Direct generation of level of service maps from images using convolutional and long short-term memory networks

Congestion in transport stations could result in stampede development and deadly crush situations. Closed circuit television (CCTV) cameras enable station managers to monitor the crowd and reduce overcrowding risks. However, identifying congestion conditions is a very laborious task for a human operator who has to monitor multiple locations at the same time. This paper presents a new approach to automated image-based identification of congestion as measured by level of service (LOS), which is the most widely accepted standard for measuring congestion. Existing methods for measuring LOS based on crowd density estimation from images have the disadvantages that, crowd density cannot be estimated accurately. In addition, the calculation of flow parameters involves a complex process, and consequently these parameters are not indicative of congestion in real-time. This paper proposes a novel method based on machine learning to directly classify LOS without calculating flow parameters. In the proposed method, visual features extracted by a deep convolutional neural network are classified using a support vector machine classifier and the classification results are further refined by using a long short-term memory network. A second contribution of this research is to develop a web-based LOS map visualization platform to monitor pedestrian distribution and variation of distribution in real-time. Experimental evaluation at Flinders Street Station in Melbourne shows that this method can achieve an accuracy of 81.9% and efficiency of 0.40?seconds per frame in LOS classification using CCTV images.     

无目标语环境下的英语课堂焦虑和互动模式

在无目标语环境下,学生的课堂参与是目的语口头输出和操练的主要途径.焦虑是影响学生课堂口头参与的主要因素之一.本文通过问卷调查和课堂观察等实证方法,研究了学生课堂焦虑水平对其在小组活动、全班活动、和教师引导活动等三种互动模式中参与频率的影响,并给出了教学启示.     

A simulation-based vessel-truck coordination strategy for lighterage terminals

Lighterage contributes significantly to the maritime industry since thousand tons of necessary supplies have to be delivered to mother vessels anchored near sea every day. A single lighter waits to receive cargoes from multiple suppliers at the berth, while the trucks wait for their turns to enter the terminal. Due to the limited space, the terminal operation becomes vulnerable to the lack of coordination of their arrivals. In this study, despite a traditional industry, we are interested in applying the emerging technologies to improve the operation efficiency. We develop a simulation-based coordination strategy to construct coordinated schedules for both the lighters and suppliers to reduce congestions in the lighterage terminal The discrete event simulation model is developed based on understanding the real-world terminal in Singapore, and the controlled arrival method, determining coordinated arrival schedules of trucks, is introduced and embedded to the simulation model. The simulation model is tuned up with a benchmark setting of 6-month historical data. To find the optimal strategy, an advanced bi-objective simulation optimization algorithm is employed. According to our findings, the proposed strategy could significantly improve the efficiency of both lighters and trucks in various indicators. At the end, a mobile application prototype is proposed to deliver the coordinated schedules to different parties, and improve the communication between parties.     

A note on the distortionary effects of revenue-neutral tolls in a bottleneck congestion game

This note demonstrates how the redistribution of revenue from a Pigouvian policy can distort incentives and handicap the social objectives of the policy by creating a moral hazard problem. Based on the Levinson (2005) game theory model, I develop a three-player bottleneck congestion game that emulates a repeated prisoner’s dilemma and derive efficient tolls. This conceptual game demonstrates the distortionary effects from a revenue-neutral toll policy with lump-sum revenue redistribution and the equity-efficiency tradeoff.     

Time-dependent area-based pricing for multimodal systems with heterogeneous users in an agent-based environment

In this paper, we investigate an area-based pricing scheme for congested multimodal urban networks with the consideration of user heterogeneity. We propose a time-dependent pricing scheme where the tolls are iteratively adjusted through a Proportional–Integral type feedback controller, based on the level of vehicular traffic congestion and traveler’s behavioral adaptation to the cost of pricing. The level of congestion is described at the network level by a Macroscopic Fundamental Diagram, which has been recently applied to develop network-level traffic management strategies. Within this dynamic congestion pricing scheme, we differentiate two groups of users with respect to their value-of-time (which related to income levels). We then integrate incentives, such as improving public transport services or return part of the toll to some users, to motivate mode shift and increase the efficiency of pricing and to attain equitable savings for all users. A case study of a medium size network is carried out using an agent-based simulator. The developed pricing scheme demonstrates high efficiency in congestion reduction. Comparing to pricing schemes that utilize similar control mechanisms in literature which do not treat the adaptivity of users, the proposed pricing scheme shows higher flexibility in toll adjustment and a smooth behavioral stabilization in long-term operation. Significant differences in behavioral responses are found between the two user groups, highlighting the importance of equity treatment in the design of congestion pricing schemes. By integrating incentive programs for public transport using the collected toll revenue, more efficient pricing strategies can be developed where savings in travel time outweigh the cost of pricing, achieving substantial welfare gain.     

