检索结果-内蒙古大学图书馆

Multicriteria interpretability driven deep learning

ANNALS OF OPERATIONS RESEARCH 2022年第2期346卷 1621-1635页

作者： Repetto, Marco Siemens Italy Digital Ind Milan Italy Univ Milano Bicocca Dept Econ Management & Stat Milan Italy

Deep Learning methods are well-known for their abilities, but their interpretability keeps them out of high-stakes situations. This difficulty is addressed by recent model-agnostic methods that provide explanations after the training process. As a result, the current guidelines' requirement for "interpretability from the start" is not met. As a result, such methods are only useful as a sanity check after the model has been trained. In an abstract scenario, "interpretability from the start" implies imposing a set of soft constraints on the model's behavior by infusing knowledge and eliminating any biases. By inserting knowledge into the objective function, we present a Multicriteria technique that allows us to control the feature effects on the model's output. To accommodate for more complex effects and local lack of information, we enhance the method by integrating particular knowledge functions. As a result, a Deep Learning training process that is both interpretable and compliant with modern legislation has been developed. Our technique develops performant yet robust models capable of overcoming biases resulting from data scarcity, according to a practical empirical example based on credit risk.

关键词： Artificial intelligence Machine learning Deep learning multiple objective programming Multicriteria optimization

来源：评论

学校读者我要写书评

暂无评论

OPPORTUNITIES AND LIMITATIONS OF AHP IN MULTIobjective programming

引用

MATHEMATICAL AND COMPUTER MODELLING 1988年第C期11卷 206-209页

作者： OLSON, DL TEXAS A&M UNIV DEPT BUSINESS ANAL & RESCOLLEGE STNTX 77843

The Analytic Hierarchy Process is a useful tool for multiobjective decision making in its own right. In addition, it has the potential for expediting multiple objective programming analyses. multiple objective programming techniques face the problem of a large (if not infinite) number of alternatives. Generally, the problem involves optimizing some unexpressed utility function over a feasible region. AHP provides a useful means of obtaining an initial linear approximation of this unexpressed utility function, with the potential of expediting the MOP analysis. Other benefits include enhancing decision maker learning through use of the consistency measure. Problems discussed are the impact of comparing many objectives, the sensitivity of the consistency index, and the use of the eigen vector as a literal estimator of utility.

关键词： Analytic Hierarchy Process multiple objective programming

来源：评论

学校读者我要写书评

暂无评论

The dynamic relocation and phase-out of a hybrid, two-echelon plant/warehousing facility: A multiple objective approach

引用

EUROPEAN JOURNAL OF OPERATIONAL RESEARCH 2000年第1期123卷 1-15页

作者： Melachrinoudis, E Min, H Univ Louisville Logist & Distribut Inst Speech Res Adm Louisville KY 40292 USA Northeastern Univ Dept Mech Ind & Mfg Engn Boston MA 02115 USA

A real-world application involving the relocation and phase-out of a combined manufacturing plant and warehousing facility is presented in this paper. The relocation and phase-out decision was called for to adapt to dynamic changes in business environments surrounding the firm's supply chain operations. Such changes include changes in supplier and customer bases, distribution networks, corporate re-engineering, business climate, and government legislation. To aid management in formulating more effective relocation strategy, we assess the viability of the proposed site from multi-echelon supply chain perspectives and determine the optimal timing of relocation and phase-out in the multiple planning horizon using a dynamic, multiple objective, mixed-integer programming model. (C) 2000 Elsevier Science B.V. All rights reserved.

