Learning techniques for automatic email message tagging

A organização automática de mensagens de correio electrónico é um desafio actual na área da aprendizagem automática. O número excessivo de mensagens afecta cada vez mais utilizadores, especialmente os que usam o correio electrónico como ferramenta de comunicação e trabalho. Esta tese aborda o problema da organização automática de mensagens de correio electrónico propondo uma solução que tem como objectivo a etiquetagem automática de mensagens. A etiquetagem automática é feita com recurso às pastas de correio electrónico anteriormente criadas pelos utilizadores, tratando-as como etiquetas, e à sugestão de múltiplas etiquetas para cada mensagem (top-N). São estudadas várias técnicas de aprendizagem e os vários campos que compõe uma mensagem de correio electrónico são analisados de forma a determinar a sua adequação como elementos de classificação. O foco deste trabalho recai sobre os campos textuais (o assunto e o corpo das mensagens), estudando-se diferentes formas de representação, selecção de características e algoritmos de classificação. É ainda efectuada a avaliação dos campos de participantes através de algoritmos de classificação que os representam usando o modelo vectorial ou como um grafo. Os vários campos são combinados para classificação utilizando a técnica de combinação de classificadores Votação por Maioria. Os testes são efectuados com um subconjunto de mensagens de correio electrónico da Enron e um conjunto de dados privados disponibilizados pelo Institute for Systems and Technologies of Information, Control and Communication (INSTICC). Estes conjuntos são analisados de forma a perceber as características dos dados. A avaliação do sistema é realizada através da percentagem de acerto dos classificadores. Os resultados obtidos apresentam melhorias significativas em comparação com os trabalhos relacionados.

Data mining framework for fatty liver disease classification in ultrasound: a hybrid feature extraction paradigm

PURPOSE: Fatty liver disease (FLD) is an increasing prevalent disease that can be reversed if detected early. Ultrasound is the safest and ubiquitous method for identifying FLD. Since expert sonographers are required to accurately interpret the liver ultrasound images, lack of the same will result in interobserver variability. For more objective interpretation, high accuracy, and quick second opinions, computer aided diagnostic (CAD) techniques may be exploited. The purpose of this work is to develop one such CAD technique for accurate classification of normal livers and abnormal livers affected by FLD. METHODS: In this paper, the authors present a CAD technique (called Symtosis) that uses a novel combination of significant features based on the texture, wavelet transform, and higher order spectra of the liver ultrasound images in various supervised learning-based classifiers in order to determine parameters that classify normal and FLD-affected abnormal livers. RESULTS: On evaluating the proposed technique on a database of 58 abnormal and 42 normal liver ultrasound images, the authors were able to achieve a high classification accuracy of 93.3% using the decision tree classifier. CONCLUSIONS: This high accuracy added to the completely automated classification procedure makes the authors' proposed technique highly suitable for clinical deployment and usage.

Estimação de cobertura rádio em GSM-R através de redes neuronais

Trabalho Final de Mestrado para obtenção do grau de Mestre em Engenharia de Eletrónica e Telecomunicações

Feature Discretization with Relevance and Mutual Information Criteria

Feature discretization (FD) techniques often yield adequate and compact representations of the data, suitable for machine learning and pattern recognition problems. These representations usually decrease the training time, yielding higher classification accuracy while allowing for humans to better understand and visualize the data, as compared to the use of the original features. This paper proposes two new FD techniques. The first one is based on the well-known Linde-Buzo-Gray quantization algorithm, coupled with a relevance criterion, being able perform unsupervised, supervised, or semi-supervised discretization. The second technique works in supervised mode, being based on the maximization of the mutual information between each discrete feature and the class label. Our experimental results on standard benchmark datasets show that these techniques scale up to high-dimensional data, attaining in many cases better accuracy than existing unsupervised and supervised FD approaches, while using fewer discretization intervals.

