Skip to main content
Top

2018 | Book

Decision Support Systems VIII: Sustainable Data-Driven and Evidence-Based Decision Support

4th International Conference, ICDSST 2018, Heraklion, Greece, May 22–25, 2018, Proceedings

insite
SEARCH

About this book

This book constitutes the proceedings of the 4th International Conference on Decision Support Systems, ICDSST 2018, held in Heraklion, Greece, in May 2018. The main topic of this year’s conference was “Sustainable Data-Driven and Evidence Based Decision Support”. The 15 papers presented in this volume were carefully reviewed and selected from 71 submissions. They were organized in topical sections named: decision support systems for a sustainable society; decision support systems serving the public; decision support systems in management and organization; and advances in decision support systems’ technologies and methods.

The EWG-DSS series of International Conference on Decision Support System Technology (ICDSST), starting with ICDSST 2015 in Belgrade, were planned to consolidate the tradition of annual events organized by the EWG-DSS in offering a platform for European and international DSS communities, comprising the academic and industrial sectors, to present state-of-the-art DSS research and developments, to discuss current challenges that surround decision-making processes, to exchange ideas about realistic and innovative solutions, and to co-develop potential business opportunities.

Table of Contents

Frontmatter

Decision Support Systems for a Sustainable Society

Frontmatter
SIRPSS - Sustainable Industrial Site Redevelopment Planning Support System
Abstract
Abandoned industrial sites should be redeveloped in a sustainable way to reduce waste land. Planning support systems (PSSs) can help in the early planning phase by presenting possible outcomes of various redevelopment scenarios to the planners. This paper presents a PSS to support sustainable industrial site redevelopment decision based on past experiences. Past experiences are recorded as cases in the system. Case-based reasoning (CBR) is applied. For sites needed to be redeveloped, similar redeveloped cases are retrieved from the case library. Strategies that the previous cases have applied are reviewed and the new site is designed based on the comparison study of new case and past experiences, together with the input from planners. Sustainability is dynamically evaluated on site and regional level. A showcase is presented for the system illustration.
Tong Wang, Qi Han, Bauke de Vries
An Intelligent Multi-agent System Using Fuzzy Analytic Hierarchy Process and Axiomatic Design as a Decision Support Method for Refugee Settlement Siting
Abstract
Crises and disasters of recent years are complex and occasionally interrelated phenomena, which require complex decision making for effective humanitarian relief operations provision. Moreover, coordination is needed between different humanitarian actors as decision makers. Massive refugee and migrant arrivals in Greece since 2014, mainly a result of a refugee crisis, require complex humanitarian supply chain management and logistics operations. In this paper, refugee settlement site planning decision making process is addressed with an intelligent multi-agent system (MAS) modeling approach. The MAS uses two multi-criteria decision making (MCDM) methods: fuzzy analytic hierarchy process (FAHP) to determine the weights of criteria and fuzzy axiomatic design approach extended with risk factors (RFAD) to rank alternative sites for refugee settlement. The proposed method will be applied to evaluate currently operating temporary accommodation sites in Greece.
Maria Drakaki, Hacer Güner Gören, Panagiotis Tzionas
Towards an Intelligent Integrated System for Urban Planning Using GIS and Cloud Computing
Abstract
During the last few years, urban field has become more and more complex, as much as the growth of new technologies, new problems occurred. Therefore, urban territory planning organizations look ahead to find out sustainable alternatives, to meet human urban needs and to reach a high level of efficiency with the best employment of available resources. This paper proposes an Intelligent Integrated System using Geographic Information System (GIS) and Cloud Computing technology. The projected approach is based on: (i) the expand of the local GIS, by adding required information; (ii) the prediction of urban needs for a local scope, via analyzing GIS information; and (iii) the support of decision-makers so as to fit suggested urban projects to appropriate areas, respecting constraints. This paper includes a new architecture combining the main components of the proposed system.
Boudjemaa Khelifa, Mohamed Ridda Laouar, Sean Eom
An Ontology-Based Decision Support Framework for Personalized Quality of Life Recommendations
Abstract
As urban atmospheric conditions are tightly connected to citizens’ quality of life, the concept of efficient environmental decision support systems becomes highly relevant. However, the scale and heterogeneity of the involved data, together with the need for associating environmental information with physical reality, increase the complexity of the problem. In this work, we capitalize on the semantic expressiveness of ontologies to build a framework that uniformly covers all phases of the decision making process: from structuring and integration of data, to inference of new knowledge. We define a simplified ontology schema for representing the status of the environment and its impact on citizens’ health and actions. We also implement a novel ontology- and rule-based reasoning mechanism for generating personalized recommendations, capable of treating differently individuals with diverse levels of vulnerability under poor air quality conditions. The overall framework is easily adaptable to new sources and needs.
Marina Riga, Efstratios Kontopoulos, Kostas Karatzas, Stefanos Vrochidis, Ioannis Kompatsiaris

