Architecture for text normalization using statistical machine translation techniques

This paper proposes an architecture, based on statistical machine translation, for developing the text normalization module of a text to speech conversion system. The main target is to generate a language independent text normalization module, based on data and flexible enough to deal with all situa-tions presented in this task. The proposed architecture is composed by three main modules: a tokenizer module for splitting the text input into a token graph (tokenization), a phrase-based translation module (token translation) and a post-processing module for removing some tokens. This paper presents initial exper-iments for numbers and abbreviations. The very good results obtained validate the proposed architecture.

Sur une méthode algorithmique de synthése d'une machine séquentielle

Dans le problème de la synthèse d'une machine séquentielle, on peut, grosso modo, distinguer trois étapes : le passage des données du système à construire à la représentation tabulée (table de fluence ou table des phases, dans le cas d'un système asynchrone);le codage des états internes de cette table (de façon,dans le cas d'une machine synchrone, à obtenir si possible une décomposition en sous-machines, et,dans le cas d'une machine asynchrone, de façon à éviter les phénomènes de courses et d'aléas); enfin,l'écriture des équations et le dessin du schéma logique de la machine (en essayant par exemple de minimaliser le nombre de composants nécessaires à la. réalisation du circuit).

New generation of human machine interfaces for controlling UAV through depth based gesture recognition

New forms of natural interactions between human operators and UAVs (Unmanned Aerial Vehicle) are demanded by the military industry to achieve a better balance of the UAV control and the burden of the human operator. In this work, a human machine interface (HMI) based on a novel gesture recognition system using depth imagery is proposed for the control of UAVs. Hand gesture recognition based on depth imagery is a promising approach for HMIs because it is more intuitive, natural, and non-intrusive than other alternatives using complex controllers. The proposed system is based on a Support Vector Machine (SVM) classifier that uses spatio-temporal depth descriptors as input features. The designed descriptor is based on a variation of the Local Binary Pattern (LBP) technique to efficiently work with depth video sequences. Other major consideration is the especial hand sign language used for the UAV control. A tradeoff between the use of natural hand signs and the minimization of the inter-sign interference has been established. Promising results have been achieved in a depth based database of hand gestures especially developed for the validation of the proposed system.

TIMPANO: Technology for complex Human-Machine conversational interaction with dynamic learning

El proyecto TIMPANO tiene por objetivo profundizar en el desarrollo de sistemas de comunicación oral hombre-máquina atendiendo principalmente a la capacidad de dar respuesta a múltiples requerimientos de los usuarios, como pueden ser el acceso a información, la extracción de información, o el análisis de grandes repositorios de información en audio. En el proyecto se hace especial énfasis en la adaptación dinámica de los modelos a diversos contextos, tanto de tipo acústico, como semántico o de idioma.

Deriving the full-reducing Krivine machine from the small-step operational semantics of normal order

We derive by program transformation Pierre Crégut s full-reducing Krivine machine KN from the structural operational semantics of the normal order reduction strategy in a closure-converted pure lambda calculus. We thus establish the correspondence between the strategy and the machine, and showcase our technique for deriving full-reducing abstract machines. Actually, the machine we obtain is a slightly optimised version that can work with open terms and may be used in implementations of proof assistants.

A machine learning approach to identify clinical trials involving nanodrugs and nanodevices from ClinicalTrials.gov

BACKGROUND: Clinical Trials (CTs) are essential for bridging the gap between experimental research on new drugs and their clinical application. Just like CTs for traditional drugs and biologics have helped accelerate the translation of biomedical findings into medical practice, CTs for nanodrugs and nanodevices could advance novel nanomaterials as agents for diagnosis and therapy. Although there is publicly available information about nanomedicine-related CTs, the online archiving of this information is carried out without adhering to criteria that discriminate between studies involving nanomaterials or nanotechnology-based processes (nano), and CTs that do not involve nanotechnology (non-nano). Finding out whether nanodrugs and nanodevices were involved in a study from CT summaries alone is a challenging task. At the time of writing, CTs archived in the well-known online registry ClinicalTrials.gov are not easily told apart as to whether they are nano or non-nano CTs-even when performed by domain experts, due to the lack of both a common definition for nanotechnology and of standards for reporting nanomedical experiments and results. METHODS: We propose a supervised learning approach for classifying CT summaries from ClinicalTrials.gov according to whether they fall into the nano or the non-nano categories. Our method involves several stages: i) extraction and manual annotation of CTs as nano vs. non-nano, ii) pre-processing and automatic classification, and iii) performance evaluation using several state-of-the-art classifiers under different transformations of the original dataset. RESULTS AND CONCLUSIONS: The performance of the best automated classifier closely matches that of experts (AUC over 0.95), suggesting that it is feasible to automatically detect the presence of nanotechnology products in CT summaries with a high degree of accuracy. This can significantly speed up the process of finding whether reports on ClinicalTrials.gov might be relevant to a particular nanoparticle or nanodevice, which is essential to discover any precedents for nanotoxicity events or advantages for targeted drug therapy.

