Adaptive modeling and high quality spectral estimation for speech enhancement

In this work an adaptive modeling and spectral estimation scheme based on a dual Discrete Kalman Filtering (DKF) is proposed for speech enhancement. Both speech and noise signals are modeled by an autoregressive structure which provides an underlying time frame dependency and improves time-frequency resolution. The model parameters are arranged to obtain a combined state-space model and are also used to calculate instantaneous power spectral density estimates. The speech enhancement is performed by a dual discrete Kalman filter that simultaneously gives estimates for the models and the signals. This approach is particularly useful as a pre-processing module for parametric based speech recognition systems that rely on spectral time dependent models. The system performance has been evaluated by a set of human listeners and by spectral distances. In both cases the use of this pre-processing module has led to improved results.

Interpretative research in information systems: two qualitative research design projects

In a scientific research project is important to define the underlying philosophical orientation of the project, because this will influence the choices made in respect of scientific methods used, as well as the way they will be applied. It is crucial, therefore, that the philosophy and research design strategy are consistent with each other. These questions become even more relevant in qualitative research. Historically, the interpretive research philosophy is more associated to the scientific areas of social sciences and humanities where the subjectivity inherent to human intervention is more explicitly defined. Information systems field are, primarily, trapped in computer science field, though it also integrates issues related with management and organizations field. This shift from a purely technological guidance for the consideration of the problems of management and organizations has fostered the rise of research projects according to the interpretive philosophy and using qualitative methods. This paper explores the importance of alignment between the epistemological orientation and research design strategy, in qualitative research projects. As a result, it is presented two PhD projects, with different research design strategies, that are being developed in the technology and information systems field, in the light of the interpretive paradigm.

Hand gesture recognition system based in computer vision and machine learning

"Lecture notes in computational vision and biomechanics series, ISSN 2212-9391, vol. 19"

Clustering barotrauma patients in ICU–A data mining based approach using ventilator variables

Lecture Notes in Computer Science, 9273

Artificial neural networks in diagnosis of liver diseases

Liver diseases have severe patients’ consequences, being one of the main causes of premature death. These facts reveal the centrality of one`s daily habits, and how important it is the early diagnosis of these kind of illnesses, not only to the patients themselves, but also to the society in general. Therefore, this work will focus on the development of a diagnosis support system to these kind of maladies, built under a formal framework based on Logic Programming, in terms of its knowledge representation and reasoning procedures, complemented with an approach to computing grounded on Artificial Neural Networks.

Logic programming and artificial neural networks in breast cancer detection

About 90% of breast cancers do not cause or are capable of producing death if detected at an early stage and treated properly. Indeed, it is still not known a specific cause for the illness. It may be not only a beginning, but also a set of associations that will determine the onset of the disease. Undeniably, there are some factors that seem to be associated with the boosted risk of the malady. Pondering the present study, different breast cancer risk assessment models where considered. It is our intention to develop a hybrid decision support system under a formal framework based on Logic Programming for knowledge representation and reasoning, complemented with an approach to computing centered on Artificial Neural Networks, to evaluate the risk of developing breast cancer and the respective Degree-of-Confidence that one has on such a happening.

Hand gesture recognition system based in computer vision and machine learning: Applications on human-machine interaction

Tese de Doutoramento em Engenharia de Eletrónica e de Computadores

Metaphorisms in programming

This paper introduces the metaphorism pattern of relational specification and addresses how specification following this pattern can be refined into recursive programs. Metaphorisms express input-output relationships which preserve relevant information while at the same time some intended optimization takes place. Text processing, sorting, representation changers, etc., are examples of metaphorisms. The kind of metaphorism refinement proposed in this paper is a strategy known as change of virtual data structure. It gives sufficient conditions for such implementations to be calculated using relation algebra and illustrates the strategy with the derivation of quicksort as example.

Desarrollos innovadores, estrategias de aprendizaje e interacciones de comunicación llevadas a cabo con Tecnologías de la Información y la Comunicación en el área de Ciencias Experimentales. Innovative developments, learning strategies and communication interactions carried out with CIT in experimental science.

