Pour savoir comment effectuer et gérer un dépôt de document, consultez le « Guide abrégé – Dépôt de documents » sur le site Web de la Bibliothèque. Pour toute question, écrivez à corpus@ulaval.ca.
 

Personne :
Heni, Hamza

En cours de chargement...
Photo de profil

Adresse électronique

Date de naissance

Projets de recherche

Structures organisationnelles

Fonction

Nom de famille

Heni

Prénom

Hamza

Affiliation

Université Laval. Département des systèmes d'information organisationnels

ISNI

Identifiant Canadiana

ncf11919237

person.page.name

Résultats de recherche

Voici les éléments 1 - 2 sur 2
  • PublicationAccès libre
    Measuring fuel consumption in vehicle routing : new estimation models using supervised learning
    (Taylor & Francis Group, 2021-07-06) Heni, Hamza; Diop, Serigne Arona; Renaud, Jacques; Coelho, Leandro C.
    In this paper, we propose and assess the accuracy of new fuel consumption estimation models for vehicle routing. Based on real-world data consisting of instantaneous fuel consumption, time-varying speeds observations, and high-frequency traffic, we propose effective methods to estimate fuel consumption. By carrying out nonlinear regression analysis using supervised learning methods, namely Neural Networks, Support Vector Machines, Conditional Inference Trees, and Gradient Boosting Machines, we develop new models that provide better prediction accuracy than classical models. We correctly estimate consumption for time-dependent point-to-point routing under realistic conditions. Our methods provide a more precise alternative to classical regression methods used in the literature, as they are developed for a specific situation. Extensive computational experiments under realistic conditions show the effectiveness of the proposed machine learning consumption models, clearly outperforming macroscopic and microscopic consumption models such as the Comprehensive Modal Emissions Model (CMEM) and the Methodology for Estimating air pollutant Emissions from Transport (MEET). Based on sensitivity analyses we show that MEET underestimates real-world consumption by 24.94% and CMEM leads to an overestimation of consumption by 7.57% with optimised parameters. Our best machine learning model (Gradient Boosting Machines) exhibited superior estimation accuracy with a gap of only 1.70%.
  • PublicationAccès libre
    Determining time-dependent minimum cost paths under several objectives
    (Elsevier, 2019-01-17) Heni, Hamza; Renaud, Jacques; Coelho, Leandro C.
    As the largest contributor to greenhouse gas (GHG) emissions in the transportation sector, road freight transportation is the focus of numerous strategies to tackle increased pollution. One way to reduce emissions is to consider congestion and being able to route traffic around it. In this paper we study time-dependent minimum cost paths under several objectives (TDMCP-SO), in which the objective function comprises GHG emissions, driver and congestion costs. Travel costs are impacted by traffic due to changing congestion levels depending on the time of the day, vehicle types and carried load. We also develop time-dependent lower and upper bounds, which are both accurate and fast to compute. Computational experiments are performed on real-life instances that incorporate the variation of traffic throughout the day, by adapting Dijkstra’s label-setting algorithm according to different cost computation methods. We show that explicitly considering first-in, first-out (FIFO) consistency using time-varying speeds allows the efficient computation of tight time-dependent bounds. Our computational results demonstrate that the TDMCP-SO is more difficult to solve to optimality but the proposed algorithm is shown to be robust and efficient in reducing the total cost even for large instances in an environment of varying speeds, outperforming those based on the link travel time model and on the smoothing method according to each optimization objective, flexible departure times, and different load patterns.