Teaching Planning of Forestry Engineering in Spain : origins and evolution

This paper addresses the historical evolution of, from its inception, to the present day, within the changing context of EHEA and linked to professional competences. The research methodology, although it is mainly a historical document review, expert opinions on university educational planning of university education of forestry engineering in Spain are also included. The results show the evolution of centralized planning, based on technical knowledge transmission to an approach based on competences (technical, contextual and behavioral) focusing on learning for improving employability.

Generation of human computational models with machine learning

Services in smart environments pursue to increase the quality of people?s lives. The most important issues when developing this kind of environments is testing and validating such services. These tasks usually imply high costs and annoying or unfeasible real-world testing. In such cases, artificial societies may be used to simulate the smart environment (i.e. physical environment, equipment and humans). With this aim, the CHROMUBE methodology guides test engineers when modeling human beings. Such models reproduce behaviors which are highly similar to the real ones. Originally, these models are based on automata whose transitions are governed by random variables. Automaton?s structure and the probability distribution functions of each random variable are determined by a manual test and error process. In this paper, it is presented an alternative extension of this methodology which avoids the said manual process. It is based on learning human behavior patterns automatically from sensor data by using machine learning techniques. The presented approach has been tested on a real scenario, where this extension has given highly accurate human behavior models,

Modelling agro-forestry scenarios for ammonia abatement in the landscape

Ammonia emissions from livestock production can have negative impacts on nearby protected sites and ecosystems that are sensitive to eutrophication and acidification. Trees are effective scavengers of both gaseous and particulate pollutants from the atmosphere making tree belts potentially effective landscape features to support strategies aiming to reduce ammonia impacts. This research used the MODDAS-THETIS a coupled turbulence and deposition turbulence model, to examine the relationships between tree canopy structure and ammonia capture for three source types?animal housing, slurry lagoon, and livestock under a tree canopy. By altering the canopy length, leaf area index, leaf area density, and height of the canopy in the model the capture efficiencies varied substantially. A maximum of 27% of the emitted ammonia was captured by tree canopy for the animal housing source, for the slurry lagoon the maximum was 19%, while the livestock under trees attained a maximum of 60% recapture. Using agro-forestry systems of differing tree structures near ?hot spots? of ammonia in the landscape could provide an effective abatement option for the livestock industry that complements existing source reduction measures.

Fast 2D to 3D conversion using a clustering-based hierarchical search in a machine learning framework

Automatic 2D-to-3D conversion is an important application for filling the gap between the increasing number of 3D displays and the still scant 3D content. However, existing approaches have an excessive computational cost that complicates its practical application. In this paper, a fast automatic 2D-to-3D conversion technique is proposed, which uses a machine learning framework to infer the 3D structure of a query color image from a training database with color and depth images. Assuming that photometrically similar images have analogous 3D structures, a depth map is estimated by searching the most similar color images in the database, and fusing the corresponding depth maps. Large databases are desirable to achieve better results, but the computational cost also increases. A clustering-based hierarchical search using compact SURF descriptors to characterize images is proposed to drastically reduce search times. A significant computational time improvement has been obtained regarding other state-of-the-art approaches, maintaining the quality results.

Validation Study of the Use of Matlab/Simulink Synchronous-Machine Block for Accurate Power-Plant Stability Studies

This paper presents results of the validity study of the use of MATLAB/Simulink synchronous-machine block for power-system stability studies. Firstly, the waveforms of the theoretical synchronous-generator short-circuit currents are described. Thereafter, the comparison between the currents obtained through the simulation model in the sudden short-circuit test, are compared to the theoretical ones. Finally, the factory tests of two commercial generating units are compared to the response of the synchronous generator simulation block during sudden short-circuit, set with the same real data, with satisfactory results. This results show the validity of the use of this generator block for power plant simulation.

