Short-term prediction of vehicle waiting queue at ferry terminal based on machine learning method

Ferry service plays an important role in several cities with waterfront areas. Transportation authorities often need to forecast volumes of vehicular traffic in queues waiting to board ships at ferry terminals to ensure sufficient capacity and establish schedules that meet demand. Several previous studies have developed models for long-term vehicle queue length prediction at ferry terminals using terminal operation data. Few studies, however, have been undertaken for short-term vehicular queue length prediction. In this study, machine learning methods including the artificial neural network (ANN) and support vector machine (SVM) are applied to predict vehicle waiting queue lengths at ferry terminals. Through time series analysis, the existence of a periodic queue-length pattern is established. Hence, methodologies used in this study take into account periodic features of vehicle queue data at terminals for prediction. To further consider the cyclical characteristics of vehicle queue data at ferry terminals, a prediction approach is proposed to decompose vehicle waiting queue length into two components: a periodic part and a dynamic part. A trigonometric regression function is introduced to capture the periodic component, and the dynamic part is modeled by SVM and ANN models. Moreover, an assembly technique for combining SVM and ANN models is proposed to aggregate multiple prediction models and in turn achieve better results than could be attained from a lone predictive method. The prediction results suggest that for multi-step ahead vehicle queue length prediction at ferry terminals, the ensemble model outperforms the separate prediction models and the hybrid models, especially as prediction step size increases. This research has important practical significance to both traffic service management interests and the travelers in cities along waterfront areas.     

Workshop report - System development

The workshop considered system development as a key element of improving the performance of public transport. The main theme was the governance of decision making, design and development of public transport projects. A first main finding is that governance should be improved to keep focus on the original values for which the projects are started. Many projects lose sight of their original aims through the long and often problematic process from inception to operation. A second main finding is that the technological choice, mainly between rubber on tarmac and steel on rails, can be postponed, as both technologies start to overlap in their capacities. A stronger focus on functional needs in the earlier phases of the projects could help. Finally, as the different technologies provide similar options and can be used interchangeably, communicating the service they provide in other ways then through vehicle and infrastructure technology becomes more important.     

长大桥梁工程的先进节段预制技术及其应用

桥梁,作为基础设施的核心部分之一,在高速铁路、高速公路、城市地铁或轻轨国家交通网络的发展中扮演了重要角色.在中国高速铁路、高速公路或客运专线交通基础设计建设中,桥梁的设计和施工经常成为决定性因素.在过去的几十年中,桥梁设计者和建造者把节段预制技术(例如,小节段混凝土精确预制、大尺寸混凝土预制和大尺度钢结构预制)推进到了一个新高度,为交通领域的决策者提供了坚实的技术平台.本文简要介绍了这种先进的预制节段技术及其在世界范围内的著名应用范例.     

Inverse discrete choice modelling: theoretical and practical considerations for imputing respondent attributes from the patterns of observed choices

ABSTRACT

The growing availability of geotagged big data has stimulated substantial discussion regarding their usability in detailed travel behaviour analysis. Whilst providing a large amount of spatio-temporal information about travel behaviour, these data typically lack semantic content characterising travellers and choice alternatives. The inverse discrete choice modelling (IDCM) approach presented in this paper proposes that discrete choice models (DCMs) can be statistically inverted and used to attach additional variables from observations of travel choices. Suitability of the approach for inferring socioeconomic attributes of travellers is explored using mode choice decisions observed in London Travel Demand Survey. Performance of the IDCM is investigated with respect to the type of variable, the explanatory power of the imputed variable, and the type of estimator used. This method is a significant contribution towards establishing the extent to which DCMs can be credibly applied for semantic enrichment of passively collected big data sets while preserving privacy.     

High-resolution surveys of the biogeochemistry of the New England shelfbreak front during Summer, 2002

We present the observations from a pair of field experiments at the New England shelfbreak front in June and August of 2002, each consisting of 14 cross-frontal surveys using the Lamont Pumping SeaSoar. Measurements of the front's physical, chemical, and bio-optical characteristics were made at high spatial and temporal resolution. The front, based on water-column hydrographic distributions, was found within a few km of the 200 m isobath during both cruises. We present here composite sections, based on averages of individual sections shifted in space to a common frontal location, of the cross-frontal distributions of these properties as a measure of the mean state of the front in both June and August. The observations show the familiar temperature, salinity, and density distributions of the summertime front, dominated by surface thermal heating. Nutrient and bio-optical distributions show the combined effects of water-mass exchange and biological processes. T, S, silicate, and phosphate distributions are suggestive of cross-frontal exchange of slope- and shelf waters, although transport mechanisms and pathways are not apparent. These properties, along with nitrate and optical measures of the suspended particle distributions, show vertical displacements of isopleths as the front is approached: property contours slope upwards toward the front from the shoreward side, and downwards toward the front from the seaward side. Again, actual water-movement pathways are not constrained by these suggestive patterns. Bio-optical distributions show elevated indicators of photosynthetic efficiency both seaward and shoreward of the front, but the front itself is a minimum in biomass. Accumulation of photosynthetic biomass appears to be controlled primarily by nitrate scarcity in waters within and above the pycnocline. At the base of the pycnocline, light limitation appears to be the controlling factor, although the base of the euphotic zone is deeper than the biomass maxima and the base of the pycnocline. Mechanisms explaining this phenomenon are unclear, but tenuous evidence suggests low stratification at the depth of the 1% light level may not allow phytoplankton to optimize for the low-light, high-nutrient conditions at depth. Cross-frontal differences in nutrient and bio-optical parameters, particularly in August, suggest distinct phytoplankton assemblages, and the presence of calcite-forming or nitrogen fixing groups to the community structure, especially in very shallow waters across the front and in pycnocline waters seaward of the front.     

