First specifications of urban traffic-congestion forecasting models

With the rapid development of intelligent transportation systems, vehicle detection and traffic flow statistics have become increasingly critical in traffic management and the construction of smart cities. However, complex weather conditions lead to challenges in vehicle detection algorithms, increasing false negatives and false positives. Additionally, the rapid growth of vehicle ownership makes traditional algorithms inadequate for meeting practical application needs. Therefore, this paper proposes a collaborative optimization-based method combining YOLOv11 for vehicle detection and traffic flow analysis under complex weather conditions. Vehicle information is accurately extracted through object detection and tracking methods, and further analyzed using Logistic Regression to assess traffic congestion. The main contributions of this study are: (1) Integration of the CBAM attention mechanism into YOLOv11, enhancing the vehicle feature extraction ability through collaborative channel and spatial attention, thereby improving interference resistance under complex weather conditions. (2) Adoption of the Shape-IoU loss function, with dynamic weight allocation to optimize the accuracy of detecting smaller vehicles and the precision of bounding box regression in images where vehicles are located at a greater distance. (3) Construction of a traffic congestion prediction model based on the detection results, integrated with Logistic Regression. The proposed method's effectiveness is validated on the public dataset UA-DETRAC. Through the synergistic effect of the CBAM attention mechanism and Shape-IoU loss function, the improved model's mAP50-95 shows a 0.3 percentage point increase over the YOLOv11 baseline, providing efficient and reliable technical support for intelligent transportation systems. This study enhances the prediction performance of traffic states under complex weather conditions by effectively calculating traffic flow parameters such as vehicle count and density, thus offering foundational data support for traffic management decision-making. The research conclusions are of practical significance for urban traffic improvement.

One of the main issues facing contemporary smart cities is urban traffic congestion, which causes delays, fuel waste, and elevated air pollution. This paper describes an intelligent traffic flow management system that combines machine learning models for real-time vehicle detection, classification, and traffic prediction with the YOLO (You Only Look Once) object detection algorithm. In order to predict congestion levels and optimize signal timings, the suggested system uses machine learning regression and clustering techniques, records live traffic video feeds, and uses YOLOv8 to detect and count vehicles. In comparison to conventional sensor-based techniques, experimental results show a detection accuracy of 95.7% and a traffic flow prediction accuracy of 93.2%. For next-generation smart cities, this combination of deep learning and machine learning guarantees effective, scalable, and adaptive traffic control.

Short-Term prediction aimed at the urban traffic congestion is an important goal for Intelligent Transport Systems (ITS). Short-term traffic prediction module tries to predict Traffic Congestion Index accurately and in approximately real-time. Up to date, there have been three basic methods in short-Term traffic prediction research namely the Kalman Filtering (KF) (Okutani and Stephanedes in Transport Res Part B 18B:1–11, 1984, [1]) method, Time Series models (Williams and Hoel in ASCE J Transport Eng 129:664–672, 2003, [2]) and Neural Network (NN) models (Smith and Demetsky in Transport Res Rec J Transport Res Board 1453:98–104, 1994, [3]). The Neural Networks based methods have proven to give good accuracy rate but they are time consuming in training. In our paper, we have implemented the new Neural Networks based algorithm called Extreme Learning Machine (ELM) (Huang and Siew in ICARCV, pp. 1029–1036, 2004, [4]) to design a real-time traffic index in the data of a real world city of Nanning in South China. Our experiment results show that ELM algorithm provides good generalization performance at extremely fast learning speed compared with other state-of-art algorithms. The algorithm obtains high accuracy in practical prediction application. In addition, quick training and good fitting results on our own large scale traffic data set proves ELM algorithm works well on large data sets.

Road traffic has long been recognized to represent a country’s prosperity. Unfortunately, traffic congestion coming with it is considered as one of the most significant challenge in modern cities. Thus, a promising paradigm, namely, Intelligent Transportation System (ITS) has become a research focus which lies on its feasibility and efficiency of solving transportation issues. In the open literature, researchers have proposed theories and developed corresponding models to alleviate traffic congestion. However, many solutions are static, which means they serve to analyze and evaluate the traffic systems rather than schedule the road traffic dynamically. To this end, this paper develops a road traffic congestion prediction model to forecast the congestion level. The congestion performance metrics are obtained by developing a queueing system subject to self-similar traffic. This is because Hurst parameter evaluation, subject to road traffic flow at rush hour, presents strong self-similar characteristic. The developed model is validated by comparing results derived from model with that of simulations on real road traffic data provided by government authorities.

