39 research outputs found
Integrated surface and departure management at airports by optimization
No full textA key challenge in Air Traffic Management is to provide a swift flow of airplanes at and near the airports. The pressure on existing airports will be higher as demand of air transport is predicted to increase over the next decades. Airline companies compete on delivering improved departure and arrival punctuality for their flights. In this paper we present experimental results where we are comparing the performance of traditional tower control decisions versus decisions supported by optimization technology in a simulation environment. We present a mathematical model for the integrated departure management and surface management problem and a solution algorithm based on a heuristic decomposition of the integrated problem. This represents a first attempt to solve the two problems simultaneously. Our approach is designed for dynamic rescheduling and real-time environment, with corresponding response time requirements. Finally, we present computational results that show significant improvements in punctuality and reductions in taxi times. © 2013 IEEE
User Involvement in the Design of ML-Infused Systems
No full textAdvances in machine learning (ML) open up possibilities for better supporting the decision making that occurs in high-stakes domains such as air traffic management (ATM). The success of such decision-making systems highly depends upon end users’ involvement in their development process. However, most designers face challenges with finding appropriate ways of doing this. This paper presents our ongoing work to investigate design practices by reporting lessons learned from user involvement in the development of an ML-infused ATM decision support system. To explore if and how UX design methods need to be refined when working with ML as a design material, we conducted an online study with domain experts consisting of three iterations. The paper reports the main challenges we faced and our actions to overcome them. Our results can be useful to other designers working with ML-infused systems
Duurzaam plannen: een groot verschil met effici\uebnt plannen? Welke bijdrage kan planningssoftware leveren?
No full textStatistical analysis of distance-based path relinking for the capacitated vehicle routing problem
No full textAbstract: In this paper we develop an intelligent path relinking procedure for the capacitated vehicle routing problem, based on the relocate distance. This procedure transforms an incumbent solution into a guiding solution in a minimal number of relocate moves. In each step of the path relinking procedure, one customer is removed from the solution and re-inserted in another position. The path relinking procedure is integrated in a grasp (greedy randomized adaptive search procedure) and vnd (variable neighborhood descent) framework and thoroughly tested. This analysis shows that the path relinking procedure is not able to improve the performance of a simple grasp+vnd metaheuristic, but some interesting conclusions can nonetheless be drawn. A second contribution of this paper is an analysis of the computational results based on sound statistical techniques. Such an analysis can be useful for the field of metaheuristics, where computational results are generally analyzed in an ad hoc way and often with dubious statistical validity