关键词： dynamic location supply chain management multiple objective programming

来源：评论

学校读者我要写书评

暂无评论

A Sustainable Bi-objective Approach for the Minimum Latency Problem 1

引用

2nd International Conference on Smart Cities (Smart-CT)

作者： Arellano-Arriaga, Nancy A. Alvarez-Socarras, Ada M. Martinez-Salazar, Iris A. Univ Autonoma Nuevo Leon Fac Ingn Mecan & Elect San Nicol De Los Garza Nuevo Leon Mexico Univ Malaga Dept Econ Aplicada Matemat Malaga Spain

ISBN: (数字)9783319595139

ISBN: (纸本)9783319595139;9783319595122

Nowadays, sustainability is a major factor to consider in the decision-making process. Specifically, for companies trying to stay competitive and having some advantage in the market it is a vital issue. In this study, we introduce a multi objective problem which aims to minimize distance and latency of a route with enough capacity to serve a set of clients. We assume that a vehicle leaves an established depot, visits all clients and returns to the depot before the end of the workday. With this bi-objective problem, we aim to improve the sustainability of the company by improving their economic and environmental contribution, through the minimization of the traveled distance of the vehicle along with the improvement of their social service by the minimization of the total waiting time of the customers. We call this problem Minimum Latency-Distance Problem (MLDP) and in this paper, we introduce a mathematical formulation which describes it.

关键词： Combinatorial optimization Mathematical formulation multiple objective programming Multi objective optimization Multi objective problem Latency Distance Multi objective routing problem

来源：评论

学校读者我要写书评

暂无评论

multiple-objective analysis of integrated relief supply and network restoration in humanitarian logistics operations

引用

INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH 2016年第1期54卷 49-68页

作者： Ransikarbum, Kasin Mason, Scott J. Clemson Univ Dept Ind Engn Clemson SC 29634 USA

While logistics research recently has placed increased focus on disruption management, few studies have examined the response and recovery phases in post-disaster operations. We present a multiple objective, integrated network optimisation model for making strategic decisions in the supply distribution and network restoration phases of humanitarian logistics operations. Our model provides an equity-based solution for constrained capacity, budget and resource problems in post-disaster logistics management. We conduct designed experiments for this NP-hard problem to analyse important aspects of the integrated problem for both small- and large-sized networks: full vs. partial restoration and pooled vs. separate budgeting approach. Finally, we apply the model to a Hazus-generated regional case study based on an earthquake scenario and generate efficient Pareto frontiers to understand the trade-off between the objectives of interest.

关键词： disruption management humanitarian logistics response and recovery equity multiple objective programming Hazus

来源：评论

学校读者我要写书评

暂无评论

Continuity of minimal points with applications to parametric multiple objective optimization

引用

EUROPEAN JOURNAL OF OPERATIONAL RESEARCH 2004年第1期157卷 59-67页

作者： Bednarczuk, EM Polish Acad Sci Syst Res Inst PL-01447 Warsaw Poland

Basing ourselves on general results we investigate stability of Pareto points to finite-dimensional parametric multiple objective optimization problems (linear and/or convex). (C) 2003 Published by Elsevier B.V.

关键词： multiple objective programming parametric programming stability analysis

来源：评论

学校读者我要写书评

暂无评论

A Fuzzy MOP Based Competence Set Expansion Method for Technology Roadmap Definitions 19

A Fuzzy MOP Based Competence Set Expansion Method for Techno...

引用

19th International Conference on New Trends in Intelligent Software Methodologies, Tools and Techniques (SoMeT)

作者： Huang, Chi-Yo Lin, Yen-Chu Yang, Chia-Li Sun, Yu Cheng, Jeng-Chieh Kuo, Ying-Ting Wang, Liang-Chieh Wang, Sing-Yan Hsu, Hao-En Hsu, Hao-Hsiu Natl Taiwan Normal Univ Dept Ind Educ Taipei Taiwan Natl Ctr High Speed Comp Taipei Taiwan

ISBN: (纸本)9781643681153;9781643681146

Technology roadmaps have already been widely adopted as an important management tool during the past three decades after the invention of the management tool by Motorola in the 1980s. The technology road-mapping processes which can be integrated with firms' competence sets are very important for strategy definitions. However, how the uncertainties being associated with the costs, time, quality, etc. for technology road mapping were seldom discussed, not to mention how various objectives can be considered at the same time. Thus, this research aims to propose a fuzzy multiple objective programming based competence set expansion technique to resolve the above mentioned technology road-mapping problem. An empirical study based on the road-mapping of novel compressors for air conditioners will be used to demonstrate the feasibility of the proposed framework. The well-verified analytic framework can serve as a basis for research and development (R&D) strategy definitions by practitioners.

