Data is the foundation of various transportation studies. Traffic signal control is the core means of urban traffic operation. Over the past decade, the rapid development of Information and Communications Technologies provided the new opportunities for transportation research and practice. On one hand, a variety of newly emerged data such as crowdsourcing data, license plate recognition data and floating car data provided rich and solid foundation for traffic monitor, prediction and control. On the other, artificial intelligence technique provided new and rich tools for transportation community, greatly promoting the efficiency of transportation research and practice. This book, Traffic Information and Control, mainly focuses on the field of traffic information processing and signal control with the support of diverse traffic data.

Social media and other online websites have rich traffic information. How to extract and mine useful traffic information from online web data to address transportation problems has become a valuable and interesting research topic in current data-explosive era. In this chapter, we introduce a traffic analytic system with online web data. The proposed system can collect online data, use machine learning and natural language processing methods to extract traffic events, analyze traffic sentiment, and reason traffic scenarios. We also present some results based on the proposed system and techniques in practice.

Urban traffic is an important part of urban activities. With the rapid development of the economy and the advancement of urbanization in many cities, urban road systems experienced serious traffic congestions, which increases the traffic delay and fuel consumption, aggravates the vehicle exhaust and noise, and seriously damages the urban environment. In order to evaluate the congestion conditions of cities, macroscopic measurements are required to provide quantified indications on evaluating the traffic performance of cities.

Predicting short-term travel time with considerable accuracy and reliability is critically important for advanced traffic management and route planning in Intelligent Transportation Systems (ITS). Short-term travel-time prediction uses real travel-time values within a sliding time window to predict travel time one or several time step(s) in future. However, the nonstationary properties and abrupt changes of travel-time series make challenges in obtaining accurate and reliable predictions. Recent achievements of deep learning approaches in classification and regression shed a light on innovations of time series prediction. This study establishes a series of Long Short-Term Memory with Deep Neural Networks (LSTM-DNN) layers using 16 settings of hyperparameters and investigates their performance on a 90-day travel-time dataset from Caltrans Performance Measurement System (PeMS). Then competitive LSTM-DNN models are tested along with linear regression, Ridge and Lasso regression, ARIMA and DNN models under ten sets of sliding windows and predicting horizons via the same dataset. The results demonstrate the advantage of LSTM-DNN models while showing different characteristics of these deep learning models with different settings of hyper parameters, providing insights for optimizing the structures.

In this chapter, we have proposed a novel graph -based model with TS-TGAT to predict short-term traffic speed under both normal and abnormal traffic fl ow conditions. The novelty of the proposed prediction model is that it can learn both spatial and temporal propagation rules for traffic on a network. Important concepts and improvements are introduced to the model, for example node -level attention weights, multi -head attention and depth -wise separable CNN module to take account of the unique and complex interactions between traffic fl ows and traffic network characteristics. The proposed prediction model was trained and tested using ILDs on a section of the M25 motorway network just before the Dartford Crossing (between Dartford Tunnel and M25 J2 with all slip roads). In order to make the model generic and reusable, the model was trained using generic data (including both normal and abnormal traffic fl ow data) and was tested under mixed conditions and disrupted conditions. A selection of baseline methods was used to benchmark the proposed model performance, including HA, kNN, GBDTs and LSTM, some of which are state-of-the-art methods in the problem of short-term traffic prediction. The results have shown that the proposed TS-TGAT method outperforms other benchmarking methods under both normal and abnormal traffic conditions.

Traffic diversion is an effective measure to solve the incidental traffic congestion in urban expressway traffic system. By adopting the macroscopic traffic flow model METANET, this study analyses the state change of traffic flow on the road network and establishes the dynamic traffic diversion model, inducing the redistribution of traffic demand. Considering the changes in the amount of origin-destination (O-D) demand, diversion rate is introduced into the basic theory of dynamic O-D model, and then established a dynamic traffic flow model based on dynamic demand change. The genetic algorithm is used to solve the non-linearity problem of the objective function in the traffic diversion model. This study sets up five cases for numerical analyses, and gets the optimal diversion scheme.

Lane change maneuvers are main causes of traffic turbulence at highway bottlenecks. We propose a dynamic game framework to derive the system optimum strategy for a network of cooperative vehicles interacting at a merging bottleneck. Cooperative vehicles on the highway mainline seek for optimal strategies (i.e., whether and when to perform courtesy lane change to facilitate the merging vehicle) to minimize their cost, while taking into account potential future interactions at the merging section while minimizing the distance traveled on the acceleration lane. An optimal strategy is found by minimizing the joint cost of all interacting vehicles while respecting behavioral and physical constraints. Numerical examples show the feasibility of the approach in capturing the nature of conflict and cooperation during the merging process, and demonstrate the benefits of sharing information and cooperative control for connected and automated vehicles.

