Sentiment-Topic Modelling in Text Mining

Peer reviewed

Sentiment-Topic Modelling in Text Mining

Peer reviewed

Probing Tissue Microstructure Using Susceptibility Contrast Magnetic Resonance Imaging

Magnetic resonance imaging is a research and clinical tool that has been applied in a wide variety of sciences. One area of magnetic resonance imaging that has exhibited terrific promise and growth in the past decade is magnetic susceptibility imaging. Imaging tissue susceptibility provides insight into the microstructural organization and chemical properties of biological tissues, but this image contrast is not well understood. The purpose of this work is to develop effective approaches to image, assess, and model the mechanisms that generate both isotropic and anisotropic magnetic susceptibility contrast in biological tissues, including myocardium and central nervous system white matter.

This document contains the first report of MRI-measured susceptibility anisotropy in myocardium. Intact mouse heart specimens were scanned using MRI at 9.4 T to ascertain both the magnetic susceptibility and myofiber orientation of the tissue. The susceptibility anisotropy of myocardium was observed and measured by relating the apparent tissue susceptibility as a function of the myofiber angle with respect to the applied magnetic field. A multi-filament model of myocardial tissue revealed that the diamagnetically anisotropy α-helix peptide bonds in myofilament proteins are capable of producing bulk susceptibility anisotropy on a scale measurable by MRI, and are potentially the chief sources of the experimentally observed anisotropy.

The growing use of paramagnetic contrast agents in magnetic susceptibility imaging motivated a series of investigations regarding the effect of these exogenous agents on susceptibility imaging in the brain, heart, and kidney. In each of these organs, gadolinium increases susceptibility contrast and anisotropy, though the enhancements depend on the tissue type, compartmentalization of contrast agent, and complex multi-pool relaxation. In the brain, the introduction of paramagnetic contrast agents actually makes white matter tissue regions appear more diamagnetic relative to the reference susceptibility. Gadolinium-enhanced MRI yields tensor-valued susceptibility images with eigenvectors that more accurately reflect the underlying tissue orientation.

Despite the boost gadolinium provides, tensor-valued susceptibility image reconstruction is prone to image artifacts. A novel algorithm was developed to mitigate these artifacts by incorporating orientation-dependent tissue relaxation information into susceptibility tensor estimation. The technique was verified using a numerical phantom simulation, and improves susceptibility-based tractography in the brain, kidney, and heart. This work represents the first successful application of susceptibility-based tractography to a whole, intact heart.

The knowledge and tools developed throughout the course of this research were then applied to studying mouse models of Alzheimer’s disease in vivo, and studying hypertrophic human myocardium specimens ex vivo. Though a preliminary study using contrast-enhanced quantitative susceptibility mapping has revealed diamagnetic amyloid plaques associated with Alzheimer’s disease in the mouse brain ex vivo, non-contrast susceptibility imaging was unable to precisely identify these plaques in vivo. Susceptibility tensor imaging of human myocardium specimens at 9.4 T shows that susceptibility anisotropy is larger and mean susceptibility is more diamagnetic in hypertrophic tissue than in normal tissue. These findings support the hypothesis that myofilament proteins are a source of susceptibility contrast and anisotropy in myocardium. This collection of preclinical studies provides new tools and context for analyzing tissue structure, chemistry, and health in a variety of organs throughout the body.

The effects of centrally acting ACE inhibitors on the rate of cognitive and functional decline in dementia: a KDD approach

Alzheimer’s Disease and other dementias are one of the most challenging illnesses confronting countries with ageing populations. Treatment options for dementia are limited, and the costs are significant. There is a growing need to develop new treatments for dementia, especially for the elderly. There is also growing evidence that centrally acting angiotensin converting enzyme (ACE) inhibitors, which cross the blood-brain barrier, are associated with a reduced rate of cognitive and functional decline in dementia, especially in Alzheimer’s disease (AD). The aim of this research is to investigate the effects of centrally acting ACE inhibitors (CACE-Is) on the rate of cognitive and functional decline in dementia, using a three phased KDD process. KDD, as a scientific way to process and analysis clinical data, is used to find useful insights from a variety of clinical databases. The data used are from three clinic databases: Geriatric Assessment Tool (GAT), the Doxycycline and Rifampin for Alzheimer’s Disease (DARAD), and the Qmci validation databases, which were derived from several different geriatric clinics in Canada. This research involves patients diagnosed with AD, vascular or mixed dementia only. Patients were included if baseline and end-point (at least six months apart) Standardised Mini-Mental State Examination (SMMSE), Quick Mild Cognitive Impairment (Qmci) or Activities Daily Living (ADL) scores were available. Basically, the rates of change are compared between patients taking CACE-Is, and those not currently treated with CACE-Is. The results suggest that there is a statistically significant difference in the rate of decline in cognitive and functional scores between CACE-I and NoCACE-I patients. This research also validates that the Qmci, a new short assessment test, has potential to replace the current popular screening tests for cognition in the clinic and clinical trials.