关键词： competence set expansion technology roadmap multiple objective programming

来源：评论

学校读者我要写书评

暂无评论

Minimal Representations of a Face of a Convex Polyhedron and Some Applications

引用

ACTA MATHEMATICA VIETNAMICA 2021年第4期46卷 761-778页

作者： Tu, Ta Van Corvinus Univ Budapest Dept Operat Res H-1093 Budapest Hungary

In this paper, we propose a method for determining all minimal representations of a face of a polyhedron defined by a system of linear inequalities. Main difficulties for determining prime and minimal representations of a face are that the deletion of one redundant constraint can change the redundancy of other constraints and the number of descriptor index pairs for the face can be huge. To reduce computational efforts in finding all minimal representations of a face, we prove and use properties that deleting strongly redundant constraints does not change the redundancy of other constraints and all minimal representations of a face can be found only in the set of all prime representations of the face corresponding to the maximal descriptor index set for it. The proposed method is based on a top-down search strategy, is easy to implement, and has many computational advantages. Based on minimal representations of a face, a reduction of degeneracy degrees of the face and ideas to improve some known methods for finding all maximal efficient faces in multiple objective linear programming are presented. Numerical examples are given to illustrate the method.

关键词： Faces of a polyhedron Degeneracy degrees of faces Prime and minimal representations of a face Maximal descriptor index set multiple objective programming

来源：评论

学校读者我要写书评

暂无评论

Designing communication networks for distributed control agents

Designing communication networks for distributed control age...

引用

1st ORP Conference

作者： Camponogara, E Talukdar, S Univ Fed Santa Catarina Dept Automacao & Sist BR-88040900 Florianopolis SC Brazil Carnegie Mellon Univ Dept Elect & Comp Engn Pittsburgh PA 15213 USA

This paper is concerned with a bicriteria combinatorial optimization Problem and its applications to the design of communication networks for distributed controllers. In a bipartite graph, a subset of the edges yields a communication network for which we pay a price but, on the other hand, it induces another network that encompasses the former and for which we receive a reward. The problem is then to find the efficient solutions. The paper delivers an IP formulation for the problem of finding supported solutions, which is shown to be NP-Hard, along with families of strong valid inequalities, which are shown to draw the LP bounds closer to the Pareto optimal frontier. To approximate the frontier, heuristics are integrated in a problem-solving architecture called asynchronous team and then put to the test in two prototypical scenarios. (C) 2003 Elsevier B.V. All rights reserved.

关键词： multiple objective programming multiagent systems combinatorial optimization metaheuristics

来源：评论

学校读者我要写书评

暂无评论

Application of particle swarm optimization to the train scheduling for high-speed passenger railroad planning

Application of particle swarm optimization to the train sche...

引用

International Symposium on Communications and Information Technologies (ISCIT2005)

作者： Ren, P Li, N Gao, LQ Lin, ZL Li, Y Northeastern Univ Sch Informat Sci & Engn Shenyang Peoples R China

ISBN: (纸本)0780395387

This paper presents an approach for solving the train scheduling for high-speed passenger railroad planning problem through the particle swarm optimization(PSO) for the first time. PSO has demonstrated the ability to deal with non-convex, nonlinear, integer-mixed optimization problems. In this formulation, the objective function consists of two terms: the variation of inter-departure times for highspeed trains and the total travel time. This combination of terms results in a non-linear objective function. A case on the train scheduling for high-speed passenger railroad planning problem is presented to show the methodology's feasibility and efficiency, compared with the existing optimal planning methods, the search time of the particle swarm optimization method is shorter and the result is close to the ideal solution, simultaneously.

关键词： train scheduling particle swarm optimization multiple objective programming transportation railway

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：