Neural networks complemented with genetic algorithms and fuzzy systems for predicting nitrogenous effluent variables in wastewater treatment plants

This work focuses on the prediction of the two main nitrogenous variables that describe the water quality at the effluent of a Wastewater Treatment Plant. We have developed two kind of Neural Networks architectures based on considering only one output or, in the other hand, the usual five effluent variables that define the water quality: suspended solids, biochemical organic matter, chemical organic matter, total nitrogen and total Kjedhal nitrogen. Two learning techniques based on a classical adaptative gradient and a Kalman filter have been implemented. In order to try to improve generalization and performance we have selected variables by means genetic algorithms and fuzzy systems. The training, testing and validation sets show that the final networks are able to learn enough well the simulated available data specially for the total nitrogen

Estudi i implementació d'un sistema multiagent intel·ligent i la seva aplicació a sistemes difusos

Estudi i implementació d'un sistema multiagent intel·ligent i la seva aplicació a sistemes difusos. Utilització de les llibreries JADE i JFuzzyLogic.

Anàlisis del modelo de la telaraña en contexto de incertidumbre

In the present work the behavior of a model acquaintance of market is analyzed with an only one, in that is considered that the parameters that tie the variables that it incorporates the pattern come expressed through uncertain magnitudes. The objective of the study consists on the analysis of the balance from the hypotheses of established uncertainties

The connection between distortion risk measures and ordered weighted averaging operators

Distortion risk measures summarize the risk of a loss distribution by means of a single value. In fuzzy systems, the Ordered Weighted Averaging (OWA) and Weighted Ordered Weighted Averaging (WOWA) operators are used to aggregate a large number of fuzzy rules into a single value. We show that these concepts can be derived from the Choquet integral, and then the mathematical relationship between distortion risk measures and the OWA and WOWA operators for discrete and finite random variables is presented. This connection offers a new interpretation of distortion risk measures and, in particular, Value-at-Risk and Tail Value-at-Risk can be understood from an aggregation operator perspective. The theoretical results are illustrated in an example and the degree of orness concept is discussed.

Análisis económico de una función cuadrática de gastos de producción con coeficientes borrosos

En el ámbito de la Economía de la Empresa tiene mucha importancia el estudio de los gastos de producción E(Q) que se originarán en el proceso y que generalmente vendrán expresados matemáticamente por una dependencia lineal o cuadrática de las unidades Q que se proponen fabricar. Supondremos, además, que esta función está afectada por dos restricciones: una es de productividad, Q1 ≤ Q2 ≤ Q3 , y otra de limitación de gastos máximos permitidos, E(Q) ≤ EM . En el presente artículo partiremos de una función cuadrática nítida, en la cual justificaremos el signo de los coeficientes que hemos empleado. Después, para adentrarnos en el campo fuzzy, la generalizaremos con otra de coeficientes borrosos. Naturalmente, la nueva función borrosa ya no se expresará a través de una única curva, sino que estará constituida por un haz infinito de curvas nítidas, cada una de ellas con un determinado grado de posibilidad. Centramos nuestra atención en las curvas que llamamos central, inferior y superior. El núcleo de nuestro análisis consistirá básicamente en reducir paulatinamente los soportes de los coeficientes hasta hallar un cierto valor k del α-corte, de manera que a partir de él todas las curvas del haz borroso tengan sentido económico y cumplan las dos restricciones impuestas. En último lugar, y a través de un caso numérico, comprobaremos las deducciones teóricas que hemos obtenido en el análisis anterior

Student modeling based on fuzzy inference mechanisms

The paper presents a competence-based instructional design system and a way to provide a personalization of navigation in the course content. The navigation aid tool builds on the competence graph and the student model, which includes the elements of uncertainty in the assessment of students. An individualized navigation graph is constructed for each student, suggesting the competences the student is more prepared to study. We use fuzzy set theory for dealing with uncertainty. The marks of the assessment tests are transformed into linguistic terms and used for assigning values to linguistic variables. For each competence, the level of difficulty and the level of knowing its prerequisites are calculated based on the assessment marks. Using these linguistic variables and approximate reasoning (fuzzy IF-THEN rules), a crisp category is assigned to each competence regarding its level of recommendation.

Integrating defeasible argumentation with fuzzy ART neural networks for pattern classification

Many classification systems rely on clustering techniques in which a collection of training examples is provided as an input, and a number of clusters c1,...cm modelling some concept C results as an output, such that every cluster ci is labelled as positive or negative. Given a new, unlabelled instance enew, the above classification is used to determine to which particular cluster ci this new instance belongs. In such a setting clusters can overlap, and a new unlabelled instance can be assigned to more than one cluster with conflicting labels. In the literature, such a case is usually solved non-deterministically by making a random choice. This paper presents a novel, hybrid approach to solve this situation by combining a neural network for classification along with a defeasible argumentation framework which models preference criteria for performing clustering.

Adding similarity-based reasoning capabilities to a Horn fragment of possibilistic logic with fuzzy constants

PLFC is a first-order possibilistic logic dealing with fuzzy constants and fuzzily restricted quantifiers. The refutation proof method in PLFC is mainly based on a generalized resolution rule which allows an implicit graded unification among fuzzy constants. However, unification for precise object constants is classical. In order to use PLFC for similarity-based reasoning, in this paper we extend a Horn-rule sublogic of PLFC with similarity-based unification of object constants. The Horn-rule sublogic of PLFC we consider deals only with disjunctive fuzzy constants and it is equipped with a simple and efficient version of PLFC proof method. At the semantic level, it is extended by equipping each sort with a fuzzy similarity relation, and at the syntactic level, by fuzzily “enlarging” each non-fuzzy object constant in the antecedent of a Horn-rule by means of a fuzzy similarity relation.