Hybrid approaches based on SARIMA and artificial neural networks for inspection time series forecasting

In this paper, the number of goods subject to inspection at European Border Inspections Post are predicted using a hybrid two-step procedure. A hybridization methodology based on integrating the data obtained from autoregressive integrated moving averages (SARIMA) model in the artificial neural network model (ANN) to predict the number of inspections is proposed. Several hybrid approaches are compared and the results indicate that the hybrid models outperform either of the models used separately. This methodology may become a powerful decision-making tool at other inspection facilities of international seaports or airports.     

基于ABC和BP神经网络的铁路货运成本预测研究

运用作业成本法,结合BP神经网络理论建立铁路货运成本预测模型。通过案例分析,得出BP神经网络可以更准确的预测铁路货运成本费用的结论。     

Cargo market competition among Asia Pacific's major airports

Globalization and the ensuing changes in the supply chain network have strengthened competition among airports. For this study, we selected 13 primary airports in Asia Pacific, and investigated their competition, airport hierarchy, and competitive potential in cargo markets in terms of demand and supply. Specifically, we examined indicators including flight frequency, route distributions, composition of flag carriers, international trade, and centrality of the selected airports. The results revealed that Taiwan Taoyuan International Airport (TPE), Hong Kong International Airport (HKG), Shanghai Pudong International Airport (PVG), and Incheon International Airport (ICN) had the greatest competitive advantage of distinct developmental patterns. Compared with TPE and ICN, which are national-carrier-oriented airports, HKG and PVG have been developed efficiently in the network of both national and foreign carriers. Although TPE and ICN perform well in the networks of conventional carriers, PVG is competitive in the network of all-freight carriers, and HKG performs efficiently in both the networks of the conventional and all-freight carriers. Overall, Hong Kong International Airport has been prominent in the Asia–Pacific air-cargo market. Nevertheless, considering the networks of the integrator carriers, Chinese airports have the most potential in this region.     

A data-driven operational model for traffic at the Dallas Fort Worth International Airport

Airports are on the front line of significant innovations, allowing the movement of more people and goods faster, cheaper, and with greater convenience. As air travel continues to grow, airports will face challenges in responding to increasing passenger vehicle traffic, which leads to lower operational efficiency, poor air quality, and security concerns. This paper evaluates methods for traffic demand forecasting combined with traffic microsimulation, which will allow airport operations staff to accurately predict traffic and congestion. Using two years of detailed data describing individual vehicle arrivals and departures, aircraft movements, and weather at Dallas-Fort Worth (DFW) International Airport, we evaluate multiple prediction methods including the Auto Regressive Integrated Moving Average (ARIMA) family of models, traditional machine learning models, and DeepAR, a modern recurrent neural network (RNN). We find that these algorithms are able to capture the diurnal trends in the surface traffic, and all do very well when predicting the next 30 minutes of demand. Longer forecast horizons are moderately effective, demonstrating the challenge of this problem and highlighting promising techniques as well as potential areas for improvement.Traffic demand is not the only factor that contributes to terminal congestion, because temporary changes to the road network, such as a lane closure, can make benign traffic demand highly congested. Combining a demand forecast with a traffic microsimulation framework provides a complete picture of traffic and its consequences. The result is an operational intelligence platform for exploring policy changes, as well as infrastructure expansion and disruption scenarios. To demonstrate the value of this approach, we present results from a case study at DFW Airport assessing the impact of a policy change for vehicle routing in high demand scenarios. This framework can assist airports like DFW as they tackle daily operational challenges, as well as explore the integration of emerging technology and expansion of their services into long term plans.     

Cascading failures in airport networks

Cascading failure phenomena can appear in complex networks that distribute flows of information, people or goods, when flow going through nodes or edges exceeds the capacity of network nodes or edges. Cascading failure models from previous research are not adequate for airport networks, as flow is not continuous, and load has to be redistributed among close airports, rather than previously existing connections. With these constraints in mind, we have defined an algorithm to simulate the management of cascading failures in airport networks. We use the algorithm to evaluate the effectiveness of several selection rules of alternative departure and arrival airports to affected flights to reduce the impact of the cascading failure. We have applied the algorithm to the Oceanic Airport Network to assess the impact of several incidents. Results show that selection rules of arriving airports have significant impact in reducing the effect of incidents affecting central airports.     

