data from Pennsylvania from 2018 to 2021, this study aims to identify characteristics and trends of BEV crashes by comparing those crashes involving Tesla vehicles (the premier BEV brand in the auto market of the United States) with crashes involving internal combustion engine vehicles (ICEV). First, Tesla and ICEV crashes are compared for crash severity, collision type, spatial and temporal distributions, and environmental features. Tesla crashes show no significant difference from those of ICEVs in severity, but they have many more rear-end and angle collisions. In addition, Tesla crashes are found to concentrate in peak hours and around noon, occurring mainly in urban areas, at intersections, and on state roads. A logistic regression model is then built to identify the important factors influencing the severity of Tesla crashes. The findings are expected to provide new insights which will help researchers understand better traffic safety issues around BEVs.

An Artificial Neural Network Model for Short-Term Traffic Flow Prediction in Two Lane Highway in Khulna Metropolitan City, Bangladesh

Short-term traffic flow prediction is one of the most significant research topics in traffic engineering. It is instrumental in designing a more modern transport network to manage traffic signals and reduce congestion. Short-term traffic flow is a challenge that a third-world country like Bangladesh is all too familiar with. Like the other cities of Bangladesh, Khulna Metropolitan City is gradually becoming more aware of this situation. The Khulna-Jashore National Highway (N-7), which runs through the city and provides a linear shape, serves as the backbone of the Khulna Metropolitan City traffic flow. This study developed an Artificial Neural Network (ANN) model for the short-term Traffic Flow Prediction on Two-Lane Highway in Khulna Metropolitan City, Bangladesh. Data was collected from March 1, 2021, through June 30, 2021, during 600–900 hours and 1200–1500 hours. Good-quality electronic cameras recorded the vehicles at the full designated length. The regression graphs displayed the network outputs with targets for the training, validation, and test sets. The various speed level parameters for which the fit is reasonable for all data sets, with R values of 0.98426 in each case. The various traffic volume parameters for which the fit is reasonable for all data sets, with R values of 0.96758 in each case. The model's superiority is indicated by its low mean squared error values. This study demonstrated that the neural network has a good prediction effect on specific road traffic flow, which can achieve the goal of short-term prediction and has improved practicability through testing on real traffic data. This study provides an opportunity to provide a suitable alternative for short-term traffic flow forecasting in Khulna Metropolitan City with traffic flow conditions for two-lane undivided highways.

Dynamic multi-scale spatial-temporal graph convolutional network for traffic flow prediction

This paper proposes a dynamic multi-scale spatial-temporal graph convolutional network (DS-STGCN) for traffic flow prediction. The network aims to comprehensively extract global and local dependencies in dynamic spatial-temporal data by inputting traffic network flow data to construct node feature graphs, topology graphs, and time slot feature graphs, capturing the complexity and dynamics of traffic flow. DS-STGCN interprets feature information of the traffic network from both spatial and temporal dimensions through dynamic multi-scale graph convolutional blocks. In the spatial dimension, these blocks use constraints at different levels to balance fine-grained local features and extensive global features, revealing the intrinsic structure of traffic flow data. In the temporal dimension, these blocks jointly learn with temporal convolutional blocks to capture multi-frequency time patterns and handle long sequence data, effectively extracting potential dependencies of time series. Furthermore, DS-STGCN effectively models the changing spatial-temporal relationships in road network flow by constructing dynamically adaptive updated adjacency tensors, generating dynamic graph structures to address the challenge of changing spatial-temporal relationships in the transportation system. Experimental results show that our method significantly outperforms other competing methods on five real traffic datasets (PEMS03, PEMS04, PEMS07, PEMS08 and METR-LA).