Transformer les pratiques professionnelles vis-à-vis des personnes prestataires de l’aide sociale : développement participatif et évaluation d’une formation continue en cabinet dentaire

L’objectif de la présente thèse est de générer des connaissances sur les contributions possibles d’une formation continue à l’évolution des perspectives et pratiques des professionnels de la santé buccodentaire. Prônant une approche centrée sur le patient, la formation vise à sensibiliser les professionnels à la pauvreté et à encourager des pratiques qui se veulent inclusives et qui tiennent compte du contexte social des patients. L’évaluation de la formation s’inscrit dans le contexte d’une recherche-action participative de développement d’outils éducatifs et de transfert des connaissances sur la pauvreté. Cette recherche-action aspire à contribuer à la lutte contre les iniquités sociales de santé et d’accès aux soins au Québec; elle reflète une préoccupation pour une plus grande justice sociale ainsi qu’une prise de position pour une santé publique critique fondée sur une « science des solutions » (Potvin, 2013). Quatre articles scientifiques, ancrés dans une philosophie constructiviste et dans les concepts et principes de l’apprentissage transformationnel (Mezirow, 1991), constituent le cœur de cette thèse. Le premier article présente une revue critique de la littérature portant sur l’enseignement de l’approche de soins centrés sur le patient. Prenant appui sur le concept d’une « épistémologie partagée », des principes éducatifs porteurs d’une transformation de perspective à l’égard de la relation professionnel-patient ont été identifiés et analysés. Le deuxième article de thèse s’inscrit dans le cadre du développement participatif d’outils de formation sur la pauvreté et illustre le processus de co-construction d’un scénario de court-métrage social réaliste portant sur la pauvreté et l’accès aux soins. L’article décrit et apporte une réflexion, notamment sur la dimension de co-formation entre les différents acteurs des milieux académique, professionnel et citoyen qui ont constitué le collectif À l’écoute les uns des autres. Nous y découvrons la force du croisement des savoirs pour générer des prises de conscience sur soi et sur ses préjugés. Les outils développés par le collectif ont été intégrés à une formation continue axée sur la réflexion critique et l’apprentissage transformationnel, et conçue pour être livrée en cabinet dentaire privé. Les deux derniers articles de thèse présentent les résultats d’une étude de cas instrumentale évaluative centrée sur cette formation continue et visant donc à répondre à l’objectif premier de cette thèse. Le premier consiste en une analyse des transformations de perspectives et d’action au sein d’une équipe de 15 professionnels dentaires ayant participé à la formation continue sur une période de trois mois. L’article décrit, entre autres, une plus grande ouverture, chez certains participants, sur les causes structurelles de la pauvreté et une plus grande sensibilité au vécu au quotidien des personnes prestataires de l’aide sociale. L’article comprend également une exploration des effets paradoxaux dans l’apprentissage, notamment le renforcement, chez certains, de perceptions négatives à l’égard des personnes prestataires de l’aide sociale. Le quatrième article fait état de barrières idéologiques contraignant la transformation des pratiques professionnelles : 1) l’identification à l’idéologie du marché privé comme véhicule d’organisation des soins; 2) l’attachement au concept d’égalité dans les pratiques, au détriment de l’équité; 3) la prédominance du modèle biomédical, contraignant l’adoption de pratiques centrées sur la personne et 4) la catégorisation sociale des personnes prestataires de l’aide sociale. L’analyse des perceptions, mais aussi de l’expérience vécue de ces barrières démontre comment des facteurs systémiques et sociaux influent sur le rapport entre professionnel dentaire et personne prestataire de l’aide sociale. Les conséquences pour la recherche, l’éducation dentaire, le transfert des connaissances, ainsi que pour la régulation professionnelle et les politiques de santé buccodentaire, sont examinées à partir de cette perspective.

