Pablo J. Villacorta

A new fuzzy linguistic approach to qualitative Cross Impact Analysis

Graphical abstractDisplay Omitted HighlightsMICMAC and other Cross Impact Analysis methods used in Scenario Planning exhibit important drawbacks that need to be addressed.This work presents FLMICMAC, an improved version of MICMAC based on Computing with Words, fuzzy numbers and linguistic variables.FLMICMAC receives linguistic inputs describing the mutual influences between variables, operates with them and computes linguistic outputs.Our proposal shows both relative and absolute linguistic information about the role of the variables in the system, which is more informative for the decision-maker.The linguistic output can be plotted in two novel graphical representations that summarize the global behaviour of the system at a glance. Scenario Planning helps explore how the possible futures may look like and establishing plans to deal with them, something essential for any company, institution or country that wants to be competitive in this globalize world. In this context, Cross Impact Analysis is one of the most used methods to study the possible futures or scenarios by identifying the systems variables and the role they play in it. In this paper, we focus on the method called MICMAC (Impact Matrix Cross-Reference Multiplication Applied to a Classification), for which we propose a new version based on Computing with Words techniques and fuzzy sets, namely Fuzzy Linguistic MICMAC (FLMICMAC). The new method allows linguistic assessment of the mutual influence between variables, captures and handles the vagueness of these assessments, expresses the results linguistically, provides information in absolute terms and incorporates two new ways to visualize the results. Our proposal has been applied to a real case study and the results have been compared to the original MICMAC, showing the superiority of FLMICMAC as it gives more robust, accurate, complete and easier to interpret information, which can be very useful for a better understanding of the system.

Sensitivity analysis in the scenario method: A multi-objective approach

Technology foresight deals with the necessity of anticipating the future to better adapt to new situations regarding innovations that directly affect business world. One widely spread methodology in technology foresight is Godets Scenario Method, which includes a module (MICMAC) performing the so-called structural analysis. The goal of the structural analysis is to identify the most important variables in a system. To this end, it makes use of an influence matrix that describes the relations between the variables. This information is usually given by experts based on their own knowledge and experience. However, some of the information of the influence matrix may contain errors due to the subjective nature of the criteria and opinions of the experts. Here we propose a new analysis that follows a multi-objective approach and allows to measure the sensibility of the model versus possible errors at the input. The well-known NSGA-II algorithm has been used as a solver. The results are encouraging and deserve further investigation.

Theoretical analysis of expected payoff in an adversarial domain

Adversarial decision making is aimed at finding strategies for dealing with an adversary who observes our decisions and tries to learn our behavior pattern. Based on a simple mathematical model, the present contribution provides analytical expressions for the expected payoff when using simple strategies which try to balance confusion and payoff. Additional insights are provided regarding the structure of the payoff matrix. Computational experiments show the agreement between theoretical expressions and empirical simulations, thus paving the way to make the assessment of new strategies easier.

Expected payoff analysis of dynamic mixed strategies in an adversarial domain

Adversarial decision making is aimed at determining optimal decision strategies to deal with an adversarial and adaptive opponent. One defense against this adversary is to make decisions that are intended to confuse him, although our rewards can be diminished. In this contribution, we describe ongoing research in the design of time varying decision strategies for a a simple adversarial model. The strategies obtained are compared against static strategies from a theoretical and empirical point of view. The results show encouraging improvements that open new venues for research.

Evolutionary design and statistical assessment of strategies in an adversarial domain

Adversarial decision making is aimed at finding strategies for dealing with an adversary who observes our decisions and tries to learn our behaviour pattern. This contribution extends a simple mathematical model with strategies that vary along time, and motivates the use of heuristic search procedures to address the problem of finding good strategies within this new search space. The evaluation of this new class of strategies requires running a stochastic simulation so the comparison of strategies should be properly addressed. A new statistics-based technique for the comparison of strategies is also proposed and tested in this context when coupled with a Genetic Algorithm. Computational experiments showed that the new strategies are better than previous ones, and that the results obtained with this new comparison technique are encouraging.

Exploring Innovative and Successful Applications of Soft Computing

Antonio D. Masegosa received a degree in Computer Engineering in 2005 and a PhD degree in Computer Sciences in 2010 from the School of Computer and Telecommunications Engineering, University of Granada, Spain. From 2010 he has been working as a post-doc researcher in the Center for ICT of the University of Granada. He has published one book and more than 20 papers in leading scientific journals, international and national conferences. He has participated in a wide variety of research projects and he is currently involved in two: Applicability of the Soft Computing in Advance Technology Environments: Sustainability and Intelligent Software Platform for Unification of Police Services. He has attended to numerous national and international conferences and he has been member of the organizing committee of the VI Nature Inspired Cooperative Strategies for Optimization Conference (NICSO2013). His research interest includes Intelligent Systems, Soft Computing, Metaheuristics, Cooperative Strategies for Optimization and Technology Foresight among others. Released: November 2013 An Excellent Addition to Your Library!

A Linguistic Approach to Structural Analysis in Prospective Studies

One of the methodologies more used to accomplish prospective analysis is the scenario method. The first stage of this method is the so called structural analysis and aims to determine the most important variables of a system. Despite being widely used, structural analysis still presents some shortcomings, mainly due to the vagueness of the information used in this process. In this sense, the application of Soft Computing to structural analysis can contribute to reduce the impact of these problems by providing more interpretable and robust models. With this in mind, we present a methodology for structural analysis based on computing with words techniques to properly address vagueness and increase the interpretability. The method has been applied to a real problem with encouraging results.

Towards fuzzy linguistic Markov chains

In this contribution we deal with the problem of doing computations with a Markov chain when the information about transition probabilities is expressed linguistically. This could be the case, for instance, if the process we are modeling is described by a human expert, for whom the use of linguistic labels is easier than being forced to give inexact numerical probabilities which, in turn, may yield an unstable chain. We address the uncertainty of linguistic judgments by introducing fuzzy probabilities, and carry on the calculation of the linguistic stationary distribution of the chain by resorting to an existing fuzzy approach with restricted matrix multiplication. Preliminary results are very promising and deserve further research.

Exploiting Adversarial Uncertainty in Robotic Patrolling: A Simulation-Based Analysis

Recently, several models for autonomous robotic patrolling have been proposed and analysed on a game-theoretic basis. The common drawback of such models are the assumptions required to apply game theory analysis. Such assumptions do not usually hold in practice, especially perfect knowledge of the adversary’s strategy, and the belief that we are facing always a best-responser. However, the agents in the patrolling scenario may take advantage of that fact. In this work, we try to analyse from an empirical perspective a patrolling model with an explicit topology, and take advantage of the adversarial uncertainty caused by the limited, imperfect knowledge an agent can acquire through simple observation. The first results we report are encouraging.

FuzzyLP: An R Package for Solving Fuzzy Linear Programming Problems

An inherent limitation of Linear Programming is the need to know precisely all the conditions concerning the problem being modeled. This is not always possible as there exist uncertainty situations which require a more suitable approach. Fuzzy Linear Programming allows working with imprecise data and constraints, leading to more realistic models. Despite being a consolidated field with more than 30 years of existence, almost no software has been developed for public use that solves fuzzy linear programming problems. Here we present an open-source R package to deal with fuzzy constraints, fuzzy costs and fuzzy coefficients in linear programming. The theoretical foundations for solving each type of problem are introduced first, followed by code examples. The package is accompanied by a user manual and can be freely downloaded, employed and extended by any R user.