Machine Learning in Scientometrics

El aprendizaje automático y la cienciometría son las disciplinas científicas que se tratan en esta tesis. El aprendizaje automático trata sobre la construcción y el estudio de algoritmos que puedan aprender a partir de datos, mientras que la cienciometría se ocupa principalmente del análisis de la ciencia desde una perspectiva cuantitativa. Hoy en día, los avances en el aprendizaje automático proporcionan las herramientas matemáticas y estadísticas para trabajar correctamente con la gran cantidad de datos cienciométricos almacenados en bases de datos bibliográficas. En este contexto, el uso de nuevos métodos de aprendizaje automático en aplicaciones de cienciometría es el foco de atención de esta tesis doctoral. Esta tesis propone nuevas contribuciones en el aprendizaje automático que podrían arrojar luz sobre el área de la cienciometría. Estas contribuciones están divididas en tres partes: Varios modelos supervisados (in)sensibles al coste son aprendidos para predecir el éxito científico de los artículos y los investigadores. Los modelos sensibles al coste no están interesados en maximizar la precisión de clasificación, sino en la minimización del coste total esperado derivado de los errores ocasionados. En este contexto, los editores de revistas científicas podrían disponer de una herramienta capaz de predecir el número de citas de un artículo en el fututo antes de ser publicado, mientras que los comités de promoción podrían predecir el incremento anual del índice h de los investigadores en los primeros años. Estos modelos predictivos podrían allanar el camino hacia nuevos sistemas de evaluación. Varios modelos gráficos probabilísticos son aprendidos para explotar y descubrir nuevas relaciones entre el gran número de índices bibliométricos existentes. En este contexto, la comunidad científica podría medir cómo algunos índices influyen en otros en términos probabilísticos y realizar propagación de la evidencia e inferencia abductiva para responder a preguntas bibliométricas. Además, la comunidad científica podría descubrir qué índices bibliométricos tienen mayor poder predictivo. Este es un problema de regresión multi-respuesta en el que el papel de cada variable, predictiva o respuesta, es desconocido de antemano. Los índices resultantes podrían ser muy útiles para la predicción, es decir, cuando se conocen sus valores, el conocimiento de cualquier valor no proporciona información sobre la predicción de otros índices bibliométricos. Un estudio bibliométrico sobre la investigación española en informática ha sido realizado bajo la cultura de publicar o morir. Este estudio se basa en una metodología de análisis de clusters que caracteriza la actividad en la investigación en términos de productividad, visibilidad, calidad, prestigio y colaboración internacional. Este estudio también analiza los efectos de la colaboración en la productividad y la visibilidad bajo diferentes circunstancias. ABSTRACT Machine learning and scientometrics are the scientific disciplines which are covered in this dissertation. Machine learning deals with the construction and study of algorithms that can learn from data, whereas scientometrics is mainly concerned with the analysis of science from a quantitative perspective. Nowadays, advances in machine learning provide the mathematical and statistical tools for properly working with the vast amount of scientometrics data stored in bibliographic databases. In this context, the use of novel machine learning methods in scientometrics applications is the focus of attention of this dissertation. This dissertation proposes new machine learning contributions which would shed light on the scientometrics area. These contributions are divided in three parts: Several supervised cost-(in)sensitive models are learned to predict the scientific success of articles and researchers. Cost-sensitive models are not interested in maximizing classification accuracy, but in minimizing the expected total cost of the error derived from mistakes in the classification process. In this context, publishers of scientific journals could have a tool capable of predicting the citation count of an article in the future before it is published, whereas promotion committees could predict the annual increase of the h-index of researchers within the first few years. These predictive models would pave the way for new assessment systems. Several probabilistic graphical models are learned to exploit and discover new relationships among the vast number of existing bibliometric indices. In this context, scientific community could measure how some indices influence others in probabilistic terms and perform evidence propagation and abduction inference for answering bibliometric questions. Also, scientific community could uncover which bibliometric indices have a higher predictive power. This is a multi-output regression problem where the role of each variable, predictive or response, is unknown beforehand. The resulting indices could be very useful for prediction purposes, that is, when their index values are known, knowledge of any index value provides no information on the prediction of other bibliometric indices. A scientometric study of the Spanish computer science research is performed under the publish-or-perish culture. This study is based on a cluster analysis methodology which characterizes the research activity in terms of productivity, visibility, quality, prestige and international collaboration. This study also analyzes the effects of collaboration on productivity and visibility under different circumstances.