Decision Support Systems Serving the Public

Frontmatter
Critical Events and Critical Infrastructures: A System Dynamics Approach
Abstract
Critical events like natural disasters or terrorist attacks have evolved to a realistic concern over the last decade. Anticipation and timely decision-making are fundamental to ensure positive outcomes, stability and safety especially with concern to Critical Infrastructure. The purpose of this paper is to promote a new framework for efficient and effective crisis management in the area of Critical Infrastructures. The main effort of the project has been to use simulation models with the purpose of investigating, reproducing and representing the interdependencies among CIs while stressed by critical events. The results of the simulation demonstrated that preparation in cases like a flooding, can prove extremely useful and make an extreme situation more manageable. Finally, elements of the human behaviour, which are the most uncertain and difficult to simulate, are the most important and can make the difference between a disaster and a manageable situation.
Stefano Armenia, Georgios Tsaples, Camillo Carlini
How to Model Stakeholder Participation for Flood Management
Abstract
Stakeholders participation for Flood Risk Management is a key factor for the improvement of policy and decision’s quality of and to create consensus. Nowadays there are many studies on this topic aimed to take into consideration the involvement of stakeholders in different phases of the process and with the use of different procedures. In Italy the situation seems to be critical compared to the international panorama, since there are no regulation or protocols to prevent disaster or repair the damage. The paper proposes a critical overview of methodologies able to engage stakeholders in decision-making process with a detail on case studies focused on the Flood Risk Management. Different aspects will be investigated and compared in order to outline considerations and possible conclusions.
Marta Dell’Ovo, Francesca Torrieri, Alessandra Oppio
Big Data Analytics to Improve the Decision-Making Process in Public Safety: A Case Study in Northeast Brazil
Abstract
The concern about national security has increased over the years. The large number of crimes has brought a variety of serious problems to Brazil and other countries around the world. Therefore, the major challenge, especially in Brazil, faced by public safety is how best to analyze large amounts of data so as to identify the factors that influence how crimes evolve. Thus, this paper analyzes public safety in the northeast of Brazil and proposes a decision-making model based on Big Data Analytics. This model is a part of a framework that will support decision processes by identifying the most dangerous places based on correlating data on location and the number of crimes from a large volume of crime data.
Jean Gomes Turet, Ana Paula Cabral Seixas Costa
An Interactive Learning Environment Based on System Dynamics Methodology for Sustainable Mobility Challenges Communication & Citizens’ Engagement
Abstract
Serving the goal of enhancing the participatory approach of sustainable urban mobility planning for delivering acceptable and viable mobility plans, the current paper presents the MOTIVATE Interactive Learning Environment (ILE)/Game. Based on the System Dynamics (SD) methodology and answering to the need for catching up to the interactivity trend, the MOTIVATE ILE offers the user with a simplified experiential procedure for understanding the consequences of mode choice and sustainable decision making. Moreover, the rewarding system proposed for allowing the performance of actions while using the ILE transforms the user into an active agent of mobility planning by asking him/her to provide travel data and opinions for the improvement of city’s daily transportation performance.
Glykeria Myrovali, Georgios Tsaples, Maria Morfoulaki, Georgia Aifadopoulou, Jason Papathanasiou