Identification model development for proactive response on irregular operations (IROPs)

The demand for air transportation service in Korea has been increasing rapidly, while the airport operation system has become even further advanced and complex. Accordingly, concerns regarding negative ripple effects, such as damage caused by flight delays or cancellations due to irregular operations (IROPs) of airports, have been amplifying. The IROPs is being newly defined, and guidelines for establishing a response system are being proposed in the U.S. and the U.K. However, studies in relation to preemptive and predictive responses aimed at minimizing the negative impacts, such as to analyze ripple effects generated after an incident, have not been sufficiently conducted. Accordingly, this study was conducted to analyze the ripple effects of IROPs according to severity and duration time, and to thus suggest a methodology to enable predictive response. The situation of IROPs was simulated and analyzed using the tower log data of 2015 from Jeju International Airport (CJU), Gimpo International Airport (GMP), and Gimhae International Airport (PUS) in Korea. The five-level classification for IROPs was then suggested using the K-means algorithm. The methodology suggested was verified for applicability to actual airport operation through scenario analysis. It is expected to serve as a framework for establishing the quantitative standards for goal setting with which airport operators solve the situation of IROPs.     

A Comparative Analysis of Three Types of Tourism Demand Forecasting Models: Individual,Linear Combination and Non‐linear Combination

This paper investigates the combination of individual forecasting models and their roles in improving forecasting accuracy and proposes two non‐linear combination forecasting models using Radial Basis Function and Support Vector Regression neural networks. These two non‐linear combination models plus the standard Multi‐layer Perceptron neural network‐based non‐linear combination model are examined and compared with the linear combination models. The UK inbound tourism quarterly arrival data is used and the empirical results demonstrate that the proposed non‐linear combination models are robust and outperform the linear combination models that currently dominate in the tourism forecasting literature. Copyright © 2013 John Wiley & Sons, Ltd.     

Tourism Demand Forecasting with Neural Network Models: Different Ways of Treating Information

This paper aims to compare the performance of three different artificial neural network techniques for tourist demand forecasting: a multi‐layer perceptron, a radial basis function and an Elman network. We find that multi‐layer perceptron and radial basis function models outperform Elman networks. We repeated the experiment assuming different topologies regarding the number of lags used for concatenation so as to evaluate the effect of the memory on the forecasting results. We find that for higher memories, the forecasting performance obtained for longer horizons improves, suggesting the importance of increasing the dimensionality for long‐term forecasting. Copyright © 2014 John Wiley & Sons, Ltd.     

Applying deep learning models to twitter data to detect airport service quality

Measuring airport service quality (ASQ) is an important process for identifying shortages and suggesting improvements that guide management decisions. This research, introduces a general framework for measuring ASQ using passengers’ tweets about airports. The proposed framework considers tweets in any language, not just in English, to support ASQ evaluation in non-speaking English countries where passengers communicate with other languages. Accordingly, this work uses a large dataset that includes tweets in two languages (English and Arabic) and from four airports. Additionally, to extract passenger evaluations from tweets, our framework applies two different deep learning models (CNN and LSTM) and compares their results. The two models are trained with both general data and data from the aviation domain in order to clarify the effect of data type on model performance. Results show that better performance is achieved with the LSTM model when trained with domain specific data. This study has clear implications for researchers and airport managers aiming to use alternative methods to measure ASQ.     

Corridors,hybrids and networks: three global development strategies for high speed rail

After 50 years of experience with high-speed rail (HSR) development in Asia and Europe, there are important lessons that can be derived to inform future efforts to introduce HSR. This paper identifies and explores three strategic models of HSR development: (1) exclusive corridors (e.g., Japan), (2) hybrid networks—both national (e.g., France and Germany) and international (e.g., European Union), and (3) comprehensive national networks (e.g., China and Spain). Evaluations of these models yield outcomes that range from generally positive assessments of the corridor and national hybrid models to more concerns and uncertainties about the international hybrid and comprehensive national network models. When applying these lessons to the United States, contextual differences can make direct applications problematic. At the same time, though, certain elements of these three models that have been proven to be successful elsewhere may be adaptable to the U.S. and other newcomers to HSR development.     

