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.

Software for pattern recognition of the larvae of Aedes aegypti and Aedes albopictus

Software for pattern recognition of the larvae of mosquitoes Aedes aegypti and Aedes albopictus, biological vectors of dengue and yellow fever, has been developed. Rapid field identification of larva using a digital camera linked to a laptop computer equipped with this software may greatly help prevention campaigns.

Texto(s) e competência textual

A investigação de que resulta o presente trabalho foi desenvolvida em Teoria do texto - área de especialização em Linguística criada na FCSH - UNL pela Professora Luísa Opitz. Os contornos teóricos e epistemológicos da configuração disciplinar assim designada merecem naturalmente uma atenção particular. Pode dizer-se que os primeiros contributos, no sentido de uma abordagem linguística do texto, se devem aos vários trabalhos que, sobretudo na Holanda e na Alemanha, desde o início dos anos setenta, preconizavam o alargamento do quadro generativista para além do domínio da frase. A estes projectos de gramática de texto convém também associar. como se pode compreender, a noção de competência textual - enquanto sistema de regras susceptíveis de derivarem qualquer texto, numa determinada lingua natural. Veja-se o paralelismo da definição proposta por Petôfi (um dos autores em destaque, nesta perspectiva): Its direct aim [of the grammatical theory of verbal texts] is to describe the knowledge of the 'ideal native speaker/listener' concernmg the grammatical structuredness of verbal texts (i.e. his verbal grammatical competence). PETÔFI 1973:206 Quase em simultâneo com a convicção generativista, ou decorrendo de alguma insatisfacão que se ia instalando, outras tendências menos formalizantes se faziam também sentir. Pode destacar-se, em particular, o ponto de vista de P. Hartmann, no prefácio que assina para Studies in Text Grammar, editado por J.S. Petôfi e H. Rieser em 1973. Assinalando a mudança, em termos de interesses epistemológicos, associada ao facto de se tratar de objectos cuja descrição requer mais dimensões do que as contempladas por uma gramática de frase, Hartmann afirma: Se a nogão de texto aparece associada å de fungão (ou funções), uma e outra são fundamentalmente determinadas pela decisão relativa aos objectos sujeitos a observação - isto é, pelo facto de se tomarem em consideração os textos efectivamente produzidos em situações de comunicação, não sujeitos, portanto, a reduções metodológicas.

Reconstructing transcriptional regulatory networks using data integration and text mining

Transcriptional Regulatory Networks (TRNs) are powerful tool for representing several interactions that occur within a cell. Recent studies have provided information to help researchers in the tasks of building and understanding these networks. One of the major sources of information to build TRNs is biomedical literature. However, due to the rapidly increasing number of scientific papers, it is quite difficult to analyse the large amount of papers that have been published about this subject. This fact has heightened the importance of Biomedical Text Mining approaches in this task. Also, owing to the lack of adequate standards, as the number of databases increases, several inconsistencies concerning gene and protein names and identifiers are common. In this work, we developed an integrated approach for the reconstruction of TRNs that retrieve the relevant information from important biological databases and insert it into a unique repository, named KREN. Also, we applied text mining techniques over this integrated repository to build TRNs. However, was necessary to create a dictionary of names and synonyms associated with these entities and also develop an approach that retrieves all the abstracts from the related scientific papers stored on PubMed, in order to create a corpora of data about genes. Furthermore, these tasks were integrated into @Note, a software system that allows to use some methods from the Biomedical Text Mining field, including an algorithms for Named Entity Recognition (NER), extraction of all relevant terms from publication abstracts, extraction relationships between biological entities (genes, proteins and transcription factors). And finally, extended this tool to allow the reconstruction Transcriptional Regulatory Networks through using scientific literature.

Estudo acústico de /a/ acentuado na fala bracarense: potenciais aplicações

Dissertação de mestrado em Ciências da Linguagem

Emotion recognition within spoken dialog systems

Magdeburg, Univ., Fak. für Elektrotechnik und Informationstechnik, Diss., 2011

Optimization-based solutions to constrained trajectory-tracking and path-following problems

Magdeburg, Univ., Fak. für Elektrotechnik und Informationstechnik, Diss., 2012

Vision-based representation and recognition of human activities in image sequences

Magdeburg, Univ., Fak. für Elektrotechnik und Informationstechnik, Diss., 2013

Statistical pattern recognition for audio-forensics : empirical investigations on the application scenarios audio steganalysis and microphone forensics

Magdeburg, Univ., Fak. für Informatik, Diss., 2013

Multimodal automatic user disposition recognition in human-machine interaction

Magdeburg, Univ., Fak. für Elektrotechnik und Informationstechnik, Diss., 2013

Neural correlates of context-dependent memory : the role of the insula in episodic encoding and recognition memory ; an fMRI experiment

Magdeburg, Univ., Med. Fak., Diss., 2014

Visual recognition systems in a car passenger compartment with the focus on facial driver identification

Magdeburg, Univ., Fak. für Informatik, Diss., 2014