Exploiting the bin-class histograms for feature selection on discrete data

In machine learning and pattern recognition tasks, the use of feature discretization techniques may have several advantages. The discretized features may hold enough information for the learning task at hand, while ignoring minor fluctuations that are irrelevant or harmful for that task. The discretized features have more compact representations that may yield both better accuracy and lower training time, as compared to the use of the original features. However, in many cases, mainly with medium and high-dimensional data, the large number of features usually implies that there is some redundancy among them. Thus, we may further apply feature selection (FS) techniques on the discrete data, keeping the most relevant features, while discarding the irrelevant and redundant ones. In this paper, we propose relevance and redundancy criteria for supervised feature selection techniques on discrete data. These criteria are applied to the bin-class histograms of the discrete features. The experimental results, on public benchmark data, show that the proposed criteria can achieve better accuracy than widely used relevance and redundancy criteria, such as mutual information and the Fisher ratio.

Learning and Knowledge in the Context of Absorptive Capacity

Develop a new model of Absorptive Capacity taking into account two variables namely Learning and knowledge to explain how companies transform information into knowledge

A supervised versus home-based program effects on liver transplanted familial amyloidotic polyneuropathy patients: walking, fatigue and quality of life

Purpose: To evaluate the effects of a six months exercise training program on walking capacity, fatigue and health related quality of life (HRQL). Relevance: Familial amyloidotic polyneuropathy disease (FAP) is an autossomic neurodegenerative disease, related with systemic deposition of amyloidal fibre mainly on peripheral nervous system and mainly produced in the liver. FAP often results in severe functional limitations. Liver transplantation is used as the only therapy so far, that stop the progression of some aspects of this disease. Transplantation requires aggressive medication which impairs muscle metabolism and associated to surgery process and previous possible functional impairments, could lead to serious deconditioning. Reports of fatigue are common feature in transplanted patients. The effect of supervised or home-based exercise training programs in FAP patients after a liver transplant (FAPTX) is currently unknown.

A supervised versus home-based program effects on liver transplanted familial amyloidotic polyneuropathy patients: walking, fatigue and quality of life

Familial amyloidotic polyneuropathy is a systemic deposition of amyloidal fibre mainly on peripheral nervous system (but also in other systems like heart, gastrointestinal tract, kidneys, etc) and mainly produced in the liver. Purpose of this study: to evaluate the effects of a six months exercise training program(supervised or home-based) on walking capacity, fatigue and health related quality of life (HRQL) on Familial Amyloidotic Polyneuropathy patients submitted to a liver transplant.

Learning dependent sources using mixtures of Dirichlet: applications on hyperspectral unmixing

This paper is an elaboration of the DECA algorithm [1] to blindly unmix hyperspectral data. The underlying mixing model is linear, meaning that each pixel is a linear mixture of the endmembers signatures weighted by the correspondent abundance fractions. The proposed method, as DECA, is tailored to highly mixed mixtures in which the geometric based approaches fail to identify the simplex of minimum volume enclosing the observed spectral vectors. We resort then to a statitistical framework, where the abundance fractions are modeled as mixtures of Dirichlet densities, thus enforcing the constraints on abundance fractions imposed by the acquisition process, namely non-negativity and constant sum. With respect to DECA, we introduce two improvements: 1) the number of Dirichlet modes are inferred based on the minimum description length (MDL) principle; 2) The generalized expectation maximization (GEM) algorithm we adopt to infer the model parameters is improved by using alternating minimization and augmented Lagrangian methods to compute the mixing matrix. The effectiveness of the proposed algorithm is illustrated with simulated and read data.

Statistical motion learning for improved transform domain Wyner-Ziv video coding

Wyner - Ziv (WZ) video coding is a particular case of distributed video coding (DVC), the recent video coding paradigm based on the Slepian - Wolf and Wyner - Ziv theorems which exploits the source temporal correlation at the decoder and not at the encoder as in predictive video coding. Although some progress has been made in the last years, WZ video coding is still far from the compression performance of predictive video coding, especially for high and complex motion contents. The WZ video codec adopted in this study is based on a transform domain WZ video coding architecture with feedback channel-driven rate control, whose modules have been improved with some recent coding tools. This study proposes a novel motion learning approach to successively improve the rate-distortion (RD) performance of the WZ video codec as the decoding proceeds, making use of the already decoded transform bands to improve the decoding process for the remaining transform bands. The results obtained reveal gains up to 2.3 dB in the RD curves against the performance for the same codec without the proposed motion learning approach for high motion sequences and long group of pictures (GOP) sizes.

