Video‐based road traffic monitoring and prediction using dynamic Bayesian networks

A scalable approach to optimize traffic signal control with federated reinforcement learning

Intelligent Transportation has seen significant advancements with Deep Learning and the Internet of Things, making Traffic Signal Control (TSC) research crucial for reducing congestion, travel time, emissions, and energy consumption. Reinforcement Learning (RL) has emerged as the primary method for TSC, but centralized learning poses communication and computing challenges, while distributed learning struggles to adapt across intersections. This paper presents a novel approach using Federated Learning (FL)-based RL for TSC. FL integrates knowledge from local agents into a global model, overcoming intersection variations with a unified agent state structure. To endow the model with the capacity to globally represent the TSC task while preserving the distinctive feature information inherent to each intersection, a segment of the RL neural network is aggregated to the cloud, and the remaining layers undergo fine-tuning upon convergence of the model training process. Extensive experiments demonstrate reduced queuing and waiting times globally, and the successful scalability of the proposed model is validated on a real-world traffic network in Monaco, showing its potential for new intersections.

A Distributed Big Data Analytics Architecture for Vehicle Sensor Data

The unceasingly increasing needs for data acquisition, storage and analysis in transportation systems have led to the adoption of new technologies and methods in order to provide efficient and reliable solutions. Both highways and vehicles, nowadays, host a vast variety of sensors collecting different types of highly fluctuating data such as speed, acceleration, direction, and so on. From the vast volume and variety of these data emerges the need for the employment of big data techniques and analytics in the context of state-of-the-art intelligent transportation systems (ITS). Moreover, the scalability needs of fleet and traffic management systems point to the direction of designing and deploying distributed architecture solutions that can be expanded in order to avoid technological and/or technical entrapments. Based on the needs and gaps detected in the literature as well as the available technologies for data gathering, storage and analysis for ITS, the aim of this study is to provide a distributed architecture platform to address these deficiencies. The architectural design of the system proposed, engages big data frameworks and tools (e.g., NoSQL Mongo DB, Apache Hadoop, etc.) as well as analytics tools (e.g., Apache Spark). The main contribution of this study is the introduction of a holistic platform that can be used for the needs of the ITS domain offering continuous collection, storage and data analysis capabilities. To achieve that, different modules of state-of-the-art methods and tools were utilized and combined in a unified platform that supports the entire cycle of data acquisition, storage and analysis in a single point. This leads to a complete solution for ITS applications which lifts the limitations imposed in legacy and current systems by the vast amounts of rapidly changing data, while offering a reliable system for acquisition, storage as well as timely analysis and reporting capabilities of these data.

Simulation of Logistics Delay in Bayesian Network Control Based on Genetic EM Algorithm

With the continuous development of e-commerce, the logistics industry is thriving, and logistics delays have become an issue that deserves more and more attention. Genetic EM algorithm is a genetic EM algorithm that is an iterative optimization strategy algorithm that can be used to solve the high-quality algorithm of travel problems with many nodes. Bayesian network (BN) is a network model based on probabilistic uncertainty. This article aims to study the probability of many factors that cause logistics delays to construct an algorithm model to control or reduce logistics delays. This paper constructs an EY model (That is the abbreviation of BN model based on genetic EM algorithm) based on the genetic EM algorithm, and conducts related simulation experiments based on the model to verify the accuracy and feasibility of the model. The experimental results of this paper show that the calculation efficiency of the EY model is significantly improved, and the actuarial accuracy is as high as 98%, which can effectively control logistics delays.

Driving Behavior Analysis of City Buses Based on Real-Time GNSS Traces and Road Information

The driving behavior of bus drivers is related to the safety of all passengers and regulation of urban traffic. In order to analyze the relevant characteristics of speed and acceleration, accurate bus trajectories and patterns are essential for driver behavior analysis and development of effective intelligent public transportation. Exploiting real-time vehicle tracking, this paper develops a platform with vehicle-mounted terminals using differential global navigation satellite system (DGNSS) modules for driver behavior analysis. The DGNSS traces were used to derive the vehicle trajectories, which were then linked to road information to produce speed and acceleration matrices. Comprehensive field tests were undertaken on multiple bus routes in urban environments. The spatiotemporal results indicate that the platform can automatically and accurately extract the driving behavior characteristics. Furthermore, the platform’s visual function can be used to effectively monitor driving risks, such as speeding and fierce acceleration, in multiple bus routes. The details of the platform’s features are provided for intelligent transport system (ITS) design and applications.

Vehicular Traffic Congestion Classification by Visual Features and Deep Learning Approaches: A Comparison

Automatic traffic flow classification is useful to reveal road congestions and accidents. Nowadays, roads and highways are equipped with a huge amount of surveillance cameras, which can be used for real-time vehicle identification, and thus providing traffic flow estimation. This research provides a comparative analysis of state-of-the-art object detectors, visual features, and classification models useful to implement traffic state estimations. More specifically, three different object detectors are compared to identify vehicles. Four machine learning techniques are successively employed to explore five visual features for classification aims. These classic machine learning approaches are compared with the deep learning techniques. This research demonstrates that, when methods and resources are properly implemented and tested, results are very encouraging for both methods, but the deep learning method is the most accurately performing one reaching an accuracy of 99.9% for binary traffic state classification and 98.6% for multiclass classification.