Near future travel-time information is one of the most critical factors that travellers consider before making trip decisions. In efforts to provide more reliable future travel-time estimations, transportation engineers have examined various techniques developed in the last three decades. However, there have not been sufficiently systematic and through reviews so far. In order to effectively support various transportation strategies and applications including Intelligent Transportation Systems (ITS), it is necessary to apply appropriate forecasting methods for matching circumstances in a timely manner. This paper conducts a comprehensive review study focusing on literatures, including modern techniques proposed recently, related to travel time and traffic condition predictions that are based on ‘data-driven' approaches. Based on the underlying mechanisms and theoretical principles, different approaches are categorized as parametric (linear regression and time series) and non-parametric approaches (artificial intelligence and pattern searching). Then, the approaches are analysed for their strengths, potential weaknesses, and performances from five main perspectives that are prediction range, accuracy, efficiency, applicability, and robustness.

This paper presents the development of an integrated microscopic mobility simulator, SimMobility Short-Term (ST). The simulator is integrated because its models, inputs and outputs, simulated components, and code base are integrated within a multiscale agent- and activity-based simulation platform capable of simulating different spatiotemporal resolutions and accounting for different levels of travelers’ decision making. The simulator is microscopic because both the demand (agents and its trips) and the supply (trip realization and movements on the network) are microscopic (i.e., modeled individually). Finally, the simulator has mobility because it copes with the multimodal nature of urban networks and the need for the flexible simulation of innovative transportation services, such as on-demand and smart mobility solutions. This paper follows previous publications that describe SimMobility’s overall framework and models. SimMobility is an open-source, multiscale platform that considers land use, transportation, and mobility-sensitive behavioral models. SimMobility ST aims at simulating the high-resolution movement of agents (traffic, transit, pedestrians, and goods) and the operation of different mobility services and control and information systems. This paper presents the SimMobility ST modeling framework and system architecture and reports on its successful calibration for Singapore and its use in several scenarios of innovative mobility applications. The paper also shows how detailed performance measures from SimMobility ST can be integrated with a daily activity and mobility patterns simulator. Such integration is crucial to model accurately the effect of different technologies and service operations at the urban level, as the identity and preferences of simulated agents are maintained across temporal decision scales, ensuring the consistency and accuracy of simulated accessibility and performance measures of each scenario.

Having access to the future traffic state information is crucial in maintaining successful intelligent transportation systems (ITS). However, predicting the future traffic state is a challenging research subject involving prediction reliability issues. Predictive performance measures, including the accuracy, efficiency, and stability, are generally considered as the most important priorities in the evaluation of prediction modules. Researchers have developed various K-nearest-neighbors-based searching algorithms that find the future state from the historical traffic patterns. Interestingly, there has not been sufficient effort made for improving the performance. For the emerging big data era, incorporating an efficient search strategy has become increasingly important since the applicability of the prediction module in ITS heavily relies on the efficiency of the searching method used. This paper develops a novel sequential search strategy for traffic state predictions. The proposed sequential strategy is found to be outperforming the conventional single-level search approach in terms of prediction measures, which are prediction accuracy, efficiency, and stability. Compared with the conventional approach, the proposed sequential method yields significantly more accurate results via internal hierarchical improvements across sublevels while maintaining excellent efficiency and stability.

Capacity drop, which is defined as discharge flow drop after bottleneck activation, has been frequently observed on urban highways, especially in merging sections. Maintaining high capacity on roadways is a main concern for traffic operators, theorists, and transportation modelers. Accordingly, many researchers have investigated capacity drop, yet highway capacity and discharge flow measurement methods vary, and results are not comparable. A systematic methodology is introduced for finding capacity drops by using detector data to estimate roadway capacity and discharge flow. The impact of the number of lanes on capacity drops at merging sections on highways is investigated. Results show that capacity drop is negatively related to the number of lanes. Detailed information is analyzed for individual lanes and off-ramp effect on capacity drop. Individual lane analysis supports the negative relationship between the amount of capacity drop and the number of lanes. A decrease in capacity drop is observed when the flow ratio of the off-ramp increases.