The Experts below are selected from a list of 912 Experts worldwide ranked by ideXlab platform
Michiel C J Bliemer - One of the best experts on this subject based on the ideXlab platform.
-
Entropy maximising facility location model for port city intermodal terminals
2017Co-Authors: Collins Teye, Michael G H Bell, Michiel C J BliemerAbstract:This paper employs the principle of Entropy Maximisation to solve the multi-user intermodal terminal (IMT) location problem in a context where users have the option not to use an IMT. The proposed model is a non-linear mixed integer programming problem, which decomposes into an IMT location sub-problem and an IMT choice sub-problem linked in one direction by the choice of IMT location(s) and in the other by dual variables relating to cost sensitivity and IMT capacity. The principal features of the model are illustrated by a numerical example based on the state of NSW, Australia, where new IMTs are planned.
-
urban intermodal container terminals the Entropy Maximisation facility location problem
2016Co-Authors: Collins Teye, Michael G H Bell, Michiel C J BliemerAbstract:An important problem confronting port cities is where and how to accommodate port growth. Larger ships combined with increased container throughput require more yard space and generate more traffic, straining the urban fabric in the vicinity of the port. A plausible solution to this problem is the development of urban intermodal container terminals that interfaces with both road and rail networks. This raises two linked choices; where to locate the intermodal terminals and what are their likely usage considering competing alternatives. Traditionally facility location models have been applied to problems of this kind, leading to mixed integer linear programming problems (MILP), where the objective function is the fixed and variable cost of facility location. MILP solutions are corner point solutions which fail to account for the fact that in a choice situation, not all elements of costs or all factors affecting the choice process are known to the analyst or can be quantified and included in the modelling process. This paper proposes an Entropy maximizing approach, where the objective is a non-linear Entropy function of the modal decision variables and a budget on fixed and variable cost of facility location. This generates a linked logit mode choice model and an integer linear facility location model. The paper illustrates the principal features of the Entropy model and demonstrates its superiority over equivalent MILP models in terms of location decisions and testing of various policy instruments to promote intermodal transport use.
Collins Teye - One of the best experts on this subject based on the ideXlab platform.
-
Entropy maximising facility location model for port city intermodal terminals
2017Co-Authors: Collins Teye, Michael G H Bell, Michiel C J BliemerAbstract:This paper employs the principle of Entropy Maximisation to solve the multi-user intermodal terminal (IMT) location problem in a context where users have the option not to use an IMT. The proposed model is a non-linear mixed integer programming problem, which decomposes into an IMT location sub-problem and an IMT choice sub-problem linked in one direction by the choice of IMT location(s) and in the other by dual variables relating to cost sensitivity and IMT capacity. The principal features of the model are illustrated by a numerical example based on the state of NSW, Australia, where new IMTs are planned.
-
urban intermodal container terminals the Entropy Maximisation facility location problem
2016Co-Authors: Collins Teye, Michael G H Bell, Michiel C J BliemerAbstract:An important problem confronting port cities is where and how to accommodate port growth. Larger ships combined with increased container throughput require more yard space and generate more traffic, straining the urban fabric in the vicinity of the port. A plausible solution to this problem is the development of urban intermodal container terminals that interfaces with both road and rail networks. This raises two linked choices; where to locate the intermodal terminals and what are their likely usage considering competing alternatives. Traditionally facility location models have been applied to problems of this kind, leading to mixed integer linear programming problems (MILP), where the objective function is the fixed and variable cost of facility location. MILP solutions are corner point solutions which fail to account for the fact that in a choice situation, not all elements of costs or all factors affecting the choice process are known to the analyst or can be quantified and included in the modelling process. This paper proposes an Entropy maximizing approach, where the objective is a non-linear Entropy function of the modal decision variables and a budget on fixed and variable cost of facility location. This generates a linked logit mode choice model and an integer linear facility location model. The paper illustrates the principal features of the Entropy model and demonstrates its superiority over equivalent MILP models in terms of location decisions and testing of various policy instruments to promote intermodal transport use.
J R Fryer - One of the best experts on this subject based on the ideXlab platform.
-
phase extension in electron crystallography using the maximum Entropy method and its application to two dimensional purple membrane data from halobacterium halobium
1993Co-Authors: Christopher J Gilmore, K Shankland, J R FryerAbstract:Abstract We consider the situation where an electron diffraction pattern has been obtained from a crystal; from the same sample an image is also produced which, when Fourier-transformed, yields phases for some, but not all, of the diffraction intensities. In particular the image yields information of lower resolution than the corresponding diffraction pattern. To phase the remaining diffraction reflections, and thus enhance the image resolution, the phased reflections are used as constraints in an Entropy Maximisation. The resulting maximum Entropy map is then used to generate a centroid electostatic potential map in which the diffracted intensities are phased and assigned weights that reflect the reliability of the new phase information. Using data from purple membrane, this method achieves a resolution enhancement of up to 25%.
Michael G H Bell - One of the best experts on this subject based on the ideXlab platform.
-
Entropy maximising facility location model for port city intermodal terminals
2017Co-Authors: Collins Teye, Michael G H Bell, Michiel C J BliemerAbstract:This paper employs the principle of Entropy Maximisation to solve the multi-user intermodal terminal (IMT) location problem in a context where users have the option not to use an IMT. The proposed model is a non-linear mixed integer programming problem, which decomposes into an IMT location sub-problem and an IMT choice sub-problem linked in one direction by the choice of IMT location(s) and in the other by dual variables relating to cost sensitivity and IMT capacity. The principal features of the model are illustrated by a numerical example based on the state of NSW, Australia, where new IMTs are planned.
