Elsevier

Decision Support Systems

Volume 81, January 2016, Pages 66-75
Decision Support Systems

A linguistic mobile Decision Support System based on fuzzy ontology to facilitate knowledge mobilization

https://doi.org/10.1016/j.dss.2015.09.001Get rights and content

Highlights

  • Web and Android platform applications employing a Fuzzy Wine Ontology have been implemented for imprecise information.

  • We show that imprecise expert knowledge can be activated and managed using mobile devices.

  • Knowledge mobilization will make it possible for users to get decision support regardless of where they are.

  • We show how to use imprecise data with a combination of decision support algorithms and fuzzy ontology.

  • The adoption of mobile devices will change the way decisions are made in everyday life, in business and in daily routines.

Abstract

The current development of the Semantic Web has created an increasing demand for methods and systems that can make use of imprecise information. As the amounts of data collected constantly grows, it will not be feasible to overlook imprecise data. We show that a combination of mobile technology and fuzzy ontology with group decision making support methods will facilitate a mobilization of knowledge, offering users a possibility to get decision making support through their mobile devices regardless of the context and location. In this paper, as an illustration and verification, a web platform and an Android application have been developed to help users to choose a suitable wine for different types of dinners.

Introduction

Nowadays, users demand more assistance applications to help them with their everyday life. As most users always carry a mobile device with them, this is the artefact they want to get assistance from. Decision support developed for mobile devices is therefore becoming an increasingly important research area. It is also a critical part of knowledge mobilization [1], a movement that will change how knowledge management is conducted. Knowledge mobilization aims at making knowledge obtained from formal research available and usable by every person who is in need of it.

At the same time, developments in the ICT-field have produced a never ending flow of new technical devices that connect to the Internet and allow users to share and consume information regardless of time and location. In order to allow knowledge mobilization to work on these devices, it is necessary implement methods and technologies for them such as Decision Support Systems [2], fuzzy ontologies [3], and recommendation systems [4]. Moreover, all these methods must work together in order to carry out the necessary tasks. Consequently, one of the present challenges is to find ways of connecting methods and technologies that will allow mobile phones to provide real-time knowledge to the user whenever and wherever he/she needs it. In other words, to bring knowledge mobilization to mobile phones. Thanks to server languages such as PHP or JSP [5], database languages such as Oracle and MySQL, and mobile operating systems such as IOS and Android [6], it can be stated that, today, the creation of multiple tools that collaborate as Internet applications is possible.

In this paper, we are going to discuss the implementation of a mobile Decision Support System that gives real time knowledge about a certain topic. By collecting expert knowledge using ontologies [3], it is possible for non-experts to take advantage of expert wisdom and use the advice of experts on topics that should be dealt with. The implemented system uses linguistic modeling in order to ease the way for experts to communicate with the system. It has been repeatedly proven that experts are more comfortable with expressing themselves using words instead of numbers [7]. This is because humans are used to deal with concepts [8]. In the GDM process, consensus measures [9] will be used to help users to reach an agreement. In order to increase clarity and to give an example of a use case, the implemented application deals with the often complex problem of choosing a wine. In it, a set of users must decide which wine they should order depending on their tastes, the food that they have ordered, the price and the context. By combining a Fuzzy Wine Ontology [3], [10], group decision making (GDM) support algorithms [7] and the fuzzyDL reasoner [11] a Web Platform Application and an Android application have been developed and implemented. Every mobile that has an Internet connection will be able to use the application and users can get access to the knowledge at any time independent of their location and decide on the choice of wine. A GPS or IP location can also be used in order to determine the set of wines that are available at a certain location.

The paper is structured in the following way. First, Preliminaries are presented in Section 2. Section 3 presents the two implementations developed. Section 4 presents a Discussion and Analysis of the implemented applications and Section 5, summarizes some conclusions.

Section snippets

Preliminaries

To make this paper as self contained as possible, this section presents concepts and definitions that are used later on in the paper.

A Decision Support System for recommending wine

We combined the Fuzzy Wine Ontology with a decision support algorithm to create a novel Decision Support System that aids dinner guests to choose the most suitable wine for the occasion. Two different versions of the system were developed and implemented:

  • Web platform: This version was implemented using JavaServer Pages (JSP) and runs over a web browser in any device that has internet access.

  • Android application: This version consists of an Android app that can be downloaded and installed in any

Discussion

A novel application that combines fuzzy ontology with a decision support algorithm has been developed and implemented. The goal is to create a Decision Support System that helps users to choose the wine that best fits them for various types of food in different dinner contexts.

Thanks to the fuzzy ontology, the knowledge of wine connoisseurs is often offered in an imprecise, linguistic form available for the application users to benefit from. Dinner guests that do not know too much about wines

Conclusions

In this paper, web platform and Android applications for selecting a wine at a dinner party have been constructed and tested. Both applications employ a Fuzzy Wine Ontology as their main source of knowledge, making it possible to manage imprecise information in the process. These applications show that it is possible to offer good decision support with mobile devices. This is a good example of how knowledge mobilization can help people to process data and take advantage of it.

In the context of

Acknowledgments

This paper has been developed with the financing of FEDER funds in TIN2013-40658-P and Andalusian Excellence ProjectTIC-5991.

Juan Antonio Morente-Molinera is a PhD student in the department of Computer Science and Artificial Intelligence at the University of Granada. He is a member of the Soft Computing and Intelligence Information Systems research group. He holds an MSc in Soft Computing and Intelligence Systems and another one in High School, Language and Professional Training Teaching. His research interests are in group decision making, decision support systems, consensus models, linguistic modelling, fuzzy

References (53)

  • L.A. Zadeh

    Fuzzy sets

    Information and Control

    (1965)
  • A. Choudhury et al.

