A Deep Learning Approach For Spatiotemporal Data Driven Traffic State Estimation
Download A Deep Learning Approach For Spatiotemporal Data Driven Traffic State Estimation PDF/ePub or read online books in Mobi eBooks. Click Download or Read Online button to get A Deep Learning Approach For Spatiotemporal Data Driven Traffic State Estimation book now. This website allows unlimited access to, at the time of writing, more than 1.5 million titles, including hundreds of thousands of titles in various foreign languages.
A Deep Learning Approach for Spatiotemporal-data-driven Traffic State Estimation
The past decade witnessed rapid developments in traffic data sensing technologies in the form of roadside detector hardware, vehicle on-board units, and pedestrian wearable devices. The growing magnitude and complexity of the available traffic data has fueled the demand for data-driven models that can handle large scale inputs. In the recent past, deep-learning-powered algorithms have become the state-of-the-art for various data-driven applications. In this research, three applications of deep learning algorithms for traffic state estimation were investigated. Firstly, network-wide traffic parameters estimation was explored. An attention-based multi-encoder-decoder (Att-MED) neural network architecture was proposed and trained to predict freeway traffic speed up to 60 minutes ahead. Att-MED was designed to encode multiple traffic input sequences: short-term, daily, and weekly cyclic behavior. The proposed network produced an average prediction accuracy of 97.5%, which was superior to the compared baseline models. In addition to improving the output performance, the model’s attention weights enhanced the model interpretability. This research additionally explored the utility of low-penetration connected probe-vehicle data for network-wide traffic parameters estimation and prediction on freeways. A novel sequence-to-sequence recurrent graph networks (Seq2Se2 GCN-LSTM) was designed. It was then trained to estimate and predict traffic volume and speed for a 60-minute future time horizon. The proposed methodology generated volume and speed predictions with an average accuracy of 90.5% and 96.6%, respectively, outperforming the investigated baseline models. The proposed method demonstrated robustness against perturbations caused by the probe vehicle fleet’s low penetration rate. Secondly, the application of deep learning for road weather detection using roadside CCTVs were investigated. A Vision Transformer (ViT) was trained for simultaneous rain and road surface condition classification. Next, a Spatial Self-Attention (SSA) network was designed to consume the individual detection results, interpret the spatial context, and modify the collective detection output accordingly. The sequential module improved the accuracy of the stand-alone Vision Transformer as measured by the F1-score, raising the total accuracy for both tasks to 96.71% and 98.07%, respectively. Thirdly, a real-time video-based traffic incident detection algorithm was developed to enhance the utilization of the existing roadside CCTV network. The methodology automatically identified the main road regions in video scenes and investigated static vehicles around those areas. The developed algorithm was evaluated using a dataset of roadside videos. The incidents were detected with 85.71% sensitivity and 11.10% false alarm rate with an average delay of 27.53 seconds. In general, the research proposed in this dissertation maximizes the utility of pre-existing traffic infrastructure and emerging probe traffic data. It additionally demonstrated deep learning algorithms’ capability of modeling complex spatiotemporal traffic data. This research illustrates that advances in the deep learning field continue to have a high applicability potential in the traffic state estimation domain.
Road Traffic Modeling and Management
Road Traffic Modeling and Management: Using Statistical Monitoring and Deep Learning provides a framework for understanding and enhancing road traffic monitoring and management. The book examines commonly used traffic analysis methodologies as well the emerging methods that use deep learning methods. Other sections discuss how to understand statistical models and machine learning algorithms and how to apply them to traffic modeling, estimation, forecasting and traffic congestion monitoring. Providing both a theoretical framework along with practical technical solutions, this book is ideal for researchers and practitioners who want to improve the performance of intelligent transportation systems. - Provides integrated, up-to-date and complete coverage of the key components for intelligent transportation systems: traffic modeling, forecasting, estimation and monitoring - Uses methods based on video and time series data for traffic modeling and forecasting - Includes case studies, key processes guidance and comparisons of different methodologies
Deep Learning for Earth Observation and Climate Monitoring
Deep Learning for Earth Observation and Climate Monitoring bridges the gap between deep learning and the Earth sciences, offering cutting-edge techniques and applications that are transforming our understanding of the environment. With a focus on practical scenarios, this book introduces readers to the fundamental concepts of deep learning, from classification and image segmentation to anomaly detection and domain adaptability. The book includes practical discussion on regression, parameter retrieval, forecasting, and interpolation, among other topics. With a solid foundational theory, real-world examples, and example codes, it provides a full understanding of how intelligent systems can be applied to enhance Earth observation and especially climate monitoring.This book allows readers to apply learning representations, unsupervised deep learning, and physics-aware models to Earth observation data, enabling them to leverage the power of deep learning to fully utilize the wealth of environmental data from satellite technologies. - Introduces deep learning for classification, covering recent improvements in image segmentation and encoding priors, anomaly detection and target recognition, and domain adaptability - Includes both learning representations and unsupervised deep learning, covering deep learning picture fusion, regression, parameter retrieval, forecasting, and interpolation from a practical standpoint - Provides a number of physics-aware deep learning models, including the code and the parameterization of models on a companion website, as well as links to relevant data repositories, allowing readers to test techniques themselves