Decision Support Systems in Management and Organizations

Frontmatter
Skills and Mindsets for an Analytically Innovative Organisation
Abstract
Much research has been carried out on factors influencing acceptance, success, and pervasiveness of business intelligence (BI) and analytics in organisations. This study focusses on the range of skills/competencies, and attitudes/mindsets, which can lead to an organization becoming sustainably data-driven and innovative through BI and analytics (BI&A). Following a literature review, business managers, users and creators of BI&A systems in South Africa were interviewed about the contribution of skills and mindsets to pervasive BI&A. Thematic analysis of the conversations uncovered five main themes: Good Communication, Prioritization of BI, Different Skillsets, Adopting BI&A, and Hunger for BI&A, all with sub-themes. Many of the important skills and mindsets were shown to be common to BI&A practitioners, as well as to their users and management.
Yusuf-Ali Karbelkar, Mike Hart
Computer Supported Team Formation
Abstract
Composing teams may be a time consuming and complex task. In any type of teams, the adequate selection of individuals to a team may increase the intellectual growth of the team in order to cooperate and reach the established goals. However, success of the composed team is not always guaranteed. To fill this gap, researchers develop different tools aiming to help team makers to assign team members to teams, in order to satisfy their expectations. The main goal of this paper is to present a literature review on team formation methodologies, tools, and applications that have been implemented. In this paper we present an analysis of what are teams, and its social structure. Next, a literature review and the efforts of computer supported team formation are presented and finally, the efforts of the researchers to achieve the optimal result are discussed.
Georgios Stavrou, Panagiotis Adamidis, Jason Papathanasiou
A Group Decision-Making Model for Supplier Selection: The Case of a Colombian Agricultural Research Company
Abstract
Decisions about supplier selection are important in the management of companies, as they directly influence their business continuity. The aim in such problem is to select the most suitable supplier from a set of potential ones, a task that involves several aspects besides cost. In this paper we build a model based on partial information in the context of MAVT (Multi-Attribute Value Theory) in order to select a satisfactory laboratory’s equipment supplier for an agricultural research company. Based on a set of criteria determined by specialists and alternatives available at local market, we applied the Flexible and Interactive Tradeoff (FITradeoff) method for eliciting preferences of multiple decision makers (DMs) and assist them to reach a consensus solution. The results showed the applicability of the method for aiding real-life situations since it enables DMs to consider tradeoffs amongst criteria based on a structured elicitation process, while lowering the cognitive effort required from them.
Jenny Milena Moreno Rodriguez, Takanni Hannaka Abreu Kang, Eduarda Asfora Frej, Adiel Teixeira de Almeida

Advances in Decision Support Systems’ Technologies and Methods

Frontmatter
SK-DSSy: How to Integrate the YouTube Platform in a Cooperative Decision Support?
Abstract
In wastewater treatment plants (WWTPs) domain, the decision support tools are nowadays necessary in order to efficiently process the large databases generated with on-line sensors. In this paper a cooperative decision support system (DSS) is presented. This DSS uses a KPI-based fuzzy logic engine to analyse the plant performance and identify the operational conditions that occur in the plants. Then, it associates the detected operational conditions with YouTube pages in which videos are uploaded to provide details and propose suggestions. The YouTube platform is then used to share and validate suggestions by means of the comment functions and the ‘likes’. This approach is innovative, free of costs, and useful for plant managers that can rely on a user-friendly platform.
Dario Torregrossa, Joachim Hansen
A DSS Model for Selection of Computer on Module Based on PROMETHEE and DEX Methods
Abstract
The onset of Industry 4.0 requires for development of self-aware systems. The core of such systems are computationally powerful yet energy efficient embedded modules, called computer on module (COM), capable of performing various tasks of control, data acquisition and signal processing. The market is flooded with various COM systems thus making the selection of the most appropriate one for appropriate task is a very difficult task. This decision problem is addressed by employing PROMETHEE and DEXi methods. The proposed solution is a decision model based on 13 attributes. The evaluation is performed on a set of 53 currently available COMs.
Gjorgji Nusev, Pavle Boškoski, Marko Bohanec, Biljana Mileva Boshkoska
Unveiling Hidden Patterns in Flexible Medical Treatment Processes – A Process Mining Case Study
Abstract
In hospital environments, treatment processes, resp. clinical pathways, are adopted based on the health state of a patient. Modeling of pathways is time consuming and due to the involvement of many participants, the introduction of clinical pathways is cost-intensive. Process mining offers a possibility for automatic or semi-automatic creation of clinical pathways based on the event log data recorded during the process execution in hospital information systems. However, state-of-the-art algorithms struggle to discover meaningful end-to-end patterns from highly flexible clinical log data. This challenge can be addressed by Local Process Models. They allow pathways to be modeled partially, thus enabling the detection of major process steps. In our case study, we apply this recently proposed method on a real world clinical dataset and discuss results and challenges.
Kathrin Kirchner, Petar Marković
A New Function for Ensemble Pruning
Abstract
We propose in this work a new function named Diversity and Accuracy for Pruning Ensembles (DAPE) which takes into account both accuracy and diversity to prune an ensemble of homogenous classifiers. A comparative study with a diversity based method and experimental results on several datasets show the effectiveness of the proposed method.
Souad Taleb Zouggar, Abdelkader Adla
Backmatter
Metadata
Title
Decision Support Systems VIII: Sustainable Data-Driven and Evidence-Based Decision Support
Editors
Dr. Fatima Dargam
Prof. Pavlos Delias
Isabelle Linden
Bertrand Mareschal
Copyright Year
2018
Electronic ISBN
978-3-319-90315-6
Print ISBN
978-3-319-90314-9
DOI
https://doi.org/10.1007/978-3-319-90315-6

Premium Partner