Deep anomaly detection: A linear one-class SVM approach for high-dimensional and large-scale data

Anomaly detection plays a crucial role in various fields including cyber security, finance, healthcare, and industrial monitoring. Traditional methods in anomaly detection often face several challenges such as scalability, adaptability, and difficulty in handling high-dimensional data. So a novel Recurrent Extreme Learning based –Boosted Chimp (REL-BC) algorithm is proposed for anomaly detection. The REL-BC model involves a data pre-processing phase and an anomaly detection phase. The data pre-processing phase involves three stages namely one-hot-encoding, outlier disposal, and min-max normalization. In this study, a Recurrent Neural Network is utilized to seize the temporal dependencies and traffic data in the network. Also, the Extreme Learning Machine (ELM) is employed in distinguishing normal as well as anomalous patterns. Further Chimp Optimization is employed for optimizing hyperparametersto improve the efficiency of the REL-BC approach. The outcome of the experimentation revealed that it demonstrated the improvement of performance for the REL-BC method in detecting anomalies based on various measures.

A predictive framework for last-mile delivery routes considering couriers’ behavior heterogeneity

Last-mile route prediction is a powerful tool for freight delivery companies that can be essential in the development of new features such as arrival time prediction or accurate workload allocation. Existing methodologies propose prediction models that, on the one hand, require external information, such as traffic data or a prior division of work areas, and, on the other hand, assume courier homogeneity in the search for travel patterns. However, this assumption may introduce noise in the predictions since different couriers may be subject to different routing habits. This study proposes a comprehensive predictive framework for delivery routes, which allows identifying the routing profiles that best suit each courier and work area, and which starts from basic information available for any carrier, ensuring the scalability of the tool. The analysis is supported by a case study, where the results obtained bring to light the heterogeneity in the routing decisions of the different drivers and show that the proposed approach produces consistent and accurate predictions for the vast majority of them.

Speed prediction and nearby road impact analysis using machine learning and ensemble of explainable AI techniques

Traffic speed prediction is an important topic in Intelligent Transport Systems (ITS). Although traffic speed prediction for real-life applications is burgeoning, the study of explaining and interpreting AI-based speed prediction is still in its initial stage. In this paper, we applied multiple advanced regression techniques, such as XGBoost and CatBoost optimized gradient boosting, Random Forest, and LASSO to predict traffic speed more accurately in the subsequent time windows. The experiment with prediction methods was conducted using the traffic speed data of the Seoul metropolitan road network. Each road segment represented as a node in the network is associated with neighboring roads within a configurable range. We picked heavily congested nodes as prediction targets. Then, we evaluated nearby road influences to determine critical contributions to the situation of the target nodes. We interpreted the model’s output and extracted the topmost influential neighboring nodes by using an ensemble of explainable artificial intelligence (XAI) techniques such as feature importance assessment using the GINI entropy function, Recursive Feature Elimination, Shapely Additive Explanation, and a method of measuring the impact of masked nodes. We validated the XAI interpretations through traffic flow simulation by tuning the topmost influential nearby roads’ speed and observing the effect on the roads’ traffic congestion relief correspondingly. We also proved our solution through local explanation techniques such as Local Interpretable Model-Agnostic Explanations. Our methods are applicable to any transport network and open the door to new strategies for controlling the specific nearby roads for effective congestion relief.

Impact of Debris Removal Post-Wildfires on Pavement Fatigue and Rutting Lives: Case Studies of California’s Camp and Carr Fires

Between 2017 and 2018, California experienced a series of four devastating fires, including the Camp and Carr Fires, which ranked among the most destructive fires in U.S. history. During these fires, roads were critical in the evacuation, rescue operations, goods transportation, and access to critical services. Additionally, postfire, road infrastructure became crucial for removing hazardous and nonhazardous waste from fire-affected areas to major landfills and recycling facilities. Despite the significance of pavements in this process, previous studies have not quantitatively assessed the potential damage caused to pavements by the additional trucks used in debris removal operations. This research aimed to address this knowledge gap by collecting precise traffic data for the routes taken to waste management facilities, including data on the number of trips involved in debris transportation. The traffic information was then utilized to calculate changes in equivalent single axle loads and traffic index values for pavement design. Pavement structures were obtained from the available core database. Pavement simulation results showed that of the nine studied highways, only one exhibited a reduction in cracking life of about 2 years. However, Skyway, the main artery in the town of Paradise, demonstrated a significantly accelerated fatigue cracking failure by 14.3 years. A sensitivity analysis of fire intensity showed other highway sections that were structurally adequate could be affected by larger fires. The presented methodology could be used in traffic planning as part of debris management operations to avoid vulnerable pavement sections.