Dynamic equilibrium through reinforcement learning

Reinforcement Learning is an area of Machine Learning that deals with how an agent should take actions in an environment such as to maximize the notion of accumulated reward. This type of learning is inspired by the way humans learn and has led to the creation of various algorithms for reinforcement learning. These algorithms focus on the way in which an agent’s behaviour can be improved, assuming independence as to their surroundings. The current work studies the application of reinforcement learning methods to solve the inverted pendulum problem. The importance of the variability of the environment (factors that are external to the agent) on the execution of reinforcement learning agents is studied by using a model that seeks to obtain equilibrium (stability) through dynamism – a Cart-Pole system or inverted pendulum. We sought to improve the behaviour of the autonomous agents by changing the information passed to them, while maintaining the agent’s internal parameters constant (learning rate, discount factors, decay rate, etc.), instead of the classical approach of tuning the agent’s internal parameters. The influence of changes on the state set and the action set on an agent’s capability to solve the Cart-pole problem was studied. We have studied typical behaviour of reinforcement learning agents applied to the classic BOXES model and a new form of characterizing the environment was proposed using the notion of convergence towards a reference value. We demonstrate the gain in performance of this new method applied to a Q-Learning agent.

e-learning in the classroom?

As teachers, we are challenged everyday to solve pedagogical problems and we have to fight for our students’ attention in a media rich world. I will talk about how we use ICT in Initial Teacher Training and give you some insight on what we are doing. The most important benefit of using ICT in education is that it makes us reflect on our practice. There is no doubt that our classrooms need to be updated, but we need to be critical about every peace of hardware, software or service that we bring into them. It is not only because our budgets are short, but also because e‐learning is primarily about learning, not technology. Therefore, we need to have the knowledge and skills required to act in different situations, and choose the best tool for the job. Not all subjects are suitable for e‐learning, nor do all students have the skills to organize themselves their own study times. Also not all teachers want to spend time programming or learning about instructional design and metadata. The promised land of easy use of authoring tools (e.g. eXe and Reload) that will lead to all teachers become Learning Objects authors and share these LO in Repositories, all this failed, like previously HyperCard, Toolbook and others. We need to know a little bit of many different technologies so we can mobilize this knowledge when a situation requires it: integrate e‐learning technologies in the classroom, not a flipped classroom, just simple tools. Lecture capture, mobile phones and smartphones, pocket size camcorders, VoIP, VLE, live video broadcast, screen sharing, free services for collaborative work, save, share and sync your files. Do not feel stressed to use everything, every time. Just because we have a whiteboard does not mean we have to make it the centre of the classroom. Start from where you are, with your preferred subject and the tools you master. Them go slowly and try some new tool in a non‐formal situation and with just one or two students. And you don’t need to be alone: subscribe a mailing list and share your thoughts with other teachers in a dedicated forum, even better if both are part of a community of practice, and share resources. We did that for music teachers and it was a success, in two years arriving at 1.000 members. Just do it.

Estudo para a implementação de plataformas de e-learning no sistema de formação dos recursos humanos da saúde: o caso particular dos enfermeiros de um hospital privado

Mestrado em Intervenção Sócio-Organizacional na Saúde - Área de especialização: Políticas de Administração e Gestão de Serviços de Saúde.

Experiencing flow while teaching and learning in individual tuition settings

Conferência anual da ISME

A utilização da plataforma Educast@fccn, como ferramenta de gravação de aulas no ambiente de e-learning português

Dissertação apresentada à Escola Superior de Comunicação Social como parte dos requisitos para obtenção de grau de mestre em Audiovisual e Multimédia.