Traffic forecasting plays a critical role in intelligent transportation systems (ITS) in smart cities. Travelers as well as urban managers rely on reliable traffic information to make their decisions for route choice and traffic management. However, noisy or missing traffic data poses a problem for accurate and robust traffic forecasting. While data-driven models such as deep neural networks can achieve high prediction accuracy with complete datasets, sensor malfunctions, and environmental effects degrade the performance of such models, as these models rely heavily on precise traffic measurements for model training and estimation. Consequently, incomplete traffic data poses a challenge for robust model design that can make accurate traffic forecasts with noisy/missing data. This research proposes the Robust Spatiotemporal Graph Convolutional Network (RT-GCN), a traffic prediction model that handles noise perturbations and missing data using a Gaussian distributed node representation and a variance based attention mechanism. Through experiments conducted on four real-world traffic datasets using diverse noisy and missing scenarios, the proposed RT-GCN model has demonstrated its ability to handle noise perturbations and missing values and provide high accuracy prediction.

Highway congestion has become a normal social problem that needs to be managed more accurately and deeply. In this paper, a traffic flow congestion prediction model is established based on LSTM, and the traffic parameters obtained from four observation points of China's long and deep high-speed video are used for training, so as to provide real-time early warning before the continuous congestion of the road section between the third and fourth points. The results show that the model constructed in this paper can reach 89.25% accuracy after predicting 400 times steps in 50 times Windows. After further evaluation of the constructed traffic flow congestion prediction model, it is found that the mean square error (MSE), mean absolute error (MAE) and R2 is 0.0897, <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$0.2334,0.6028$</tex>, respectively, revealing that the model can well predict the future traffic congestion.

As one of the most widely used applications of the Internet of Things (IoT), intelligent transportation system (ITS) is of great significance for urban traffic planning, traffic control, and traffic guidance. However, widespread traffic congestion occurs with the increased number of vehicles. The traffic flow prediction is a good idea for traffic congestion. Therefore, many schemes have been proposed for accurate and real-time traffic flow prediction, but there still exist many issues, including low accuracy, weak adaptability and inferior real-time. Meanwhile, the complex spatial and temporal dependencies in traffic flow are still challenging. To address the above issues, we propose a novel spatial-temporal Chebyshev graph neural network model (ST-ChebNet) for traffic flow prediction to capture the spatial-temporal features, which can ensure accurate traffic flow prediction. Concretely, we first add a fully connected layer to fuse the features of traffic data into a new feature to generate a matrix, and then the long short-term memory (LSTM) model is adopted to learn traffic state changes for capturing the temporal dependencies. Then, we use the Chebyshev graph neural network (ChebNet) to learn the complex topological structures in the traffic network for capturing the spatial dependencies. Eventually, the spatial features and the temporal features are fused to guarantee the traffic flow prediction. The experiments show that ST-ChebNet can make accurate and real-time traffic flow prediction compared with other eight baseline methods on real-world traffic data sets PeMS.

The intelligent transportation system seeks to reduce traffic and improve the driving experience. They give us a lot of data that we can use to improve services for both the public and transportation officials by feeding it into machine learning systems. Most importantly, Traffic environment refers to everything that might have an impact on how much traffic is moving down the road, including traffic signals, accidents, protests, and even road repairs that might result in a backup. A motorist or rider can make an informed choice if they have previous knowledge that is very close to approximate all the above and many more real-world circumstances that can affect traffic. Additionally, it aids in the development of driverless vehicles. Traffic data have been growing dramatically in recent decades, and we are moving toward big data concepts for transportation. The current approaches for predicting traffic flow use some traffic prediction models, however they are still inadequate to handle practical situations. We thus aimed to focus on the traffic flow forecast problem using the traffic data and prediction models. The proposed model called DRGNN, a dilated recurrent graph neural network framework aims to effectively analyze and predict the traffic pattern by considering the spatial (space) and temporal (time) aspects of the real-time traffic data considering social relationships between internet of vehicles which indeed produced accurate and valuable insights that could help in deploying the model in any suitable real-time traffic monitoring and prediction system.

