Combined optimisation and MCDA based solution of the tram depot location problem

This paper deals with an issue of technical facilities location in a public transport system. The decision problem is formulated as a selection of the most advantageous alternative, i.e. the location of a new tram depot among the already existing facilities of this type. The selection is preceded by the evaluation of the alternatives. The assessment is not a trivial task, because there are many groups of interest with usually contradictory points of view. Therefore, the evaluation of the new tram depot locations should represent different aspects, e.g., economical, technical, environmental, and organizational. To handle such a complex decision problem the authors propose a methodology, which is a composition of the optimisation and multiple criteria evaluation techniques. The developed methodology is experimentally applied to the selection of one out of five tram depot locations in the public transport system of the city of Poznan, Poland. All the computational experiments are performed by means of optimization and multiple criteria decision aiding (MCDA) methods and tools, i.e. a linear optimization engine Solver Premium Platform and AHP method with its application AHORNsimple. The calculations are the basis for recommending the location of a new depot in the central part of the transport system network, which is a reasonable solution taking into account, e.g. the proximity of the main railway line, the possibility of triple distribution of the transport means from depot. The proposed methodology of the decision problem solution gives also an opportunity to create the hierarchy of considered tram depot locations as well as to compare the position in the ranking of the best solution with the existing one. Since the proposed methodology assumes the selection of the most suitable MCDA method to the problem under consideration and the decision maker’s preferen¬ces, it guarantees that the result of analysis becomes reliable and the decision aiding process is credible.

Multicriteria Analysis in Additive Manufacturing: An ELECTRE-MOr Based Approach

3D printing technologies define the essence of Additive Manufacturing and make possible the agile production of customized parts from different materials, with lower unit cost and waste generation. Currently, one of the most widespread 3D printer technologies is the Fused Deposition Modeling (FDM) type, which is the object of this paper. The choice of 3D printing equipment depends on the alignment of the purpose of use and technical knowledge to consider certain requirements. Therefore, this choice can be time-consuming and/or imprecise. In this sense, this work aimed to classify FDM-type 3D printer models by applying the ELECTRE-MOr method, a Multi-criteria Decision Aiding (MCDA) method. As a result, based on a categorization between classes, the FABER 10 alternative was the only one that presented class A performance in all evaluated scenarios, based on criteria defined by the experts consulted in this study.

On the Identifiability of Hierarchical Decision Models

Interpretability is a desirable property for machine learning and decision models, particularly in the context of safety-critical applications. Another most desirable property of the sought model is to be unique or {\em identifiable} in the considered class of models: the fact that the same functional dependency can be represented by a number of syntactically different models adversely affects the model interpretability, and prevents the expert from easily checking their validity. This paper focuses on the Choquet integral (CI) models and their hierarchical extensions (HCI). HCIs aim to support expert decision making, by gradually aggregating preferences based on criteria; they are widely used in multi-criteria decision aiding {and are receiving interest from the} Machine Learning {community}, as they preserve the high readability of CIs while efficiently scaling up w.r.t. the number of criteria. The main contribution is to establish the identifiability property of HCI under mild conditions: two HCIs implementing the same aggregation function on the criteria space necessarily have the same hierarchical structure and aggregation parameters. The identifiability property holds even when the marginal utility functions are learned from the data. This makes the class of HCI models a most appropriate choice in domains where the model interpretability and reliability are of primary concern.

Effect of Procedural Elements on Trust and Compliance with anImperfect Decision Aid

We sought to establish to what extent incorporating a dichotomized procedural variable (in this case, maritime ‘rules of the road’) and incentives into a decision aiding algorithm would change a previously found non-compliance bias when the algorithm contradicted the known procedure. We also sought to examine the relationship between trust in and dependence on an automated system. An experiment was conducted using a simple, simulated maritime collision avoidance task featuring an imperfect, but highly reliable (87%), decision aid. Adding the dichotomous procedural variable into the algorithms recommendations increased compliance with the system, even for recommendations that violated learned procedures. Performance was still not perfectly calibrated to the actual reliability of the system (underreliance and under-trust). Results also revealed the dissociation between rated trust in, and behavioral dependence on decision aiding automation.