Runway capacity management – An empirical study with application to Doha International Airport

This paper examines a three-faceted approach for runway capacity management, based on the runway configuration, a chosen scheduling approach, and an aircraft separation standard. These factors prompt alternative runway settings that are encapsulated using a classical mixed-integer formulation. The optimal solution for each runway setting is compared against our proposed optimization-based heuristic. This integrated approach is applied to investigating the transition from the (Old) Doha International Airport to the New Doha International Airport. Our empirical study based on historical data reveals that the proposed heuristic consistently yields optimal or near-optimal schedules, with considerable savings in fuel cost and reductions in delays, while preserving the spirit of an FCFS sequencing policy.     

Relaxing the perimeter and high-density rules: implications for Washington Dulles International Airport

The Perimeter and High-Density Rules have been the foundation upon which the physically limited capacity of Ronald Reagan Washington National Airport has been allocated. The perimeter rule at National Airport requires nonstop scheduled airline flights from that airport to serve destinations within a 1250-mile perimeter. The distance limit was initially introduced for a combination of reasons including environmental conservation (especially with respect to noise nuisance) and the desire to offer some protection for other airports in the Washington DC area as they built up traffic to reach a critical mass. The US Senate has recently taken actions to adjust the perimeter rule at National Airport. Any major relaxing of the rule will have implications for the other major airports in the National Capital Region; namely Washington Dulles International Airport and Baltimore–Washington International Airport. The resultant knock-on effects of this development on the wider economy of the region is examined here. The main attention of the paper is on the impact of any major change in the perimeter rule on Washington Dulles International Airport, and on the subsequent knock-on effects this would have on the region's employment level and structure.     

北京大兴国际机场轨道交通专线延时运营方案设计研究

随着北京大兴国际机场夜间到港旅客量的增加,机场轨道交通运营时长已难以满足客运需求。为提升线路服务水平,延长夜间运营时间,同时减少运力浪费,需要平衡线路夜间客运需求、维检修需求及运营成本,制定延时运营方案。通过挖掘北京大兴国际机场及大兴机场线客流变化规律,分析线路夜间客运需求,结合大兴机场线夜间维检修要求,探讨延时运营对设备设施作业的影响,并进一步研究延时运营成本的构成以及成本计算方式。最后通过对比、分析不同的延时运营方案对夜间维修时间的影响、增开列次与路网换乘情况、运营成本的增加情况,提出当前大兴机场线宜采取上行单向延长运营30 min的方案,并结合大兴机场线实际情况设计线路延时运营阶段的列车运行方案。     

Monte Carlo comes to Rome: a note on the estimation of unconstrained runway capacity at Rome Fiumucino International Airport

A new airport capacity concept has been advanced by the International Air Transport Association (IATA). Unconstrained capacity represents the airport capacity with reservoirs of traffic always available and the use of all planned technological and air traffic managerial improvements. To establish its utility and estimate its value for the first time, the case of Rome Fiumucino International Airport is examined.     

Efficiency drivers of international airports: A worldwide benchmarking study

The main purpose of these work was to identify operational efficiency drivers of international airports. In order to achieve this, a two-step quantitative-qualitative research approach was conducted. In the first step, a two-stage DEA model was used, and it was possible to identify, within a sample of the 60 biggest airports from the six Airport Council International (ACI) regions, the most efficient airports of the world: Beijing International Airport, Heathrow International Airport, Dubai International Airport, and Hartsfield-Jackson Atlanta International Airport. In the second step of the research, four airports were selected in order to search for the efficiency drivers. In this context, Heathrow International Airport was considered to be a benchmark and presented most of the identified efficiency drivers (27 of 31). Standing out were Just-in-Time (JIT) and Total Quality Management (TQM) principles and also Passenger boarding optimization, besides the presence of almost all of the most relevant efficiency drivers, according to airport managers.     