Traffic flow prediction is an essential part of intelligent transportation systems (ITS), facilitating dynamic traffic control, congestion alleviation, and route planning. The past few years have seen the booming of Graph Neural Networks (GNNs), providing a strong tool to capture the sophisticated spatial compositions and dynamic temporal patterns inherent in urban road networks. In this paper, I provide a systematic and comprehensive review of GNN-based solutions for short-term traffic prediction. I first briefly review the basic concepts and categorization of GNNs, then elaborate on representative models such as spatial and spectral convolutional networks, temporal graph structures, and hybrid models with attention mechanisms and recurrent units. Besides, I recap typical traffic datasets and evaluation metrics, compare the performance of different models from multiple aspects, and highlight key technical challenges such as spatiotemporal heterogeneity, scalability, and interpretability. Finally, I suggest future research lines to improve the accuracy, efficiency, and robustness of GNN-based traffic prediction models for real-world ITS applications.

As the application of deep learning in intelligent transportation systems becomes increasingly widespread, the accuracy and reliability of traffic flow prediction have become crucial. However, existing deep learning methods are often complex in model design and lack intuitiveness, making it challenging to provide responsible explanations for traffic predictions. This paper references a responsible and reliable traffic flow prediction model (R2T-LLM) based on large language models (LLMs). This model captures complex spatiotemporal patterns and external factors by converting multimodal traffic data into natural language descriptions. By leveraging LLMs’ advanced understanding capabilities, R2T-LLM provides more transparent and interpretable predictions. It bridges the gap between technical performance and real-world application needs. While maintaining accuracy comparable to deep learning baselines, R2T-LLM offers intuitive and reliable prediction explanations. This paper also explores the spatiotemporal and input dependencies of conditional future traffic predictions and compares the model with other different approaches and types. Furthermore, it evaluates the potential of R2T-LLM in addressing challenges in large-scale urban traffic systems, highlighting its developmental and application prospects.

Traffic speed prediction is an emerging paradigm for achieving a better transportation system in smart cities and improving the heavy traffic management in the intelligent transportation system (ITS). The accurate traffic speed prediction is affected by many contextual factors such as abnormal traffic conditions, traffic incidents, lane closures due to construction or events, and traffic congestion. To overcome these problems, we propose a new method named fuzzy optimized long short‐term memory (FOLSTM) neural network for long‐term traffic speed prediction. FOLSTM technique is a hybrid method composed of computational intelligence (CI), machine learning (ML), and metaheuristic techniques, capable of predicting the speed for macroscopic traffic key parameters. First, the proposed hybrid unsupervised learning method, agglomerated hierarchical K‐means (AHK) clustering, divides the input samples into a group of clusters. Second, based on parameters the Gaussian bell‐shaped fuzzy membership function calculates the degree of membership (high, low, and medium) for each cluster using Takagi‐Sugeno fuzzy rules. Finally, the whale optimization algorithm (WOA) is used in LSTM to optimize the parameters obtained by fuzzy rules and calculate the optimal weight value. FOLSTM evaluates the accurate traffic speed from the abnormal traffic data to overcome the nonlinear characteristics. Experimental results demonstrated that our proposed method outperforms the state‐of‐the‐art approaches in terms of metrics such as mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE).

To develop an Edge-AI based IoT framework that can accurately predict real-time urban traffic flow and proactively identify congestion using lightweight edge models supported by cloud-based deep learning. Real-time traffic flow prediction plays a critical role in intelligent transportation systems, smart city development, and effective congestion control. Although cloud-based models can deliver high prediction accuracy, they are often constrained by latency, high bandwidth usage, and reliance on uninterrupted network connectivity, which limits their practicality for edge-level deployment. Edge nodes struggle to run complex models due to limited processing power, and variations in IoT sensor data can negatively impact prediction accuracy and congestion identification. To mitigate these challenges, the system employs an LSTM model for high-accuracy cloud prediction alongside a compact Conv1D model optimized for fast, real-time inference on edge devices. The approach delivers precise traffic prediction with the LSTM model and supports rapid, energy-efficient real-time processing on edge devices using the lightweight Conv1D model. The findings indicate that the LSTM model performs well particularly on the PEMS-BAY dataset with an RMSE of 0.6120 and MAE of 0.2082—but its large parameter count limits its suitability for edge devices. In comparison, the lightweight Conv1D model achieves similar accuracy with an RMSE of 0.6167 and MAE of 0.4196 while using only 1,969 parameters, making it far more efficient and fully compatible with TFLite INT8 for real-time edge deployment.