    Consensus-based intelligent group decision-making model for the selection of advanced technology

    Decision Support Systems

    (2006)
  • I. Palomares et al.

    An attitude-driven web consensus support system for heterogeneous group decision making

    Expert Systems with Applications

    (2013)
  • V. Nebot et al.

    Building data warehouses with semantic web data

    Decision Support Systems

    (2012)
  • T. Lukasiewicz et al.

    Managing uncertainty and vagueness in description logics for the semantic web

    Web Semantics: Science, Services and Agents on the World Wide Web

    (2008)
  • Y. Jiang et al.

    Reasoning and change management in modular fuzzy ontologies

    Expert Systems with Applications

    (2011)
  • F. Bobillo et al.

    Aggregation operators for fuzzy ontologies

    Applied Soft Computing

    (2013)
  • J. Kacprzyk

    Group decision making with a fuzzy linguistic majority

    Fuzzy Sets and Systems

    (1986)
  • J. Lan et al.

    Group decision making based on induced uncertain linguistic OWA operators

    Decision Support Systems

    (2013)
  • M. Reformat et al.

    Ontological approach to development of computing with words based systems

    International Journal of Approximate Reasoning

    (2009)
  • Y. Tang et al.

    Linguistic modelling and information coarsening based on prototype theory and label semantics

    International Journal of Approximate Reasoning

    (2009)
  • J. Morente-Molinera et al.

    On multi-granular fuzzy linguistic modeling in group decision making problems: a systematic review and future trends

    Knowledge-Based Systems

    (2015)
  • S. Alonso et al.

    A linguistic consensus model for web 2.0 communities

    Applied Soft Computing

    (2013)
  • J.A. Bateman et al.

    A linguistic ontology of space for natural language processing

    Artificial Intelligence

    (2010)
  • H.L. Gainforth et al.

    The role of interpersonal communication in the process of knowledge mobilization within a community-based organization: a network analysis

    Implementation Science

    (2014)
  • C. Carlsson et al.

    Fuzzy ontology used for knowledge mobilization

    International Journal of Intelligent Systems

    (2012)
  • Cited by (71)

    • Fudge: Fuzzy ontology building with consensuated fuzzy datatypes

      2020, Fuzzy Sets and Systems
      Citation Excerpt :

      Finally, Section 7 sets out some conclusions and ideas for future work. Fuzzy ontologies have already proved to be useful in several applications, such as information retrieval [8,44,50], Semantic Web and the Internet [42], ambient intelligence [15], ontology merging [46], matchmaking [37], decision making [33], summarization [25], construction [19], robotics [17], diabetes diagnosis [18], design [35], human resources [43], decision making [41], gait recognition [22], and many others [28,38]. For a more detailed overview, we refer the reader to [11].

    • Diagnosis of heart diseases by a secure Internet of Health Things system based on Autoencoder Deep Neural Network

      2020, Computer Communications
      Citation Excerpt :

      Additionally, it is also often tried to improve effectiveness and efficiency, by using hybrid methods in which different solution ways such as optimization algorithms and machine learning techniques are combined together for the classification [1,8,9]. It is also remarkable that the way of decision support systems is affected from the latest technological developments such as mobile communication or cloud systems [10,11]. Recently, the technology era is rising over many innovative solutions and the Internet of Things (IoT), which is known as a network of communicating smart devices [12,13] is among them.

    View all citing articles on Scopus

    Juan Antonio Morente-Molinera is a PhD student in the department of Computer Science and Artificial Intelligence at the University of Granada. He is a member of the Soft Computing and Intelligence Information Systems research group. He holds an MSc in Soft Computing and Intelligence Systems and another one in High School, Language and Professional Training Teaching. His research interests are in group decision making, decision support systems, consensus models, linguistic modelling, fuzzy ontologies and information aggregation.

    Dr Robin Wikström is currently a postdoc researcher in the Laboratory of Industrial Management at Åbo Akademi University in Finland. In his doctoral thesis in Information Systems at IAMSR he worked on decision support systems, fuzzy ontologies and knowledge mobilisation in research projects carried out in cooperation with major Finnish multinational corporations. His post-doc research topics represent a continuation of his thesis work, concentrating on facilitating decision making and encouraging decisions makers to think.

    Professor Enrique Herrera-Viedma is Professor of Computer Science and the Vice-President of Research and Innovation in University of Granada. He received the M.Sc. and Ph.D. degrees in Computer Science from the University of Granada in 1993 and 1996, respectively. His h-index is 48 with more than 7500 citations received [WoS]. He was identified in 2014 and 2015 as one of the world’s most influential researchers by the Shanghai Center and Thomson Reuters in both Computer Science and Engineering. His current research interests include group decision making, consensus models, linguistic modelling, and aggregation of information, information retrieval, bibliometric, digital libraries, web quality evaluation, recommender systems, and social media.

    Professor Christer Carlsson is the Research Director of the Institute for Advanced Management Systems Research [IAMSR] at Abo Akademi University and the Past President of the International Fuzzy Systems Association. He received his DSc (BA) degree from Abo Akademi University in Management Science in 1977. His h-index is 34 with more than 7000 citations [WoS]. He received the VII Kaufmann Prize and Gold Medal of SIGEF for research in uncertain management and economy, the Nystrom Prize for scientific excellence from Societas Scientarium Fennia and he is an IFSA Fellow and an IEEE Senior Member. At IAMSR he has worked on research projects in partnership with major Finnish multinational corporations; his research started with mathematical systems theory and operational research and then moved on to multi-criteria optimization, decision support systems, fuzzy optimization, foresight, soft computing, mobile value services, knowledge mobilization, fuzzy real options valuation and fuzzy ontology.

    View full text