Social Networking Sites (SNS) offer a full set of possibilities to perform opinion studies such as polling or market analysis. Normally, artificial intelligence techniques are applied, and they often require supervised datasets. The process of building these is complex, time-consuming and expensive. In this paper, we propose to assist the labelling task by taking advantage of social network mechanics. In order to do that, we introduce theco-retweetrelation to build a graph that allows us to propagate user labels to their similarity neighbourhood. Therefore, it is possible to iteratively build supervised datasets with significant less human effort and with higher accuracy than other weak-supervision techniques. We tested our proposal with 3 datasets labelled by an expert committee, and results shows that it outperforms other weak-supervision techniques. This methodology may be adapted to other social networks and topics, and it is relevant for applications like informed decision-making (e.g., content moderation), specially when interpretability is required.

Hospital Information Systems (H.I.S) use Electronic Health Record to store heterogeneous data from the patients. One important goal in this kind of systems is that the information must be, normalized and codify with a clinical terminology to represent exactly the healthcare meaning. Usually this process need human experts to identify and map the correct concept, this is a slow and tedious task. One of the most widespread clinical terminologies with more projection is Snomed-CT. This is an ontology multilingual clinical terminology that represent the clinical concepts with a unique code. We introduce in this paper Snomed2Vec, new approach of semantic search tool to find the most similar concepts using Snomed-CT. This is an ontology based named entity recognition system using word embedding, that suggest what is the most similar concept, that appear in a text. To evaluate the tool we suggest two kind of validations, one against a corpus gold with diagnostic from clinical reports, and a social validation, with a public free web access. We publish an access web to the academic world to use, test and validate the tool. The results of validation shows that this process help to the specialist to the election of choose the correct concepts from Snomed-CT. The paper illustrates 1) how create the initial big corpus of texts, to train the word2vec models, 2) how we use this vector space model to create our final Snomed2Vec vector space model, 3) The use of the cosine similarity distance, to obtain the most similar concepts, grouping by the hierarchies from Snomed-CT. We publish to the academic world: https://github.com/NachusS/Snomed2Vec access to the public web tool, and the notebook, for develop and test this paper.

In this paper we propose a recognition system of medical concepts from free text clinical reports. Our approach tries to recognize also concepts which are named with local terminology, with medical writing scripts, short words, abbreviations and even spelling mistakes. We consider a clinical terminology ontology (Snomed-CT), as a dictionary of concepts. In a first step we obtain an embedding model using word2vec methodology from a big corpus database of clinical reports. Word vectors are positioned in the vector space such that words that share common contexts in the corpus are located in close proximity to one another in the space, and so the geometrical similarity can be considered a measure of semantic relation. We have considered 615513 emergency clinical reports from the Hospital "Rafael Méndez" in Lorca, Murcia. In these reports there are a lot of local language of the emergency domain, medical writing scripts, short words, abbreviations and even spelling mistakes. With the model obtained we represent the words and sentences as vectors, and by applying cosine similarity we identify which concepts of the ontology are named in the text. Finally, we represent the clinical reports (EHR) like a bag of concepts, and use this representation to search similar documents. The paper illustrates 1) how we build the word2vec model from the free text clinical reports, 2) How we extend the embedding from words to sentences, and 3) how we use the cosine similarity to identify concepts. The experimentation, and expert human validation, shows that: a) the concepts named in the text with the ontology terminology are well recognized, and b) others concepts that are not named with the ontology terminology are also recognized, obtaining a high precision and recall measures.

The use of embodied conversational agents (ECAs) in the primary health care educational field is rare, although it has been demonstrated that it has advantages over traditional learning processes. This is due to the high production and maintenance costs of creating a specific ECA for some domain. In this paper we describe a methodology to reduce the effort of creating virtual patients inside the virtual simulated patient framework. This framework is an ECA adapted to simulate a sick patient during an appointment with a primary health care doctor. In order to do it, the system separates patient's physical conditions and personal features, i.e. with the diseases they have, their personality or cultural level from the patient's behaviour. The modeling of physical conditions makes use of fuzzy aggregation functions and the behaviour of the patient employ a fuzzy rule based system to control the subjectivity associated to their personality. The advantage of this approach is that many different patients can be created without effort just creating the physical models that represent them and their behaviour are in accordance with the illnesses they suffer from and their personality.