Hybrid Graph Heuristics within a Hyper-heuristic Approach to Exam Timetabling Problems

This paper is concerned with the hybridization of two graph coloring heuristics (Saturation Degree and Largest Degree), and their application within a hyperheuristic for exam timetabling problems. Hyper-heuristics can be seen as algorithms which intelligently select appropriate algorithms/heuristics for solving a problem. We developed a Tabu Search based hyper-heuristic to search for heuristic lists (of graph heuristics) for solving problems and investigated the heuristic lists found by employing knowledge discovery techniques. Two hybrid approaches (involving Saturation Degree and Largest Degree) including one which employs Case Based Reasoning are presented and discussed. Both the Tabu Search based hyper-heuristic and the hybrid approaches are tested on random and real-world exam timetabling problems. Experimental results are comparable with the best state-of-the-art approaches (as measured against established benchmark problems). The results also demonstrate an increased level of generality in our approach.

Case-Based Reasoning as a Heuristic Selector in a Hyper-Heuristic for Course Timetabling Problems

This paper studies Knowledge Discovery (KD) using Tabu Search and Hill Climbing within Case-Based Reasoning (CBR) as a hyper-heuristic method for course timetabling problems. The aim of the hyper-heuristic is to choose the best heuristic(s) for given timetabling problems according to the knowledge stored in the case base. KD in CBR is a 2-stage iterative process on both case representation and the case base. Experimental results are analysed and related research issues for future work are discussed.

Case Based Heuristic Selection for Timetabling Problems

This paper presents a case-based heuristic selection approach for automated university course and exam timetabling. The method described in this paper is motivated by the goal of developing timetabling systems that are fundamentally more general than the current state of the art. Heuristics that worked well in previous similar situations are memorized in a case base and are retrieved for solving the problem in hand. Knowledge discovery techniques are employed in two distinct scenarios. Firstly, we model the problem and the problem solving situations along with specific heuristics for those problems. Secondly, we refine the case base and discard cases which prove to be non-useful in solving new problems. Experimental results are presented and analyzed. It is shown that case based reasoning can act effectively as an intelligent approach to learn which heuristics work well for particular timetabling situations. We conclude by outlining and discussing potential research issues in this critical area of knowledge discovery for different difficult timetabling problems.

Case Based Heuristic Selection for Timetabling Problems

This paper presents a case-based heuristic selection approach for automated university course and exam timetabling. The method described in this paper is motivated by the goal of developing timetabling systems that are fundamentally more general than the current state of the art. Heuristics that worked well in previous similar situations are memorized in a case base and are retrieved for solving the problem in hand. Knowledge discovery techniques are employed in two distinct scenarios. Firstly, we model the problem and the problem solving situations along with specific heuristics for those problems. Secondly, we refine the case base and discard cases which prove to be non-useful in solving new problems. Experimental results are presented and analyzed. It is shown that case based reasoning can act effectively as an intelligent approach to learn which heuristics work well for particular timetabling situations. We conclude by outlining and discussing potential research issues in this critical area of knowledge discovery for different difficult timetabling problems.

Aplicação de sistemas inteligentes à optimização de um sistema de tratamento de água

Um dos principais problemas que estação de Tratamento de Água do Monte Novo tem vindo a apresentar é o aparecimento de teores em manganês na água tratada, que por vezes ultrapassam o valor paramétrico estabelecido no Decreto-Lei 306/07, 27 de Agosto (50 g dm-3). Este trabalho permitiu relacionar resultados de várias determinações analíticas efectuadas no laboratório da empresa Águas do Centro Alentejo e, através deles construir modelos fundamentados em técnicas e Descoberta de Conhecimento em Base de Dados que permitiram responder ao problema identificado. Foi ainda possível estabelecer a época do ano em que é mais provável o aparecimento de teores elevados manganês na água tratada. Além disso, mostrou-se que a tomada de água desempenha um papel relevante no aparecimento deste metal na água tratada. Os modelos desenvolvidos permitiram também estabelecer as condições em que é provável o aparecimento de turvação na cisterna de água tratada. Estas estão relacionadas com o pH, o teor em manganês e o teor em ferro. Foi ainda realçada a importância da correcção do pH na fase final do processo de tratamento. Por um lado, o pH deve ser suficientemente elevado para garantir uma água incrustante e, por outro, deve ser baixo para evitar problemas de turvação na cisterna da água tratada. ABSTRACT; The present study took place in the water treatment plant of Monte Novo. This study aimed for solutions to the problem of high values of manganese concentration in the treated water, in some periods of the year. The present work reports models for manganese concentration and for turbidity using Knowledge Discovery Techniques in Data Bases.