Implementación de una Support Vector Machine en RVC – CAL para imágenes hiperespectrales

El análisis de imágenes hiperespectrales permite obtener información con una gran resolución espectral: cientos de bandas repartidas desde el espectro infrarrojo hasta el ultravioleta. El uso de dichas imágenes está teniendo un gran impacto en el campo de la medicina y, en concreto, destaca su utilización en la detección de distintos tipos de cáncer. Dentro de este campo, uno de los principales problemas que existen actualmente es el análisis de dichas imágenes en tiempo real ya que, debido al gran volumen de datos que componen estas imágenes, la capacidad de cómputo requerida es muy elevada. Una de las principales líneas de investigación acerca de la reducción de dicho tiempo de procesado se basa en la idea de repartir su análisis en diversos núcleos trabajando en paralelo. En relación a esta línea de investigación, en el presente trabajo se desarrolla una librería para el lenguaje RVC – CAL – lenguaje que está especialmente pensado para aplicaciones multimedia y que permite realizar la paralelización de una manera intuitiva – donde se recogen las funciones necesarias para implementar el clasificador conocido como Support Vector Machine – SVM. Cabe mencionar que este trabajo complementa el realizado en [1] y [2] donde se desarrollaron las funciones necesarias para implementar una cadena de procesado que utiliza el método unmixing para procesar la imagen hiperespectral. En concreto, este trabajo se encuentra dividido en varias partes. La primera de ellas expone razonadamente los motivos que han llevado a comenzar este Trabajo de Investigación y los objetivos que se pretenden conseguir con él. Tras esto, se hace un amplio estudio del estado del arte actual y, en él, se explican tanto las imágenes hiperespectrales como sus métodos de procesado y, en concreto, se detallará el método que utiliza el clasificador SVM. Una vez expuesta la base teórica, nos centraremos en la explicación del método seguido para convertir una versión en Matlab del clasificador SVM optimizado para analizar imágenes hiperespectrales; un punto importante en este apartado es que se desarrolla la versión secuencial del algoritmo y se asientan las bases para una futura paralelización del clasificador. Tras explicar el método utilizado, se exponen los resultados obtenidos primero comparando ambas versiones y, posteriormente, analizando por etapas la versión adaptada al lenguaje RVC – CAL. Por último, se aportan una serie de conclusiones obtenidas tras analizar las dos versiones del clasificador SVM en cuanto a bondad de resultados y tiempos de procesado y se proponen una serie de posibles líneas de actuación futuras relacionadas con dichos resultados. ABSTRACT. Hyperspectral imaging allows us to collect high resolution spectral information: hundred of bands covering from infrared to ultraviolet spectrum. These images have had strong repercussions in the medical field; in particular, we must highlight its use in cancer detection. In this field, the main problem we have to deal with is the real time analysis, because these images have a great data volume and they require a high computational power. One of the main research lines that deals with this problem is related with the analysis of these images using several cores working at the same time. According to this investigation line, this document describes the development of a RVC – CAL library – this language has been widely used for working with multimedia applications and allows an optimized system parallelization –, which joins all the functions needed to implement the Support Vector Machine – SVM - classifier. This research complements the research conducted in [1] and [2] where the necessary functions to implement the unmixing method to analyze hyperspectral images were developed. The document is divided in several chapters. The first of them introduces the motivation of the Master Thesis and the main objectives to achieve. After that, we study the state of the art of some technologies related with this work, like hyperspectral images, their processing methods and, concretely, the SVM classifier. Once we have exposed the theoretical bases, we will explain the followed methodology to translate a Matlab version of the SVM classifier optimized to process an hyperspectral image to RVC – CAL language; one of the most important issues in this chapter is that a sequential implementation is developed and the bases of a future parallelization of the SVM classifier are set. At this point, we will expose the results obtained in the comparative between versions and then, the results of the different steps that compose the SVM in its RVC – CAL version. Finally, we will extract some conclusions related with algorithm behavior and time processing. In the same way, we propose some future research lines according to the results obtained in this document.