MGHCN: Multi-graph structures and hypergraph convolutional networks for traffic flow prediction

Accurate and timely traffic flow predictions are essential for effective traffic management and congestion reduction. However, most traditional prediction methods often fail to capture the complex dynamics and correlations within traffic flows due to insufficient processing of spatiotemporal data. Specifically, these methods struggle to integrate and analyze the multi-layered spatial and temporal interactions inherent in traffic data, leading to suboptimal prediction accuracy and robustness. To address this limitation, this paper presents a Multi-Graph Structures and Hypergraph Convolutional Network (MGHCN) that combines diverse graphs and hypergraphs. The MGHCN simplifies the predictive framework by integrating key components that improve its robustness and accuracy. One of the most critical components is the dual hypergraph structure, which captures edge correlations by converting traditional graph edges into hypergraph nodes. To better capture the spatiotemporal correlation of traffic data, a Graph Convolutional Network (GCN) is employed to analyze these hypergraphs in depth. Finally, a novel adjacency matrix and a dynamic graph module are used to accurately simulate interactions between spatiotemporal features, thereby enhancing the accuracy and robustness of predictions. Experimental validation on four distinct real-world traffic datasets shows that MGHCN outperforms existing state-of-the-art traffic prediction methods.

Derived cannabinoid product availability among online vape shops

ObjectivesTo determine the proportion of online vape shops that offer derived cannabinoid products in a large metropolitan area (San Diego, California), measure their compliance with state hemp regulations, and estimate whether these shops receive more website traffic compared to those that offered nicotine or tobacco. MethodsWe obtained vape shops (n = 109) using browser-based (i.e., Google Search) and map-based (i.e., Google Maps and Yelp) searches in San Diego from March to August 2023 and conducted a content analysis of their websites to identify derived cannabinoid products offered for mail-order purchasing. Using website traffic data, we examined the association between derived cannabinoid product availability and monthly website visits. ResultsAmong the 109 online vape shops in the study sample, 35.8 % offered derived cannabinoid products for mail-order purchase and 26.6 % sold flavored (excluding terpenes) and inhalable cannabinoid products. Compared to vape shops that did not offer derived cannabinoid products (Mean: 23,619; 95 % CI: 23,605–23,634), those offering flavored and inhalable cannabinoid products received 2.5 times more monthly website visits (Mean: 57,950; 95 % CI: 57,913–57,986) and those offering any derived cannabinoid products received 5.5 times more monthly website visits (Mean: 130,694; 95 % CI: 130,607–130,782). ConclusionThe prevalence of flavored and inhalable derived cannabinoid products, despite being prohibited under California’s hemp regulations, highlights the need for additional enforcement measures to ensure retailer compliance. The higher website traffic observed among vape shops offering cannabinoid products may be indicative of greater popularity of retailers selling derived cannabinoid products compared to those selling nicotine or tobacco products alone.

A lightweight model design approach for few-shot malicious traffic classification

Classifying malicious traffic, which can trace the lineage of attackers’ malicious families, is fundamental to safeguarding cybersecurity. However, the deep learning approaches currently employed require substantial volumes of data, conflicting with the challenges in acquiring and accurately labeling malicious traffic data. Additionally, edge network devices vulnerable to cyber-attacks often cannot meet the computational demands required to deploy deep learning models. The rapid mutation of malicious activities further underscores the need for models with strong generalization capabilities to adapt to evolving threats. This paper introduces an innovative few-shot malicious traffic classification method that is precise, lightweight, and exhibits enhanced generalization. By refining traditional transfer learning, the source model is segmented into public and private feature extractors for stepwise transfer, enhancing parameter alignment with specific target tasks. Neuron importance is then sorted based on the task of each feature extractor, enabling precise pruning to create an optimal lightweight model. An adversarial network guiding principle is adopted for retraining the public feature extractor parameters, thus strengthening the model’s generalization power. This method achieves an accuracy of over 97% on few-shot datasets with no more than 15 samples per class, has fewer than 50 K model parameters, and exhibits superior generalization compared to baseline methods.