-
urban intermodal container terminals the Entropy Maximisation facility location problem
2016Co-Authors: Collins Teye, Michael G H Bell, Michiel C J BliemerAbstract:An important problem confronting port cities is where and how to accommodate port growth. Larger ships combined with increased container throughput require more yard space and generate more traffic, straining the urban fabric in the vicinity of the port. A plausible solution to this problem is the development of urban intermodal container terminals that interfaces with both road and rail networks. This raises two linked choices; where to locate the intermodal terminals and what are their likely usage considering competing alternatives. Traditionally facility location models have been applied to problems of this kind, leading to mixed integer linear programming problems (MILP), where the objective function is the fixed and variable cost of facility location. MILP solutions are corner point solutions which fail to account for the fact that in a choice situation, not all elements of costs or all factors affecting the choice process are known to the analyst or can be quantified and included in the modelling process. This paper proposes an Entropy maximizing approach, where the objective is a non-linear Entropy function of the modal decision variables and a budget on fixed and variable cost of facility location. This generates a linked logit mode choice model and an integer linear facility location model. The paper illustrates the principal features of the Entropy model and demonstrates its superiority over equivalent MILP models in terms of location decisions and testing of various policy instruments to promote intermodal transport use.
Lawrence Eva - One of the best experts on this subject based on the ideXlab platform.
-
Maximum Entropy on the mean approach to solve generalized inverse problems with an application in computational thermodynamics
2021Co-Authors: Gamboa Fabrice, Gueneau Christine, Klein Thierry, Lawrence EvaAbstract:International audienceIn this paper, we study Entropy Maximisation problems in order to reconstruct functions or measures subject to very general integral constraints. Our work has a twofold purpose. We first make a global synthesis of Entropy Maximisation problems in the case of a single reconstruction (measure or function) from the convex analysis point of view, as well as in the framework of the embedding into the Maximum Entropy on the Mean (MEM) setting. We further propose an extension of the Entropy methods for a multidimensional case
-
Reconstruction fonctionnelle et analyse d'incertitude dans le cadre d'un problème inverse de thermodynamique chimique.
2020Co-Authors: Lawrence EvaAbstract:The topics addressed in this thesis lie in statistical learning and uncertainty analysis within the frame of a thermodynamic problem.We are interested in two problems linked with the reconstruction of a multidimensional function $f$: an uncertainty propagation problem within the Bayesian linear model in the first place; a non parametric reconstruction problem using a convex analysis Maximisation criterion in the second place.The specificity of the thermodynamic problem considered in this manuscript consists in the complicated structure of the data: the assimilation data are not direct observations of the quantity $f$ to reconstruct.In the framework of the Bayesian linear model, we propose a method allowing us to take into account the thermodynamic model specificity.We consider a real case study for the application of the method.In the framework of non-parametric reconstruction problems, we are interested in the reconstruction of a multidimensional function $f$ over a compact set $U$ and such that $f$ satisfies a certain amount of very general integral constraints.We propose to solve this reconstruction problem by setting it in the frame of the $\gamma$-Entropy Maximisation problem under constraints.That is, we define a convex function $\gamma$ of $\mathbb{R}^p$ to $\mathbb{R}_+$ with some good properties and we are interested in the Maximisation under constraints of the quantity $ I_\gamma(f) = - \int_U \gamma(f) dP_U $.We explain that this problem can be linked to another one that deals with signed measures $F$.Such problems have been studied in the case of a single function or a single measure reconstruction.We propose to study the more general case of the reconstruction of a function or a measure with values in $\mathbb{R}^p$.Cette thèse s'inscrit dans les domaines de l’apprentissage statistique et de l'analyse d'incertitude dans le cadre d'un problème de thermodynamique chimique.On s'intéresse à deux problèmes liés à la reconstruction d'une fonction $f$ multidimensionnelle : en premier lieu, un problème de propagation de l'incertitude dans le cadre du modèle linéaire bayésien ;en second lieu, la reconstruction non paramétrique d'une fonction par Maximisation d'un critère d'analyse convexe.La spécificité du problème de thermodynamique chimique considéré dans cette thèse réside dans la structure compliquée des données : les données d'assimilation ne sont pas des observations directes de la quantité $f$ à reconstruire.Dans le cadre du modèle linéaire bayésien, on propose une méthode permettant de prendre en compte la spécificité de ce modèle.On considère un cas de thermodynamique chimique réel pour l'application de la méthode.Dans le cadre de la reconstruction non-paramétrique, on s'intéresse à la reconstruction d'une fonction $f$ multidimensionnelle sur un compact $U$ et telle que $f$ satisfait un certain nombre de contraintes intégrales très générales.On se propose de résoudre ce problème de reconstruction fonctionnelle dans le cadre de la Maximisation de la $\gamma$-entropie sous contraintes.A savoir, on se donne une fonction convexe $\gamma$ de $\mathbb{R}^p$ dans $\mathbb{R}_+$, munie de bonnes propriétés et on s'intéresse à la Maximisation sous contraintes de la quantité $ I_\gamma(f) = - \int_U \gamma(f) dP_U $.On expliquera que ce problème peut être rapproché d'un autre problème connu portant cette fois-ci sur des mesures signées $F$.Ces problèmes ont été étudiés dans le cas d'une unique reconstruction, à savoir une unique fonction ou une unique mesure.Nous nous proposons d'étudier le cas plus général d'une fonction ou d'une mesure à valeurs dans $\mathbb{R}^p$