The role of visualizations in urban forestry. Conclusions from managers’ perspectives

La presente tesis examina el uso potencial y actual de las técnicas de simulación visual aplicadas al campo de la gestión y la planificación del arbolado urbano. El estudio incluye las aplicaciones potenciales de las visualizaciones por ordenador, así como los beneficios que esto acarrearía. También se analizan las posibles barreras que surgirían de la implementación de esta nueva herramienta y se ofrece una lista de recomendaciones para superarlas. La investigación tiene un carácter exploratorio que utiliza una combinación de técnicas de investigación cuantitativas y cualitativas, dónde se emplean cuestionarios y entrevistas personales semi-estructuradas para estudiar y analizar las opiniones y reacciones de los gestores de arbolado urbano de los distritos de la ciudad de Londres (Reino Unido), denominados Tree Officers (LTOs). Para el desarrollo de la tesis se recopilaron y analizaron las respuestas al cuestionario del 41 por ciento de los LTOs pertenecientes al 88 por ciento de los distritos de Londres y se realizaron un total de 17 entrevistas personales. Los resultados del análisis estadístico de las respuestas del cuestionario y los análisis cruzados de las distintas variables se complementaron con las conclusiones obtenidas del análisis temático de los datos cualitativos recopilados durante las entrevistas. Los usos potenciales de las técnicas de simulación visual aplicadas a la gestión y planificación del arbolado urbano sugeridos fueron obtenidos combinado las conclusiones de, primero, la comparación de las cuestiones que los LTOs consideraron que más tiempo y recursos necesitaban y que actualmente no era posible resolverlas satisfactoriamente con las herramientas y los procesos disponibles, con la información acerca de cómo se habían empleado las visualizaciones en situaciones similares en otros campos tales como planificación urbano, el paisajismo o la gestión forestal. Segundo, se analizaron las reacciones y opiniones de los LTOs ante un conjunto de visualizaciones presentadas durante las entrevistas, desarrolladas ad hoc para mostrar un abanico representativo de ejemplos de utilización de las técnicas de simulación visual, que, a su vez se complementaron con los usos adicionales que los propios LTOs sugirieron tras ver las visualizaciones presentadas. Los resultados muestran que el uso actual de simulaciones visuales por parte de los LTOs es muy limitado pero si que reciben un gran número de visualizaciones de otros departamentos y como parte de la documentación presentada en las solicitudes de permisos para edificación o desarrollo urbanístico. Los resultados indican que las visualizaciones que son presentadas a los LTOs no son objetivas ni precisas por lo que se argumenta que esta situación es un factor importante que impide una toma de decisiones adecuada y una correcta transmisión de infracción al público y al resto de partes implicadas. Se sugiere la creación de un código que regule el uso de visualizaciones en el campo de la gestión y planificación del arbolado urbano. ABSTRACT This thesis examined the use of computer visualizations in urban forestry management and planning. Potential roles of visualizations were determined the benefits that its use would provide. Additionally, the possible barriers in the implementation of visualizations in urban forestry management and planning were also studied and recommendations on how to overcome them were provided The research conducted was an exploratory study using survey research methods and personal semi-structured interviews. The perspectives and reactions of London (UK) boroughs’ tree officers (LTOs) were analysed combining quantitative and qualitative research methods. The study surveyed 41 percent of all Tree Officers in London, obtaining responses from 88 percent of the boroughs and performed 17 personal interviews. Statistical analysis of the data and cross-variables analysis provided rich information that was then complemented with the conclusions from thematic analysis of the qualitative data from the interviews. Potential roles of visualizations were determined first by understanding the challenges that LTOs are facing today and comparing them with how visualizations have helped in similar situations in urban forestry and other related fields like landscape architecture, urban planning and forestry; second, the reactions of LTOs to a set of examples of proposed uses of visualizations were also complemented with the additional uses proposed by LTOs after seeing the visualizations. The visualizations were created ad hoc to show a variety of representative examples of the sue of visualization in urban forestry management and planning and were presented during the interviews to LTOS. Results show that the current production of visualizations is very reduced among tree officers but that they are frequent receptors of visualizations coming from other departments and as part of the documentation of planning applications. Findings show that the current visualizations that get to Tree Officers are biased and inaccurate and therefore it is argued the the current use of visualizations is a threat to legitimate informed decision making and public information. The development of a code for the use of visualizations in urban forestry management and planning is suggested.