In this paper we present an Embodied Conversational Agent (ECA) that simulates a real human patient presenting several symptoms for training medical students in the field of primary health care. Students interview the ECA to diagnose his diseases as a doctor would do in a real situation. This virtual patient can communicate using natural language and express different moods that depend on the diseases he suffers from and the student’s behavior. The ECA’s behavior is done by means of the coordination of several modules devoted to different tasks: Natural Language Understanding, Dialogue Management, Emotional State Control and Natural Language Generation. An ontology that gathers the domain knowledge of the agent specifies a semantic language that the modules use to communicate themselves. The system has two kinds of advantages. First, it offers a way to put in practice the theoretical knowledge acquired by the students in their degree courses and to improve the diagnostic and communicative skills decreasing the learning curve of these abilities, setting them for an interview process like the one they are going to face in their real job. Second, the system is ready to use at any time without needing special or expensive equipment, only a standard PC.

Usually, the rules in a fuzzy model contain in the antecedent a set of propositions each of which restricts a fuzzy variable to a single fuzzy value by means of the predicate equal-to. That way, each rule covers a single fuzzy region of the fuzzy grid. This paper proposes to extent this structure in order to provide more general fuzzy rules, in the sense of covering the input space as much as possible. In order to do this, new predicates are considered and an ant colony optimization algorithm is proposed to learn such fuzzy rules. The obtained fuzzy models provide two benefits: they are described with a lower number of rules and their accuracy improves with the increase in generalization introduced. Some experimental results illustrate these facts

In this paper, the FRIwE method is proposed to identify fuzzy models from examples. Such a method has been developed trying to achieve a double goal:accuracy and interpretability. In order to do that, maximal structure fuzzy rules are firstly obtained based on a method proposed by Castro et al. In a second stage, the conflicts generated by the maximal rules are solved, thus increasing the model accuracy. The resolution of conflicts are carried out by including exceptions in the rules. This strategy has been identified by psychologists with the learning mechanism employed by the human being, thus improving the model interpretability. Besides, in order to improve the interpretability even more, several methods are presented based on reducing and merging rules and exceptions in the model. The exhaustive use of the training examples gives the method a special suitability for problems with small training sets or high dimensionality. Finally, the method is applied to an example in order to analyze the achievement of the goals.

With identification methods that learn fuzzy rules directly from certainty degrees, we refer to methods that select the most promising rules from the training examples in only one pass. In order to do that, these methods employ a certainty measure to assess the goodness of each rule. This paper aims to analyze in depth the behaviors and features of two different strategies for identifying fuzzy models from certainty degrees, each of both combined with one of two well-known alternatives for measuring the certainty degrees of the rules. With this aim, the advantages and drawbacks of each method are analyzed experimentally by considering the model error when applied to several systems. Besides, the robustness of the results is investigated by applying the methods to noisy data. As a conclusion, a new method combining the best components of the previously considered methods is proposed and its results are analyzed. The achieved performance in accuracy and computational cost shows the benefit of this new method.

In this paper, we develop a technique for acquiring the finite set of attributes or variables which the expert uses in a classification problem for characterising and discriminating a set of elements. This set will constitute the schema of a training data set to which an inductive learning algorithm will be applied. The technique developed uses ideas taken from psychology, in particular from Kelly's Personal Construct Theory. While we agree that Kelly's repertory grid technique is an efficient way to do this, it has several disadvantages which we shall try to solve by using a fuzzy repertory table. With the suggested technique, we aim to obtain the set of attributes and values which the expert can use to "measure" the object type (class) on the classification problem in some way. We will also acquire some general rules to identify the expert's evident knowledge; these rules will comprise concepts belonging to their conceptual structure.