Transformer les pratiques professionnelles vis-à-vis des personnes prestataires de l’aide sociale : développement participatif et évaluation d’une formation continue en cabinet dentaire

L’objectif de la présente thèse est de générer des connaissances sur les contributions possibles d’une formation continue à l’évolution des perspectives et pratiques des professionnels de la santé buccodentaire. Prônant une approche centrée sur le patient, la formation vise à sensibiliser les professionnels à la pauvreté et à encourager des pratiques qui se veulent inclusives et qui tiennent compte du contexte social des patients. L’évaluation de la formation s’inscrit dans le contexte d’une recherche-action participative de développement d’outils éducatifs et de transfert des connaissances sur la pauvreté. Cette recherche-action aspire à contribuer à la lutte contre les iniquités sociales de santé et d’accès aux soins au Québec; elle reflète une préoccupation pour une plus grande justice sociale ainsi qu’une prise de position pour une santé publique critique fondée sur une « science des solutions » (Potvin, 2013). Quatre articles scientifiques, ancrés dans une philosophie constructiviste et dans les concepts et principes de l’apprentissage transformationnel (Mezirow, 1991), constituent le cœur de cette thèse. Le premier article présente une revue critique de la littérature portant sur l’enseignement de l’approche de soins centrés sur le patient. Prenant appui sur le concept d’une « épistémologie partagée », des principes éducatifs porteurs d’une transformation de perspective à l’égard de la relation professionnel-patient ont été identifiés et analysés. Le deuxième article de thèse s’inscrit dans le cadre du développement participatif d’outils de formation sur la pauvreté et illustre le processus de co-construction d’un scénario de court-métrage social réaliste portant sur la pauvreté et l’accès aux soins. L’article décrit et apporte une réflexion, notamment sur la dimension de co-formation entre les différents acteurs des milieux académique, professionnel et citoyen qui ont constitué le collectif À l’écoute les uns des autres. Nous y découvrons la force du croisement des savoirs pour générer des prises de conscience sur soi et sur ses préjugés. Les outils développés par le collectif ont été intégrés à une formation continue axée sur la réflexion critique et l’apprentissage transformationnel, et conçue pour être livrée en cabinet dentaire privé. Les deux derniers articles de thèse présentent les résultats d’une étude de cas instrumentale évaluative centrée sur cette formation continue et visant donc à répondre à l’objectif premier de cette thèse. Le premier consiste en une analyse des transformations de perspectives et d’action au sein d’une équipe de 15 professionnels dentaires ayant participé à la formation continue sur une période de trois mois. L’article décrit, entre autres, une plus grande ouverture, chez certains participants, sur les causes structurelles de la pauvreté et une plus grande sensibilité au vécu au quotidien des personnes prestataires de l’aide sociale. L’article comprend également une exploration des effets paradoxaux dans l’apprentissage, notamment le renforcement, chez certains, de perceptions négatives à l’égard des personnes prestataires de l’aide sociale. Le quatrième article fait état de barrières idéologiques contraignant la transformation des pratiques professionnelles : 1) l’identification à l’idéologie du marché privé comme véhicule d’organisation des soins; 2) l’attachement au concept d’égalité dans les pratiques, au détriment de l’équité; 3) la prédominance du modèle biomédical, contraignant l’adoption de pratiques centrées sur la personne et 4) la catégorisation sociale des personnes prestataires de l’aide sociale. L’analyse des perceptions, mais aussi de l’expérience vécue de ces barrières démontre comment des facteurs systémiques et sociaux influent sur le rapport entre professionnel dentaire et personne prestataire de l’aide sociale. Les conséquences pour la recherche, l’éducation dentaire, le transfert des connaissances, ainsi que pour la régulation professionnelle et les politiques de santé buccodentaire, sont examinées à partir de cette perspective.