Improving flexible databases searches using machine learning

El objetivo principal de este proyecto ha sido introducir aprendizaje automático en la aplicación FleSe. FleSe es una aplicación web que permite realizar consultas borrosas sobre bases de datos nítidos. Para llevar a cabo esta función la aplicación utiliza unos criterios para definir los conceptos borrosos usados para llevar a cabo las consultas. FleSe además permite que el usuario cambie estas personalizaciones. Es aquí donde introduciremos el aprendizaje automático, de tal manera que los criterios por defecto cambien y aprendan en función de las personalizaciones que van realizando los usuarios. Los objetivos secundarios han sido familiarizarse con el desarrollo y diseño web, al igual que recordar y ampliar el conocimiento sobre lógica borrosa y el lenguaje de programación lógica Ciao-Prolog. A lo largo de la realización del proyecto y sobre todo después del estudio de los resultados se demuestra que la agrupación de los usuarios marca la diferencia con la última versión de la aplicación. Esto se basa en la siguiente idea, podemos usar un algoritmo de aprendizaje automático sobre las personalizaciones de los criterios de todos los usuarios, pero la gran diversidad de opiniones de los usuarios puede llevar al algoritmo a concluir criterios erróneos o no representativos. Para solucionar este problema agrupamos a los usuarios intentando que cada grupo tengan la misma opinión o mismo criterio sobre el concepto. Y después de haber realizado las agrupaciones usar el algoritmo de aprendizaje automático para precisar el criterio por defecto de cada grupo de usuarios. Como posibles mejoras para futuras versiones de la aplicación FleSe sería un mejor control y manejo del ejecutable plserver. Este archivo se encarga de permitir a la aplicación web usar el lenguaje de programación lógica Ciao-Prolog para llevar a cabo la lógica borrosa relacionada con las consultas. Uno de los problemas más importantes que ofrece plserver es que bloquea el hilo de ejecución al intentar cargar un archivo con errores y en caso de ocurrir repetidas veces bloquea todas las peticiones siguientes bloqueando la aplicación. Pensando en los usuarios y posibles clientes, sería también importante permitir que FleSe trabajase con bases de datos de SQL en vez de almacenar la base de datos en los archivos de Prolog. Otra posible mejora basarse en distintas características a la hora de agrupar los usuarios dependiendo de los conceptos borrosos que se van ha utilizar en las consultas. Con esto se conseguiría que para cada concepto borroso, se generasen distintos grupos de usuarios, los cuales tendrían opiniones distintas sobre el concepto en cuestión. Así se generarían criterios por defecto más precisos para cada usuario y cada concepto borroso.---ABSTRACT---The main objective of this project has been to introduce machine learning in the application FleSe. FleSe is a web application that makes fuzzy queries over databases with precise information, using defined criteria to define the fuzzy concepts used by the queries. The application allows the users to change and custom these criteria. On this point is where the machine learning would be introduced, so FleSe learn from every new user customization of the criteria in order to generate a new default value of it. The secondary objectives of this project were get familiar with web development and web design in order to understand the how the application works, as well as refresh and improve the knowledge about fuzzy logic and logic programing. During the realization of the project and after the study of the results, I realized that clustering the users in different groups makes the difference between this new version of the application and the previous. This conclusion follows the next idea, we can use an algorithm to introduce machine learning over the criteria that people have, but the problem is the diversity of opinions and judgements that exists, making impossible to generate a unique correct criteria for all the users. In order to solve this problem, before using the machine learning methods, we cluster the users in order to make groups that have the same opinion, and afterwards, use the machine learning methods to precise the default criteria of each users group. The future improvements that could be important for the next versions of FleSe will be to control better the behaviour of the plserver file, that cost many troubles at the beginning of this project and it also generate important errors in the previous version. The file plserver allows the web application to use Ciao-Prolog, a logic programming language that control and manage all the fuzzy logic. One of the main problems with plserver is that when the user uploads a file with errors, it will block the thread and when this happens multiple times it will start blocking all the requests. Oriented to the customer, would be important as well to allow FleSe to manage and work with SQL databases instead of store the data in the Prolog files. Another possible improvement would that the cluster algorithm would be based on different criteria depending on the fuzzy concepts that the selected Prolog file have. This will generate more meaningful clusters, and therefore, the default criteria offered to the users will be more precise.