Where are the dangerous intersections for pedestrians and cyclists: A colocation-based approach

Pedestrians and cyclists are vulnerable road users. They are at greater risk for being killed in a crash than other road users. The percentage of fatal crashes that involve a pedestrian or cyclist is higher than the overall percentage of total trips taken by both modes. Because of this risk, finding ways to minimize problematic street environments is critical. Understanding traffic safety spatial patterns and identifying dangerous locations with significantly high crash risks for pedestrians and cyclists is essential in order to design possible countermeasures to improve road safety. This research develops two indicators for examining spatial correlation patterns between elements of the built environment (intersections) and crashes (pedestrian- or cyclist-involved). The global colocation quotient detects the overall connection in an area while the local colocation quotient identifies the locations of high-risk intersections. To illustrate our approach, we applied the methods to inspect the colocation patterns between pedestrian- or cyclist-vehicle crashes and intersections in Houston, Texas and we identified among many intersections the ones that significantly attract crashes. We also scrutinized those intersections, discussed possible attributes leading to high colocation of crashes, and proposed corresponding countermeasures.     

A framework to evaluate policy options for supporting electric vehicles in urban freight transport

Electric vehicles (EVs) are considered as a feasible alternative to traditional vehicles. Few studies have addressed the impacts of policies supporting EVs in urban freight transport. To cast light on this topic, we established a framework combining an optimization model with economic analysis to determine the optimal behavior of an individual delivery service provider company and social impacts (e.g., externalities and welfare) in response to policies designed to support EVs, such as purchase subsidy, limited access (zone fee) to congestion/low-emission zones with exemptions for EVs, and vehicle taxes with exemptions for EVs. Numerical experiments showed that the zone fee can increase the company’s total logistics costs but improve the social welfare. It greatly reduced the external cost inside the congestion/low-emission zone with a high population, dense pollution, and heavy traffic. The vehicle taxes and subsidy were found to have the same influence on the company and society, although they have different effects with low tax/subsidy rates because their different effects on vehicle routing plans. Finally, we performed a sensitivity analysis. Local factors at the company and city levels (e.g., types of vehicle and transport network) are also important to designing efficient policies for urban logistics that support EVs.     

Probe data-driven travel time forecasting for urban expressways by matching similar spatiotemporal traffic patterns

Travel time is an effective measure of roadway traffic conditions. The provision of accurate travel time information enables travelers to make smart decisions about departure time, route choice and congestion avoidance. Based on a vast amount of probe vehicle data, this study proposes a simple but efficient pattern-matching method for travel time forecasting. Unlike previous approaches that directly employ travel time as the input variable, the proposed approach resorts to matching large-scale spatiotemporal traffic patterns for multi-step travel time forecasting. Specifically, the Gray-Level Co-occurrence Matrix (GLCM) is first employed to extract spatiotemporal traffic features. The Normalized Squared Differences (NSD) between the GLCMs of current and historical datasets serve as a basis for distance measurements of similar traffic patterns. Then, a screening process with a time constraint window is implemented for the selection of the best-matched candidates. Finally, future travel times are forecasted as a negative exponential weighted combination of each candidate’s experienced travel time for a given departure. The proposed approach is tested on Ring 2, which is a 32km urban expressway in Beijing, China. The intermediate procedures of the methodology are visualized by providing an in-depth quantitative analysis on the speed pattern matching and examples of matched speed contour plots. The prediction results confirm the desirable performance of the proposed approach and its robustness and effectiveness in various traffic conditions.     

Multi-day activity-travel pattern sampling based on single-day data

Although it is important to consider multi-day activities in transportation planning, multi-day activity-travel data are expensive to acquire and therefore rarely available. In this study, we propose to generate multi-day activity-travel data through sampling from readily available single-day household travel survey data. A key observation we make is that the distribution of interpersonal variability in single-day travel activity datasets is similar to the distribution of intrapersonal variability in multi-day. Thus, interpersonal variability observed in cross-sectional single-day data of a group of people can be used to generate the day-to-day intrapersonal variability. The proposed sampling method is based on activity-travel pattern type clustering, travel distance and variability distribution to extract such information from single-day data. Validation and stability tests of the proposed sampling methods are presented.