Redes de influencias y líderes de opinión en las redes sociales

Este Trabajo de Fin de Grado (TFG) se engloba en la línea general Social CRM. Concretamente, está vinculado a un trabajo de investigación llamado “Knowledge discovery in social networks by using a logic-based treatment of implications” desarrollado por P. Cordero, M. Enciso, A. Mora, M. Ojeda-Aciego y C. Rossi en la Universidad de Málaga, en el cual se ofrecen nuevas soluciones para la identificación de influencias de los usuarios en las redes sociales mediante herramientas como el Analisis de Conceptos Formales (FCA). El TFG tiene como objetivo el desarrollo de una aplicación que permita al usuario crear una configuración minimal de usuarios en Twitter a los que seguir para conocer información sobre un número determinado de temas. Para ello, obtendremos información sobre dichos temas mediante la API REST pública que proporciona Twitter y procesaremos los datos mediante algoritmos basados en el Análisis de Conceptos Formales (FCA). Posteriormente, la interpretación de los resultados de dicho análisis nos proporcionará información útil sobre lo expuesto al principio. Así, el trabajo se ha dividido en tres partes fundamentales: 1. Obtención de información (fuentes) 2. Procesamiento de los datos 3. Análisis de resultados El sistema se ha implementado como una aplicación web Java EE 7, utilizando JSF para las interfaces. Para el desarrollo web se han utilizado tecnologías y frameworks como Javascript, JQuery, CSS3, Bootstrap, Twitter4J, etc. Además, se ha seguido una metodología incremental para el desarrollo del proyecto y se ha usado UML como herramienta de modelado. Este proyecto se presenta como un trabajo inicial en el que se expondrán, además del sistema implementado, diversos problemas reales y ejemplos que prueben su funcionamiento y muestren la utilidad práctica del mismo

STORM - a novel information fusion and cluster interpretation technique

Analysis of data without labels is commonly subject to scrutiny by unsupervised machine learning techniques. Such techniques provide more meaningful representations, useful for better understanding of a problem at hand, than by looking only at the data itself. Although abundant expert knowledge exists in many areas where unlabelled data is examined, such knowledge is rarely incorporated into automatic analysis. Incorporation of expert knowledge is frequently a matter of combining multiple data sources from disparate hypothetical spaces. In cases where such spaces belong to different data types, this task becomes even more challenging. In this paper we present a novel immune-inspired method that enables the fusion of such disparate types of data for a specific set of problems. We show that our method provides a better visual understanding of one hypothetical space with the help of data from another hypothetical space. We believe that our model has implications for the field of exploratory data analysis and knowledge discovery.

Automatic learning of pre-miRNAs from different species.

Discovery of microRNAs (miRNAs) relies on predictive models for characteristic features from miRNA precursors (pre-miRNAs). The short length of miRNA genes and the lack of pronounced sequence features complicate this task. To accommodate the peculiarities of plant and animal miRNAs systems, tools for both systems have evolved differently. However, these tools are biased towards the species for which they were primarily developed and, consequently, their predictive performance on data sets from other species of the same kingdom might be lower. While these biases are intrinsic to the species, their characterization can lead to computational approaches capable of diminishing their negative effect on the accuracy of pre-miRNAs predictive models. We investigate in this study how 45 predictive models induced for data sets from 45 species, distributed in eight subphyla/classes, perform when applied to a species different from the species used in its induction. Results: Our computational experiments show that the separability of pre-miRNAs and pseudo pre-miRNAs instances is species-dependent and no feature set performs well for all species, even within the same subphylum/class. Mitigating this species dependency, we show that an ensemble of classifiers reduced the classification errors for all 45 species. As the ensemble members were obtained using meaningful, and yet computationally viable feature sets, the ensembles also have a lower computational cost than individual classifiers that rely on energy stability parameters, which are of prohibitive computational cost in large scale applications. Conclusion: In this study, the combination of multiple pre-miRNAs feature sets and multiple learning biases enhanced the predictive accuracy of pre-miRNAs classifiers of 45 species. This is certainly a promising approach to be incorporated in miRNA discovery tools towards more accurate and less species-dependent tools.

A survey on multi-output regression

In recent years, a plethora of approaches have been proposed to deal with the increasingly challenging task of multi-output regression. This paper provides a survey on state-of-the-art multi-output regression methods, that are categorized as problem transformation and algorithm adaptation methods. In addition, we present the mostly used performance evaluation measures, publicly available data sets for multi-output regression real-world problems, as well as open-source software frameworks.