Scielo RSS <![CDATA[Polibits]]> vol. num. 44 lang. pt <![CDATA[SciELO Logo]]> <![CDATA[<b>Editorial</b>]]> <![CDATA[<b>Automatic Bubble Detection in Cardiac Video Imaging</b>]]> Bubble recognition is a challenging problem in a broad range from mechanics to medicine. These gas-filled structures whose pattern and morphology alter in their surrounding environment would be counted either manually or with computational recognition procedures. In cardiology, user dependent bubble detection and temporal counting in videos require special trainings and experience due to ultra fast movement, inherent noise and video quality. In this study, we propose an efficient recognition routine to increase the objectivity of emboli detection. Firstly, we started to compare five different methods on two synthetic data sets emulating cardiac chamber environment with increasing speckle noise levels. Secondly, real echocardiographic video records were segmented by variational active contours and Left Atria (LA) were extracted. Finally, three successful methods in simulation were applied to LAs in order to reveal candidate bubbles on video frames. Our detection rate of proposed method was 95.7% and the others were 86.2% and 88.3%. We conclude that our approach would be useful in long lasting video processing and would be applied in other disciplines. <![CDATA[<b>Automated Classification of Bitmap Images using Decision Trees</b>]]> The paper addresses the design of a method for automated classification of bitmap images into classes described by the user in natural language. Examples of such naturally defined classes are images depicting buildings, landscape, artistic images, etc. The proposed classification method is based on the extraction of suitable attributes from a bitmap image such as contrast, histogram, the occurrence of straight lines, etc. Extracted attributes are subsequently processed by a decision tree which has been trained in advance. A performed experimental evaluation with 5 classification classes showed that the proposed method has the accuracy of 75%-85%. The design of the method is general enough to allow the extension of the set of classification classes as well as the number of extracted attributes to increase the accuracy of classification. <![CDATA[<b>Automatic Emotional Speech Recognition with Alpha-Beta SVM Associative Memories</b>]]> Una de las de investigación de mayor interés y con más crecimiento en la actualidad, dentro del área de procesamiento de voz, es el reconocimiento automático de emociones, el cual consta de 2 etapas; la primera es la extracción de parámetros a partir de la señal de voz y la segunda es la elección del modelo para hacer la tarea de clasificación. La problemática que actualmente existe es que no se han identificado aún los parámetros más representativos del problema ni tampoco se ha encontrado al mejor clasificador para hacer la tarea. En este artículo se introduce un nuevo modelo asociativo de reconocimiento automático de voz emotiva basado en las máquinas asociativas Alfa-Beta SVM, cuyas entradas se han codificado como representaciones bidimensionales de la energía de las señales de voz. Los resultados experimentales muestran que este modelo es competitivo en la tarea de clasificación automática de emociones a partir de señales de voz [1].<hr/>One of the research lines of interest and more growth at present, within the area of voice processing is automatic emotion recognition. It is vitally important the study of speech signal not only to extract information about what is being said, but how is being said, this in order to be closer to the human-machine interaction. In literature the procedure of automatic emotion recognition consists of two stager, the first is the extraction of parameters from the voice signal and the second is the choice of model for the classification task, the problem that currently exists is not yet identified the most representative parameters of the problem nor has found the best classifier for the task, but have not yet been tested several models, this paper presents a two-dimensional representation of energy as data entry for Alpha-Beta associative machines SVM (Support Vector Machine) for the classification of emotions. <![CDATA[<b>A Dynamic Model for Identification of Emotional Expressions</b>]]> This paper discusses the dynamics of emotion recognition on faces, layering basic capabilities of an emotion sensor. It also introduces a model for the recognition of the overall conveyed emotion during a human-machine interaction, based on the emotional trajectory over an emotional surface. <![CDATA[<b>Optical Parameter Extraction using Differential Evolution Rendering in the Loop</b>]]> Image synthesis is highly dependent on rendering algorithm and optical properties of scenario objects. The goal of this work is to develop a methodology to obtain some illumination parameters of a real scenario represented by an acquired image, and use these parameters for a virtual scenario rendering with the same objects as the original. The proposed methodology consists, first, in acquiring an image of the working scenario, and by using a DE (Differential Evolution) algorithm to render images that gradually approximate to the real acquired image, by some virtual scenario parameter modification based on the DE optimization. We call it "ED Rendering in the loop". Finally we use the obtained parameters to render an image to compare it with similar methods. <![CDATA[<b>A Model of Decision-Making Based on the Theory of Persuasion used in MMORPGs</b>]]> From a videogame perspective, decision-making is a crucial activity that takes place at all times and at different leveis of perception. Moreover, this process influences the gamers' performances, which is an interesting feature for RPGs as they are games that are able to work as tools for increasing the improvement of the proximal development zones of players due to their inherent trait of cooperation, which alone, stimulates their skills of socialization, interaction and, consequently, communication. A feat that is achieved by involving players in a kind of plot that requires them to interact and take decisions, hence, favoring decision-making process. For these reasons, the RPG genre was considered as an appropriate test bed to apply the decision-making model proposed by this paper, which was built by using a Petri Net and that combines