Tommaso Pirotti

Being Healthy in Fuzzy Logic: The Case of Italy

Health is a crucial dimension of individual well being and it is in itself multidimensional and complex. In this paper we tackle this complexity by using fuzzy expert logic that allows us to keep its complexity and at the same time to get crisp indicators that can be used to measure its status. The applied analysis refers to a country, Italy, that shows a high regional variability in health achievements related to the different diffusion and quality of health services across Italy. The source of data used for this purpose is the Italian National Statistical Institute (ISTAT) survey on health conditions. We proceed with a comparison of the results of the application of fuzzy logic to health measurement to a more standard methodology (SF-12) outlining the advantages of using fuzzy logic. The obtained fuzzy measure of health is then analyzed by means of multivariate analysis that confirms regional variability, lower health achievements for women, elderly and lower educated individuals. People in nonstandard working positions (like temporary contract) or unemployed show a lower health achievement too.

A fuzzy approach to face the multidimensional aspects of well-being

The new impulse from European Commissions “Beyond GDP” and the Stiglitz, Sen and Fitoussis report renewed the necessity to define new indicators of well-being that go beyond GDP, and increased the need of measuring complex dimensions of living not measurable with classical techniques. Concepts as quality of life, child well being, health are mediated by human perception and intangible evaluation. A fuzzy logic approach gives the opportunity to face these problems thanks to its capability to work in a framework of uncertainty, ambiguity and vague information, situations that are typical of social and human problems. This paper provides the results based on different socioeconomic surveys with the use of fuzzy logic.

A New Definition of Evaluation/Defuzzification of an Interval Type-2 Fuzzy Set

In this paper we propose a new evaluation/defuzzification formula for an Interval Type-2 Fuzzy Quantity (IT2 FQ), that is an Interval Type-2 Fuzzy Set (IT2 FS) defined by two Type-1 Fuzzy Quantities (T1 FQs) having membership functions that may be neither convex nor normal. We start from a parametric formula to evaluate them and we propose to call the IT2 FQ value their average. To compare the results we obtain changing the parameters, we use the final output of an example of Interval Type-2 Fuzzy Logic System (IT2 FLS).

Quality of work and elderly care - Preliminary experiments

This paper focuses on the definition and measurement of quality of work (QoW) using a multidimensional approach, based on fuzzy logic. The multidimensional nature of quality of work has been widely acknowledged in economic and sociological literature and attempts at measuring its different dimensions can be found at European level in the work carried out by the European Foundation for the Improvement of living and working conditions. The European Commission and the International Labour Office have also identified different dimensions for quality of work and proposed new indicators to measure them. In this paper an attempt is made to maintain the complexity of the quality of work concept by using a technique that allows measurement without introducing too strong assumptions and makes the rules for judging the different dimensions of QoW and their interactions explicit.

The Ordinal Controversy and the Fuzzy Inference System Through an Application and Simulation to Teaching Activity Evaluation

The handling of ordinal variables presents many difficulties in both the measurements phase and the statistical data analysis. Many efforts have been made to overcome them. An alternative approach to traditional methods used to process ordinal data has been developed over the last two decades. It is based on a fuzzy inference system and is presented, here, applied to the student evaluations of teaching data collected via Internet in Modena, during the academic year 2009/10, by a questionnaire containing items with a four-point Likert scale. The scores emerging from the proposed fuzzy inference system proved to be approximately comparable to scores obtained through the practical, but questionable, procedure based on the average of the item value labels. The fuzzification using a number of membership functions smaller than the number of modalities of input variables yielded outputs that were closer to the average of the item value labels. The Center-of-Area defuzzification method showed good performances and lower dispersion around the mean of the value labels.

Fuzzy Inference System to Analyze Ordinal Variables

The handling of ordinal variables presents many difficulties in both the measurements phase and the statistical data analysis. Many efforts have been made to overcome them. An alternative approach to traditional methods used to process ordinal data has been developed over the last two decades. It is based on a fuzzy inference system and is presented, here, applied to the student evaluations of teaching data collected via Internet in Modena, during the academic year 2009/10, by a questionnaire containing items with a four-point Likert scale. The scores emerging from the proposed fuzzy inference system proved to be approximately comparable to scores obtained through the practical, but questionable, procedure based on the average of the item value labels. The fuzzification using a number of membership functions smaller than the number of modalities of input variables yielded outputs that were closer to the average of the item value labels. The Center-of-Area defuzzification method showed good performances and lower dispersion around the mean of the value labels.