Due to excessive usage of artificial intelligence and sudden expansion of Internet of Things, research on smart city and intelligent transportation system have intensified in current times. Traffic system design and traffic flow prediction is evolving as a hot topic among all stakeholders. Traffic system design must be done effectively by the integration of AI and its supporting technologies. Different critical issue like traffic congestion, designing traffic flow, and forecasting future traffic management must be addressed properly through the integration of AI. This chapter dives into the basic phenomenon of AI driven traffic flow prediction in smart cities. It proposes a design model of intelligent traffic system that includes different machine learning algorithms. It reviews AI utilization in traffic system and provides a comprehensive study for future research. Some specific open challenges in this regard are discussed and future research path is explored.

Aim. Threats of a non-physical nature have a significant effect on the security of intelligent transportation systems (ITS). They may have the form of unlawful interference in the development and implementation of ITS. The creation of a trusted framework for the development and implementation of ITS is examined as in the case of intelligent water transportation systems (IWTS). Problems. By decree of the President of the Russian Federation, ITS, telecommunications and security of information processing are among the priority areas of scientific and technological development. ITS technologies, as well as those involved in the creation of trusted, secure system and application software are among the most important critical high technologies. The operation of ITS involves wide use of computerised systems that implement the latest information and telecommunication technologies, automated and automatic control technologies, artificial intelligence that can pose security threats. ITS are to be developed and operated in a trusted environment. Methods. The paper used the methodology for ensuring the security of IWTS, development of secure hardware and software platforms for secure automated systems, methods of system analysis, dependability theory, information protection, and law. Results. The paper defines the problem of creating a trusted framework for the development and implementation of IWTS, the applicable terminology is developed. The author examined the effect of IWTS on the security of critical information infrastructure (CII) and national security, developed a model of relationships between the IWTS security domains taking into account threats of physical and non-physical origin. Examples of computer incidents within IWTS that caused consequences at the national and international levels are given. The composition of the IWTS facilities attributed to CII is defined, critical processes implemented by standard CII facilities as part of the IWTS are set forth. The author lists conceptual problems of IWTS security, defines the principles of creating a trusted framework for the development and implementation of IWTS. Conclusion. Ensuring the security of IWTS against modern threats requires solving a number of problems associated with the creation of a trusted framework for the development and implementation of IWTS. For the purpose of improving the timeliness and quality of their solution, the paper proposes an intuitive terminology that reflects the subject area and helps finding a common understanding of the security domain by experts from various industries. IWTS facilities have an effect on CII security and national security in general. That is taken into account in the model of relationships between IWTS security domains, demonstrated using cases of computer incidents within IWTS that caused consequences at the national and international level. Given the above, the paper lists IWTS facilities attributed to CII and sets forth examples of critical processes implemented by standard CII facilities as part of the IWTS. The defined list of conceptual IWTS security problems take into account the growing landscape of IWTS security threats that includes insecure software, hardware and software platforms, software and hardware systems and emerging technologies. When developing the principles for the creation of a trusted IWTS development and implementation framework, the author took into account the best practice of implementing the methodology for creating national secure hardware and software platforms of CII facilities that enables the creation of secure automated systems for various applications that are based on domestically-developed solutions. The examined matters are of a systemic nature, which allows using the findings in the development and implementation of ITS in other modes of transportation.

As urban traffic congestion continues to intensify, predicting short-term traffic flow has become essential to enabling real-time control in intelligent transportation systems (ITS). However, traditional models face significant limitations in capturing the spatiotemporal and nonlinear characteristics of traffic data. Long Short-Term Memory (LSTM) networks, with their gated mechanisms, can effectively model long-term dependencies and periodic patterns in traffic flow. The accuracy of these predictions directly influences decision-making in scenarios such as traffic guidance and emergency management, offering substantial practical value for improving road network efficiency. This study constructs an optimized LSTM model to evaluate its effectiveness in short-term traffic prediction and to compare predictive performance across different time granularities. A dual-layer LSTM architecture is employed, incorporating the Adam optimizer, Dropout, and early stopping as regularization strategies. Using urban traffic monitoring data from the United States, both hourly and daily prediction models are developed for experimental validation. Results indicate that the hourly prediction model (MSE = 0.0709) markedly surpasses the daily model (MSE = 0.2987), effectively identifying recurring patterns like rush periods in the morning and evening. These outcomes offer a practical solution for adaptive traffic regulation.