Las Tecnologías de la Información y la Comunicación (TIC) han alcanzando una fuerte expansión en la última década y se convierten en una estrategia clave para la educación científica y tecnológica. Actualmente se realizan significativas inversiones en computadoras e insumos acordes a esta tecnología lo que no garantiza que éstas mejores disponibilidades sean necesariamente conducentes a propuestas educativas aceptables, ya que la incorporación de las TIC en la educación científica no puede consistir en un mero cambio de soporte sin que esto se acompañe de una renovación constructivista del aprendizaje. También se observa un escaso desarrollo y aplicación de las TIC tanto en la formación de grado de las carreras científicas, como en la formación permanente de los docentes. A partir de lo expuesto, nos planteamos los siguientes problemas: ¿cómo generar cursos de formación docente con alternativas virtuales que garanticen la construcción, actualización y transferencia de conocimientos en las disciplinas científicas? ¿qué diseño de materiales se requiere para potenciar aprendizajes flexibles de calidad?, ¿qué dimensiones, variables e indicadores dan cuenta de procesos de comunicación en estos entornos?, ¿Cuáles son las principales estrategias que promueven los desarrollos tecnológicos? ¿De qué manera se lleva a cabo el seguimiento y evaluación de los desarrollos tecnológicos? Para dar respuesta a estos interrogantes nos planteamos este proyecto que tiene por objetivos: diseñar, desarrollar, implementar y evaluar materiales basados en un modelo constructivista que utiliza como soporte las TIC el marco de la "Enseñanza para la Comprensión". Analizar las relaciones que se establecen en el intercambio comunicativo a través de las TIC, ya sea de manera síncrona o asíncrona e identificar las estrategias de aprendizaje utilizadas por los estudiantes cuando trabajan con entornos virtuales. Se profundizará en los siguientes temas: "La materia y sus cambios", "Biotecnología" y "Dilemas investigativos a los que se enfrentan los científicos". Los dos primeros módulos estarán destinados a la formación de futuros docentes en Ciencias y a la formación permanente de docentes en ejercicio. Los usuarios del tercer módulo serán los estudiantes del ciclo de nivelacion. Se propone desarrollar instrumentos de evaluación, adaptando indicadores que sirvan para evaluar el modelo, el diseño de los materiales, el medio tecnológico, la eficiencia de estos programas con TIC. Se van a definir variables que permitan identificar las estrategias de aprendizaje utilizadas por los usuarios de estos desarrollos tecnológicos y las relaciones que se establecen en el intercambio comunicativo de los entornos virtuales, haciendo hincapié en la lecto-escritura científica. Se utilizará la plataforma Moodle que permite la administración de los estudiantes, las interacciones sociales necesarias para integrar una comunidad de aprendizaje a través de los foros y correo electrónico y la evaluación continua de los aprendizajes. El desarrollo de los contenidos específicos y las actividades de aprendizaje se hará en CD interactivos elaborados con diferentes programas de computación. En el desarrollo de los materiales se incluyen algunas simulaciones interactivas que permiten comprender conceptos que habitualmente requerían experimentación fáctica. El estudio se enmarca en la combinación de dos enfoques metodológicos que integran técnicas y procedimientos de análisis tanto cuantitativos como cualitativos. Consideramos que esta investigación es una contribución teórica importante ya que propone mejorar un modelo para la enseñanza de las Ciencias Naturales introduciendo las TIC. Se espera realizar un aporte novedoso al campo de la Didáctica de las Ciencias con la obtención de los resultados y acciones tendientes a establecer una red de comunicaciones entre los docentes participantes y los investigadores involucrados en el programa, instalada en forma progresiva.