神经网络与四阶段预测法在铁路运量预测中的组合应用研究

利用神经网络与四阶段预测法组合构造出新的交通量预测模型,以胶济铁路提速改造为例,就构造的客运量预测模型进行了应用研究。其中以平均增长率法计算客流量的交通分布;以重力模型法计算诱发客流;依据运输阻力构建的分担率模型计算转移客流;在计算诱发客流时考虑了时间价值。     

Warehouse location problems for air freight forwarders: a challenge created by the airport relocation

The move of Hong Kong International Airport from the city centre to a suburban area in July 1998 provided sufficient capacity to meet the increasing demand of passenger and air-cargo flows in Hong Kong in the foreseeable future. However, the move has adverse side effects such as causing the readjustment of many existing systems and creating many imminent strategic problems. One of such problems is the warehouse location of freight forwarders: they have to decide whether they should locate their warehouses in the new airport, in current locations, or in new locations somewhere in the city. This paper delineates the results of a survey conducted in the summer of 1997 before the airport was relocated. The survey asked what decisions the freight forwarders had made and how they evaluated some potential warehouse locations. The paper also considers two mathematical models, which explain and predict, respectively, the location pattern of freight forwarder warehouses before and after the relocation of the airport.     

CO2 emissions associated with hubbing activities in air transport: an international comparison

Hubbing is an important operational practice in air transport. Many studies have been conducted to examine the benefits and impacts of hubbing from an economic perspective. However, its impact on CO₂ emissions, especially across different air spaces, is not well understood. This paper explores the impact of hubbing activities in air transport from an environmental perspective. With a detailed methodology and data from the Greek and Hong Kong/Sanya flight information regions (FIRs), three levels of CO₂ emissions are estimated: airport-based, airspace-based and flight-based. After contrasting the CO₂ emission efficiencies of Athens International Airport (AIA) and the Hong Kong International Airport (HKIA), aircraft type and flight distance are examined to explain their emission efficiency differences. It is found that HKIA is associated with poorer CO₂ emission efficiency at the airport and airspace levels because of the larger aircraft and longer flight distance. However, when CO₂ emission efficiency at the flight level is considered, HKIA, with a higher passenger load factor, performs better. Major international hub airports should implement additional environmental measures to minimize the impact of hubbing activities on CO₂ emissions at the airport and airspace levels.     

Strategic design of precautionary measures for airport passengers in times of global health crisis Covid 19: Parametric modelling and processing algorithms

Presently, the negative results of a pandemic loom in a threatening manner on an international scale. Facilities such as airports have contributed significantly to the global spread of the COVID-19 virus. Therefore, in order to address this challenge, studies on sanitary risk management and the proper application of countermeasures should be carried out. To measure the consequences over passenger flow, simulation modelling has been set up at Casablanca Mohammed V International Airport. Several scenarios using daily traffic data were run in different circumstances. This allowed the development of some assumptions regarding the overall capacity of the airport. The proposed simulations make it possible to calculate the number of passengers to be processed in accordance with the available check-in counters based on the proposed sanitary measures.     

Comparative analysis of efficiency for major Southeast Asia airports: A two-stage approach

Within the past few years, the economy of Southeast Asia has been expanding rapidly with the rise in demand for air transport services. International airports are important driving forces for Southeast Asia countries' economies. Therefore, the competitive ability of these airports is very essential in terms of development and competitiveness within the region. This paper investigates the capabilities of these airports by a two-stage approach. The strengths and weaknesses of each Southeast Asia airport are evaluated by Data Envelopment Analysis – Slack-Based Measurement (DEA-SBM) in the first stage. This is a non-parametric approach to measure the efficiency of 9 major airports in the area including Changi Airport (Singapore), Suvarnabhumi Airport (Thailand), Kuala Lumpur Airport (Malaysia), Soekarno Hatta Airport (Indonesia), Ninoy Aquino Airport (the Philippines), Noi Bai Airport, Tan Son Nhat Airport (Vietnam) and Guangzhou Baiyun Airport (China), Hong Kong Airport (Hong Kong). In the second stage, Tobit regression is used to estimate the influence of multiple factors toward the efficiency of each airport. By generalizing and comparing two stages, the analysis allows us to evaluate each airport's efficiency in seven years, as well as the impact of multiple factors in one airport's performance. The implications for improvement are also obtained and discussed.