Cross-shelf circulation and phytoplankton distribution at the summertime New England shelfbreak front

We investigate aspects of the secondary (cross-shelf) circulation at the Middle Atlantic Bight shelfbreak front using high-resolution data collected on the New England Shelf in August 2002. The alongshore shelfbreak jet coincides with the front at the seaward edge of the cold pool (remnant winter shelf water) and there is a suggestion of a cross-stream convergence centered at the jet core. Despite indications of convergence we found no evidence of a surface subduction on the seaward side of the front. At depth 70 m near the shelfbreak there was a patch of chlorophyll, located within a local temperature–salinity maximum which, though significantly below the euphotic zone, appeared to be photo-acclimated and viable. The chlorophyll feature could be the result of a local subduction by a larger scale eddy circulation seaward of the front.Dye tracer experiments directly observed the convergence at the foot of the shelfbreak front and subsequent upwelling of bottom boundary layer water along the shoreward side of the shelfbreak front. But, we found no evidence that this upwelling influenced productivity at the front. Further, since there was no cross-shelf maximum in subsurface chlorophyll at the front, we conclude that this productivity is in general, sustained by a broadly distributed local vertical nutrient flux from an underlying nutrient reservoir.     

关于桥面防水和沥青面层的设计与规范

该文简述了桥面防水层对桥梁结构的重要作用,阐述了设计桥面铺装时应考虑的面层厚度、压实及水的影响等因素,并介绍了防水膜沥青体系及液态聚合物体系。     

Development and evaluation of a hybrid travel time forecasting model

The purpose of this paper is to develop and evaluate a hybrid travel time forecasting model with geographic information systems (GIS) technologies for predicting link travel times in congested road networks. In a separate study by You and Kim (cf. You, J., Kim, T.J., 1999b. In: Proceedings of the Third Bi-Annual Conference of the Eastern Asia Society for Transportation Studies, 14–17 September, Taipei, Taiwan), a non-parametric regression model has been developed as a core forecasting algorithm to reduce computation time and increase forecasting accuracy. Using the core forecasting algorithm, a prototype hybrid forecasting model has been developed and tested by deploying GIS technologies in the following areas: (1) storing, retrieving, and displaying traffic data to assist in the forecasting procedures, (2) building road network data, and (3) integrating historical databases and road network data. This study shows that adopting GIS technologies in link travel time forecasting is efficient for achieving two goals: (1) reducing computational delay and (2) increasing forecasting accuracy.     

A critical examination of an airport noise mitigation scheme and an aircraft noise charge: the case of capacity expansion and externalities at Sydney (Kingsford Smith) airport

In the wake of the Australian airline liberalization in 1990 and its forecasted impact on air traffic, capacity has been expanded at Sydney (Kingsford Smith) airport (Sydney KSA) – Australia's busiest commercial airport – with the construction of the third runway in 1994. Coinciding with the approval for this capacity expansion, the Commonwealth Government amended the Federal Airports Corporation (FAC) Act to direct the FAC to carry out activities which protect the environment from the effects of aircraft operations, with the cost to be borne by the airline industry according to the ‘Polluter Pays Principle'. Noise management plans were part of the conditions for developmental approval for a third runway. To this end, since 1995, Sydney KSA imposes a noise levy designed to generate sufficient revenues to fund a noise mitigation scheme. Although the issues of aircraft noise, in particular its impact on property values and land use planning around the airport, have been extensively addressed in the literature, no one has empirically examined the implications of new environmental policies in conjunction with airline liberalization and change in airport infrastructure. Principles and policy analyses are discussed in this paper. By focusing on the specifics of Sydney KSA, broader policy issues likely to be relevant for other major airports around the world are discussed.     

Cycling to work in 90 large American cities: new evidence on the role of bike paths and lanes

This article analyzes the variation in bike commuting in large American cities, with a focus on assessing the influence of bike paths and lanes, which have been the main approach to increasing cycling in the USA. To examine the role of cycling facilities, we used a newly assembled dataset on the length of bike lanes and paths in 2008 collected directly from 90 of the 100 largest U.S. cities. Pearson’s correlation, bivariate quartile analysis, and two different types of regressions were used to measure the relationship between cycling levels and bikeways, as well as other explanatory and control variables. Ordinary Least Squares and Binary Logit Proportions regressions confirm that cities with a greater supply of bike paths and lanes have significantly higher bike commute rates—even when controlling for land use, climate, socioeconomic factors, gasoline prices, public transport supply, and cycling safety. Standard tests indicate that the models are a good fit, with R ² ranging between 0.60 and 0.65. Computed coefficients have the expected signs for all variables in the various regression models, but not all are statistically significant. Estimated elasticities indicate that both off-street paths and on-street lanes have a similar positive association with bike commute rates in U.S. cities. Our results are consistent with previous research on the importance of separate cycling facilities and provide additional information about the potentially different role of paths vs. lanes. Our analysis also revealed that cities with safer cycling, lower auto ownership, more students, less sprawl, and higher gasoline prices had more cycling to work. By comparison, annual precipitation, the number of cold and hot days, and public transport supply were not statistically significant predictors of bike commuting in large cities.