Embedding metadata in computer graphics for interaction

Illustration Watermarks, Image annotation, Virtual data exploration, Interaction techniques

New perspectives in the use of ink evidence in forensic science: Part I. Development of a quality assurance process for forensic ink analysis by HPTLC

The level of information provided by ink evidence to the criminal and civil justice system is limited. The limitations arise from the weakness of the interpretative framework currently used, as proposed in the ASTM 1422-05 and 1789-04 on ink analysis. It is proposed to use the likelihood ratio from the Bayes theorem to interpret ink evidence. Unfortunately, when considering the analytical practices, as defined in the ASTM standards on ink analysis, it appears that current ink analytical practices do not allow for the level of reproducibility and accuracy required by a probabilistic framework. Such framework relies on the evaluation of the statistics of the ink characteristics using an ink reference database and the objective measurement of similarities between ink samples. A complete research programme was designed to (a) develop a standard methodology for analysing ink samples in a more reproducible way, (b) comparing automatically and objectively ink samples and (c) evaluate the proposed methodology in a forensic context. This report focuses on the first of the three stages. A calibration process, based on a standard dye ladder, is proposed to improve the reproducibility of ink analysis by HPTLC, when these inks are analysed at different times and/or by different examiners. The impact of this process on the variability between the repetitive analyses of ink samples in various conditions is studied. The results show significant improvements in the reproducibility of ink analysis compared to traditional calibration methods.

Bayesian Networks for Probabilistic Inference and Decision Analysis in Forensic Science

Continuing developments in science and technology mean that the amounts of information forensic scientists are able to provide for criminal investigations is ever increasing. The commensurate increase in complexity creates difficulties for scientists and lawyers with regard to evaluation and interpretation, notably with respect to issues of inference and decision. Probability theory, implemented through graphical methods, and specifically Bayesian networks, provides powerful methods to deal with this complexity. Extensions of these methods to elements of decision theory provide further support and assistance to the judicial system. Bayesian Networks for Probabilistic Inference and Decision Analysis in Forensic Science provides a unique and comprehensive introduction to the use of Bayesian decision networks for the evaluation and interpretation of scientific findings in forensic science, and for the support of decision-makers in their scientific and legal tasks. Includes self-contained introductions to probability and decision theory. Develops the characteristics of Bayesian networks, object-oriented Bayesian networks and their extension to decision models. Features implementation of the methodology with reference to commercial and academically available software. Presents standard networks and their extensions that can be easily implemented and that can assist in the reader's own analysis of real cases. Provides a technique for structuring problems and organizing data based on methods and principles of scientific reasoning. Contains a method for the construction of coherent and defensible arguments for the analysis and evaluation of scientific findings and for decisions based on them. Is written in a lucid style, suitable for forensic scientists and lawyers with minimal mathematical background. Includes a foreword by Ian Evett. The clear and accessible style of this second edition makes this book ideal for all forensic scientists, applied statisticians and graduate students wishing to evaluate forensic findings from the perspective of probability and decision analysis. It will also appeal to lawyers and other scientists and professionals interested in the evaluation and interpretation of forensic findings, including decision making based on scientific information.

On the use of IRMS in forensic science: proposals for a methodological approach.

The flourishing number of publications on the use of isotope ratio mass spectrometry (IRMS) in forensicscience denotes the enthusiasm and the attraction generated by this technology. IRMS has demonstratedits potential to distinguish chemically identical compounds coming from different sources. Despite thenumerous applications of IRMS to a wide range of forensic materials, its implementation in a forensicframework is less straightforward than it appears. In addition, each laboratory has developed its ownstrategy of analysis on calibration, sequence design, standards utilisation and data treatment without aclear consensus.Through the experience acquired from research undertaken in different forensic fields, we propose amethodological framework of the whole process using IRMS methods. We emphasize the importance ofconsidering isotopic results as part of a whole approach, when applying this technology to a particularforensic issue. The process is divided into six different steps, which should be considered for a thoughtfuland relevant application. The dissection of this process into fundamental steps, further detailed, enablesa better understanding of the essential, though not exhaustive, factors that have to be considered in orderto obtain results of quality and sufficiently robust to proceed to retrospective analyses or interlaboratorycomparisons.