concepts taken from The Game Theory and from the reciprocity principle from the Theory of Persuasion. <![CDATA[<b>User Preference Model for Conscious Services in Smart Environments</b>]]> Awareness of user preferences and analysis of the current situation makes capable to provide user with invasive services in various applications of smart environments. In smart meeting rooms context-aware systems analyze user behavior based on multimodal sensor data and provide proactive services for meeting support, including active control PTZ (pan, tilt and zoom) cameras, microphone arrays, context dependent automatic archiving and web-transmission of meeting data at the interaction. History of interaction sessions between a user and a service is used for knowledge accumulation in order to forecast user behavior during the next visit. The user preference model based on audiovisual data recorded during interaction and statistics of his/her speech activity, requests, movement trajectories and other parameters was implemented for the developed mobile information robot and smart meeting room. <![CDATA[<b>FPGA Implementation of Fuzzy Mamdani System with Parametric Conjunctions Generated by Monotone Sum of Basic t-Norms</b>]]> The paper presents the results of FPGA implementation of fuzzy Mamdani system with parametric conjunctions generated by monotone sum of basic t-norms. The system is implemented on the DE2 Altera development board using VHDL language. The system contains reconfigurable fuzzy Mamdani model with parametric membership functions and parametric operations that gives possibility to adjust the system to specific application. <![CDATA[<b>Automatic Music Composition with Simple Probabilistic Generative Grammars</b>]]> We propose a model to generate music following a linguistic approach. Musical melodies form the training corpus where each of them is considered a phrase of a language. Implementing an unsupervised technique we infer a grammar of this language. We do not use predefined rules. Music generation is based on music knowledge represented by probabilistic matrices, which we call evolutionary matrices because they are changing constantly, even while they are generating new compositions. We show that the information coded by these matrices can be represented at any time by a probabilistic grammar; however we keep the representation of matrices because they are easier to update, while it is possible to keep separated matrices for generation of different elements of expressivity such as velocity, changes of rhythm, or timbre, adding several elements of expressiveness to the automatically generated compositions. We present the melodies generated by our model to a group of subjects and they ranked our compositions among and sometimes above human composed melodies. <![CDATA[<b>An Approach to Cross-Lingual Textual Entailment using Online Machine Translation Systems</b>]]> In this paper, we show an approach to cross-lingual textual entailment (CLTE) by using machine translation systems such as Bing Translator and Google Translate. We experiment with a wide variety of data sets to the task of textual Entailment (TE) and evaluate the contribution of an algorithm that expands a monolingual TE corpus that seems promising for the task of CLTE. We built a CLTE corpus and we report a procedure that can be used to create a CLTE corpus in any pair of languages. We also report the results obtained in our experiments with the three-way classification task for CLTE and we show that this result outperform the average score of RTE (Recognizing Textual Entailment) systems. Finally, we find that using WordNet as the only source of lexical-semantic knowledge it is possibly to build a system for CLTE, which achieves comparable results with the average score of RTE systems for both two-way and three-way tasks. <![CDATA[<b>Identifying the User's Intentions</b>: <b>Basic Illocutions in Modern Greek</b>]]> This paper presents a comprehensive classification of basic illocutions in Modern Greek, extracted following the linguistic choices speakers make when they formulate an utterance, provided such choices form part of a language's grammar. Our approach lies on the interface between Morphosyntax, Pragmatics and Phonology and allows for basic illocutions to be established depending on the particular verb mood, particle, number, person, aspect and segmental marker, as well as the prosodic contour used when an utterance is realized. Our results show that Indicative uses, for example, are mostly associated with propositional illocutions, consisting of declarative uses, including assertions, miratives, and assertions in disguise; interrogative uses, including polar and content interrogatives; and behavioral illocutions i.e. exhortations (expressed in first person plural only). Secondary sentence types, (involving additional segmental marking) include requests for confirmation, wondering, expression of uncertainty and proffer. In this paper we discuss propositional uses only. Such a theoretical approach can have a direct impact on applications involving Human-Computer Interaction, including intention-based dialogue systems' modeling, natural language interfaces to Data Bases and Intelligent Agents as well as Belief, Desire and Intention systems, which require the computer to be able to interpret what a user's objective (intention) is, so that the users' needs can be best served. <![CDATA[<b>Inference of Fine-grained Attributes of Bengali Corpus for Stylometry Detection</b>]]> Stylometry, the science of inferring characteristics of the author from the characteristics of documents written by that author, is a problem with a long history and belongs to the core task of Text categorization that involves authorship identification, plagiarism detection, forensic investigation, computer security, copyright and estáte disputes etc. In this work, we present a strategy for stylometry detection of documents written in Bengali. We adopt a set of fine-grained attribute features with a set of lexical markers for the analysis of the text and use three semi-supervised measures for making decisions. Finally, a majority voting approach has been taken for final classification. The system is fully automatic and language-independent. Evaluation results of our attempt for Bengali author' s stylometry detection show reasonably promising accuracy in comparison to the baseline model.