This paper presents an extension of the method presented by Benitez et al (1997) for extracting fuzzy rules from an artificial neural network (ANN) that express exactly its behavior. The extraction process provides an interpretation of the ANN in terms of fuzzy rules. The fuzzy rules presented are in accordance with the domain of the input variables. These rules use a new operator in the antecedent. The properties and intuitive meaning of this operator are studied. Next, the role of the biases in the fuzzy rule-based systems is analyzed. Several examples are presented to comment on the obtained fuzzy rule-based systems. Finally, the interpretation of ANNs with two or more hidden layers is also studied.

In this paper, a model to represent knowledge (MORSE) that abstracts the structure of an automatic system is presented. This model is able to represent several ways of human reasoning, structured knowledge, execution strategies of an automatic system and many models presented in different works, such as hierarchical fuzzy controllers, cascade correlation neural networks architecture, decision trees, multilayer perceptrons, etc. Finally, thanks to the high level of abstraction of MORSE, the automatic systems specified by means of this model, have been classified in terms of their general features. This classification could allow a designer of systems to choose the best model of an automatic system to solve a problem. ©2000 John Wiley & Sons, Inc.

This article presents a machine learning method for solving classification and approximation problems. This method uses the divide-and-conquer algorithm design technique (taken from machine learning models based on a tree), with the aim of achieving design ease and good results on the training examples and allows semi-global actions on its computational elements (a feature taken from neural networks), with the aim of attaining good generalization and good behavior in the presence of noise in training examples. Finally, some results obtained after solving several problems with a particular implementation of SEPARATE are presented together with their analysis.

Artificial neural networks are efficient computing models which have shown their strengths in solving hard problems in artificial intelligence. They have also been shown to be universal approximators. Notwithstanding, one of the major criticisms is their being black boxes, since no satisfactory explanation of their behavior has been offered. In this paper, we provide such an interpretation of neural networks so that they will no longer be seen as black boxes. This is stated after establishing the equality between a certain class of neural nets and fuzzy rule-based systems. This interpretation is built with fuzzy rules using a new fuzzy logic operator which is defined after introducing the concept of f-duality. In addition, this interpretation offers an automated knowledge acquisition procedure.

The aim of this article is to design a truth maintenance system (TMS) which allows us to overcome some of the shortcomings of the use of multivalued logic versus classical logic in the deduction process. The detection of inconsistencies, belief revision, and justification of results obtained are some of these shortcomings. The notion of context associated to a specific proposition is incorporated. © 1996 John Wiley & Sons, Inc.

In this paper, we consider a fundamental theoretical question: Is it always possible to design a fuzzy system capable of approximating any real continuous function on a compact set with arbitrary accuracy? Moreover, we research whether the answer to the above question is positive when we restrict to a fixed (but arbitrary) type of fuzzy reasoning and to a subclass of fuzzy relations. This result can be viewed as an existence theorem of an optimal fuzzy system for a wide variety of problems.

In this paper, we consider a fundamental theoretical question on why does fuzzy control have such a good performance for a wide variety of practical problems. We try to answer this fundamental question by proving that for each fixed fuzzy logic belonging to a wide class of fuzzy logics, and for each fixed type of membership function belonging to a wide class of membership functions, the fuzzy logic control systems using these two and any method of defuzzification are capable of approximating any real continuous function on a compact set to arbitrary accuracy. On the other hand, this result can be viewed as an existence theorem of an optimal fuzzy logic control system for a wide variety of problems.>

This article discusses the applications of fuzzy boolean programming problems for representing and reasoning with propositional knowledge. the use of the models provided by the fuzzy boolean problems are proposed to answer imprecise questions in precisely stated knowledge-based systems. Also, the advantages of using fuzzy boolean programming instead of classical ones are presented in the framework of propositional knowledge. © 1994 John Wiley & Sons, Inc.

In this paper we will show that the different definitions of contradiction obtained in the literature can be modeled by means of an incompatibility relation.