A Methodological Framework to Support the Sustainable Innovation Development Process: A Collaborative Approach

The notion of sustainable innovation (SI) emerged recently in the academic literature and evokes deep changes in organizations’ products, processes, and practices to favour the creation of social and environmental value in addition to economic returns. The development of SI implies a collaborative process that requires the orchestration of several actors and streams of knowledge to be successful. Indeed, companies adopting the SI path need structured methodologies to guide the collaboration process with internal and external actors and support the decision process. Nevertheless, the literature has focused on the analysis of determinants and drivers of sustainable innovation development, while the process perspective has been discussed less. Through an in-depth case study in a large-sized company in France, this article proposes a methodological framework to guide the collaborative process in the early phases of sustainable innovation development. The framework relies on a combination of qualitative research and a multicriteria decision aiding method (AHP). The contributions of this work address two main aspects: (i) the conceptualization of sustainable innovation (SI) and (ii) the collaborative process between internal and external actors to develop SI. Firstly, our study leads to two additional dimensions to complete the concept of SI, traditionally based on the three pillars of sustainability (economic, environmental, and social), by adding the functional and relational dimensions. Secondly, concerning the collaborative process to develop SI, our framework proposes a structured methodology following five steps: definition of the project scope, setting actors’ motivations, defining satisfaction criteria, proposing SI solutions, and performing a decision-aiding process to define the preference profiles of the key actors.

A prescriptive framework for recommending decision attributes of infrastructure disaster recovery problems

This paper proposes a framework to systematically evaluate and select attributes of decision models used in disaster risk management. In doing so, we formalized the attribute selection process as a sequential screening-utility problem by formulating a prescriptive decision model. The aim is to assist decision-makers in producing a ranked list of attributes and selecting a set among them. We developed an evaluation process consisting of ten criteria in three sequential stages. We used a combination of three decision rules for the evaluation process, alongside mathematically integrated compensatory and non-compensatory techniques as the aggregation methods. We implemented the framework in the context of disaster resilient transportation network to investigate its performance and outcomes. Results show that the framework acted as an inclusive systematic decision aiding mechanism and promoted creative and collaborative decision-making. Preliminary investigations suggest the successful application of the framework in evaluating and selecting a tenable set of attributes. Further analyses are required to discuss the performance of the produced attributes. The properties of the resulting attributes and feedback of the users suggest the quality of outcomes compared to the retrospective attributes that were selected in an unaided selection process. Research and practice can use the framework to conduct a systematic problem-structuring phase of decision analysis and select an equitable set of decision attributes.

Residual life-based importance measures for predictive maintenance decision-making

Importance measures have been widely used as meaningful decision-aiding indicators in reliability engineering, risk management and maintenance optimization. However, few importance measures integrates the actual condition (working states or degradation levels) of components that dynamically evolves with time. This work develops a novel time-dependent importance measure defined as the capacity of a component (or group of components) to improve, when it is replaced, the system residual life. The proposed [Formula: see text] measure can help to better prioritize a component or group of components regarding to its improvement ability in the system life time while considering the actual conditions of all components of the system. The originality and complementarity of the proposed measure when compared to existing importance measures is also investigated. The proposed importance measure is then extended to integrate the economic dimension of the maintenance decision, through the maintenance costs, the benefit gained by the maintenance operations and as well as the economic dependence between components. It is finally shown how the proposed [Formula: see text] measure and its extension can “optimally” suggest a component or a group of several components for preventive maintenance decision-making, based on both the technical criterion (residual life of the system) and the economic aspects (benefit and costs). The use and the advantages of the proposed importance measure and its extension are illustrated on a four-component system.

Reducing Cognitive Effort in Scoring Negotiation Space Using the Fuzzy Clustering Model

Negotiation scoring systems are fundamental tools used in negotiation support to facilitate parties searching for negotiation agreement and analyzing its efficiency and fairness. Such a scoring system is obtained in prenegotiation by implementing selected multiple criteria decision-aiding methods to elicit the negotiator’s preferences precisely and ensure that the support is reliable. However, the methods classically used in the preference elicitation require much cognitive effort from the negotiators, and hence, do not prevent them from using heuristics and making simple errors that result in inaccurate scoring systems. This paper aims to develop an alternative tool that allows scoring the negotiation offers by implementing a sorting approach and the reference set of limiting profiles defined individually by the negotiators in the form of complete packages. These limiting profiles are evaluated holistically and verbally by the negotiator. Then the fuzzy decision model is built that uses the notion of increasing the preference granularity by introducing a series of limiting sub-profiles for corresponding sub-categories of offers. This process is performed automatically by the support algorithm and does not require any additional preferential information from the negotiator. A new method of generating reference fuzzy scores to allow a detailed assignment of any negotiation offer from feasible negotiation space to clusters and sub-clusters is proposed. Finally, the efficient frontier and Nash’s fair division are used to identify the recommended packages for negotiation in the bargaining phase. This new approach allows negotiators to obtain economically efficient, fair, balanced, and reciprocated agreements while minimizing information needs and effort.