Efficient feature selection filters for high-dimensional data

Feature selection is a central problem in machine learning and pattern recognition. On large datasets (in terms of dimension and/or number of instances), using search-based or wrapper techniques can be cornputationally prohibitive. Moreover, many filter methods based on relevance/redundancy assessment also take a prohibitively long time on high-dimensional. datasets. In this paper, we propose efficient unsupervised and supervised feature selection/ranking filters for high-dimensional datasets. These methods use low-complexity relevance and redundancy criteria, applicable to supervised, semi-supervised, and unsupervised learning, being able to act as pre-processors for computationally intensive methods to focus their attention on smaller subsets of promising features. The experimental results, with up to 10(5) features, show the time efficiency of our methods, with lower generalization error than state-of-the-art techniques, while being dramatically simpler and faster.

A emergência da leitura em crianças no jardim de infância

Relatório da Prática Profissional Supervisionada Mestrado em Educação Pré-Escolar

Programas de intervenção de escritas Inventadas: comparação de uma abordagem transmissiva e construtivista

O objectivo deste estudo é comparar programas de intervenção de escritas inventadas de natureza construtivista ou transmissiva. Participaram nesta investigação 78 crianças de idade pré-escolar, cujas escritas não representavam ainda os sons, tendo sido distribuídas por cinco grupos, quatro experimentais e um de controlo, equivalentes quanto à idade, inteligência, número de letras conhecidas e consciência fonológica. Entre o pré e o pós teste, as crianças dos grupos experimentais participaram num programa de intervenção de escritas inventadas de natureza construtivista ou transmissiva, manipulando-se ainda variáveis relacionadas com as características das palavras de treino e o tipo de instruções. Só se verifi cou uma evolução signifi cativa da qualidade das escritas inventadas nas crianças que participaram nos programas de intervenção de natureza construtivista.

Letter names and sounds: their implications for the phonetisation process

Our aim was to analyse the impact of the characteristics of words used in spelling programmes and the nature of instructional guidelines on the evolution from grapho-perceptive writing to phonetic writing in preschool children. The participants were 50 5-year-old children, divided in five equivalent groups in intelligence, phonological skills and spelling. All the children knew the vowels and the consonants B, D, P, R, T, V, F, M and C, but didn’t use them on spelling. Their spelling was evaluated in a pre and post-test with 36 words beginning with the consonants known. In-between they underwent a writing programme designed to lead them to use the letters P and T to represent the initial phonemes of words. The groups differed on the kind of words used on training (words whose initial syllable matches the name of the initial letter—Exp. G1 and Exp. G2—versus words whose initial syllable is similar to the sound of the initial letter—Exp. G3 and Exp. G4). They also differed on the instruction used in order to lead them to think about the relations between the initial phoneme of words and the initial consonant (instructions designed to make the children think about letter names—Exp. G1 and Exp. G3 —versus instructions designed to make the children think about letter sounds—Exp. G2 and Exp. G4). The 5th was a control group. All the children evolved to syllabic phonetisations spellings. There are no differences between groups at the number of total phonetisations but we found some differences between groups at the quality of the phonetisations.

A emergência da escrita: produções escritas de crianças no jardim de infância

Relatório da Prática Profissional Supervisionada Mestrado em Educação Pré-Escolar

Robot visual localization through local feature fusion: an evaluation of multiple classifiers combination approaches

In the last decade, local image features have been widely used in robot visual localization. In order to assess image similarity, a strategy exploiting these features compares raw descriptors extracted from the current image with those in the models of places. This paper addresses the ensuing step in this process, where a combining function must be used to aggregate results and assign each place a score. Casting the problem in the multiple classifier systems framework, in this paper we compare several candidate combiners with respect to their performance in the visual localization task. For this evaluation, we selected the most popular methods in the class of non-trained combiners, namely the sum rule and product rule. A deeper insight into the potential of these combiners is provided through a discriminativity analysis involving the algebraic rules and two extensions of these methods: the threshold, as well as the weighted modifications. In addition, a voting method, previously used in robot visual localization, is assessed. Furthermore, we address the process of constructing a model of the environment by describing how the model granularity impacts upon performance. All combiners are tested on a visual localization task, carried out on a public dataset. It is experimentally demonstrated that the sum rule extensions globally achieve the best performance, confirming the general agreement on the robustness of this rule in other classification problems. The voting method, whilst competitive with the product rule in its standard form, is shown to be outperformed by its modified versions.

A MAP approach to evidence accumulation clustering

The Evidence Accumulation Clustering (EAC) paradigm is a clustering ensemble method which derives a consensus partition from a collection of base clusterings obtained using different algorithms. It collects from the partitions in the ensemble a set of pairwise observations about the co-occurrence of objects in a same cluster and it uses these co-occurrence statistics to derive a similarity matrix, referred to as co-association matrix. The Probabilistic Evidence Accumulation for Clustering Ensembles (PEACE) algorithm is a principled approach for the extraction of a consensus clustering from the observations encoded in the co-association matrix based on a probabilistic model for the co-association matrix parameterized by the unknown assignments of objects to clusters. In this paper we extend the PEACE algorithm by deriving a consensus solution according to a MAP approach with Dirichlet priors defined for the unknown probabilistic cluster assignments. In particular, we study the positive regularization effect of Dirichlet priors on the final consensus solution with both synthetic and real benchmark data.

Text classification using compression-based dissimilarity measures

Arguably, the most difficult task in text classification is to choose an appropriate set of features that allows machine learning algorithms to provide accurate classification. Most state-of-the-art techniques for this task involve careful feature engineering and a pre-processing stage, which may be too expensive in the emerging context of massive collections of electronic texts. In this paper, we propose efficient methods for text classification based on information-theoretic dissimilarity measures, which are used to define dissimilarity-based representations. These methods dispense with any feature design or engineering, by mapping texts into a feature space using universal dissimilarity measures; in this space, classical classifiers (e.g. nearest neighbor or support vector machines) can then be used. The reported experimental evaluation of the proposed methods, on sentiment polarity analysis and authorship attribution problems, reveals that it approximates, sometimes even outperforms previous state-of-the-art techniques, despite being much simpler, in the sense that they do not require any text pre-processing or feature engineering.