This chapter first reviewed recent advancements in cooperative driving at intersections and on-ramps and comprehensively introduced three cooperative driving strategies at intersections, namely, the safety driving pattern-based strategy, the reservation-based strategy and the trajectory optimization-based strategy, as well as two cooperative driving strategies at on -ramps, namely, the virtual vehicle mapping strategy and the lot-based strategy. Then, a novel concept, i.e., the lane change-free road transportation system, was newly proposed for the future world. This future road transportation system consists of a CI-A, a CMA, a CDA and a CACD strategy, and vehicles that move in such a road system are able to reach their destinations without making any on-road lane changes. It is expected that, through this system with no lane changes, the CAV technology could be greatly simplified and driving safety, as well as efficiency, could be improved.

With the development of edge computing, internet of things, connected vehicles and big traffic data, future urban traffic signal control will be improved in several aspects. Future urban traffic signal control systems will be a cooperative and network system, which contains abilities of detection data sharing, real-time optimization, synchronized control, comprehensive -monitoring, fault -tolerant and coordination evaluation. With these new features and functions, urban signal control systems will be intelligent and efficient.

This chapter briefs about the history of the development of signal coordination and the achievements so far in this field. The review on the field is focused on a methodology called MAXBAND and its various derivatives.

Emerging technologies and tools play a vital role for advancing the state of practice on signal timing and coordination. The discussions in this chapter primarily focused on addressing the four critical aspects and challenges facing management agencies and signal timing engineers: timing management and documentation, optimization without traffic volumes, trajectory -based timing diagnosis, and performance evaluation. Such emerging technologies and techniques help practitioners economize the laborious processes of the traditional signal timing process. It is anticipated that new technologies will continue to emerge and hold promises for significantly changing how traffic signal control issues are addressed. For example, with connected -vehicle technologies gaining increased market penetration, traffic flows would be predictable and guidable, which allow quicker and more accurate information exchange and signal control response. Although emerging technologies are promising, practitioners should not simply deem that such technologies would automatically achieve better results. A careful investigation before applying any technologies and a comprehensive performance evaluation after the implementation are always necessary.

Short-distance intersections are defined as intersection pairs with short link and strongly interact with each other, and they are often challenged with overflow due to the limited queuing length. In order to solve this kind of traffic bottleneck, a coordinated signal control method for short-distance intersections with dynamic reversible lanes on the link is proposed in this paper. The direction of the dynamic reversible lanes is switched in coordination to the signal phase in a signal cycle, which can increase the storage space of the link and enhance capacity in both directions to prevent overflow. Based on the signal sequence under counter-clockwise split phasing scheme, signal timing is modeled to avoid spillover on the link with clearance time prepared for the dynamic reversible lanes, which is calibrated and validated with VISSIM, a microscopic simulation modeling tool based on time interval and driving behavior, to significantly avoid spillover and reduce the number of vehicle stops. It is concluded that the coordinated control method for short-distance intersections with dynamic reversible lane performs better with a shorter link, fewer lanes, higher saturation or high left-turn ratio into the link. This research may provide insights on enhancing road capacity for short distance intersections.

This study evaluates the performance of an adaptive traffic signal control system (ATSCS) based on license plate recognition (LPR) detector data. The LPR detector data can provide abundant individual vehicle-based information for comprehensive, detailed evaluation of traffic signal control. Several measurements including travel time delay, cumulative travel time frequency diagram, Purdue coordination diagram, 95th percentile travel time, and buffer index are applied to reveal the various aspects of traffic signal control performance. A before and after comparison was conducted in the eastbound direction of a road segment, in which the ATSCS was deployed in October 2016 while the time-of-day traffic signal planning was used previously. Results show the improvement in traffic condition in the morning and evening peaks after the deployment of the ATSCS. However, the traffic condition at midnight worsened on certain days after the deployment of the ATSCS.

In the age of the explosion of new technology and information, traditional humandependent and feedback-based traffic engineering are rapidly stepping into the highly automated and data-rich stage with advanced technologies such as wireless communication and artificial intelligence. The book is organized in the following two parts to timely reflect the advancement of the modern traffic information technology and control.