Automatic cymbal classification

Dissertação apresentada na Faculdade de Ciências e Tecnologia da Universidade Nova de Lisboa para a obtenção do grau de Mestre em Engenharia Informática

Automatic Electricity Markets Data Extraction for Realistic Multi-agent Simulations

Electricity markets worldwide suffered profound transformations. The privatization of previously nationally owned systems; the deregulation of privately owned systems that were regulated; and the strong interconnection of national systems, are some examples of such transformations [1, 2]. In general, competitive environments, as is the case of electricity markets, require good decision-support tools to assist players in their decisions. Relevant research is being undertaken in this field, namely concerning player modeling and simulation, strategic bidding and decision-support.

An automatic tool to Extract, Transform and Load data from real electricity markets

The study of Electricity Markets operation has been gaining an increasing importance in the last years, as result of the new challenges that the restructuring produced. Currently, lots of information concerning Electricity Markets is available, as market operators provide, after a period of confidentiality, data regarding market proposals and transactions. These data can be used as source of knowledge, to define realistic scenarios, essential for understanding and forecast Electricity Markets behaviour. The development of tools able to extract, transform, store and dynamically update data, is of great importance to go a step further into the comprehension of Electricity Markets and the behaviour of the involved entities. In this paper we present an adaptable tool capable of downloading, parsing and storing data from market operators’ websites, assuring actualization and reliability of stored data.

Sistema de apoio à navegação baseado em automatic identification system

Dissertação de Mestrado Integrado em Engenharia Electrotécnica e Computadores

Automatic musical instrument recognition for multimedia indexing

Trabalho apresentado no âmbito do Mestrado em Engenharia Informática, como requisito parcial para obtenção do grau de Mestre em Engenharia Informática

Feeding sources and trypanosome infection index of Rhodnius pallescens in a Chagas disease endemic area of Amador County, Panama

The sylvatic triatomine Rhodnius pallescens is considered to be the most important and widespread vector of Trypanosoma cruzi and Trypanosoma rangeli in Panama. However, its behavior and biological characteristics have only been partially investigated. Thus, to achieve sustainable and efficient control over Chagas disease in Panama, a better understanding of the ecology and biology of R. pallescens is essential. In this study we evaluated R. pallescens host feeding sources using a dot-blot assay, and the trypanosome infection index by PCR analysis in a Chagas disease endemic area of central Panama. It was found that in peridomestic palm trees, 20.3% of the examined bugs had fed on opossums (Didelphis marsupialis). However, we observed an increased anthropophagy (25.4%) for those bugs collected inside houses. Considering the domestic and peridomestic habitats as a whole, the proportion of collected R. pallescens infected with trypanosomes was 87.4%. In the two habitats the predominant infection was with T. cruzi (80-90%). Between 47-51% of the analyzed triatomines were infected with T. rangeli. Mixed infections (40-51%) were also detected. These findings provide a better basis for the implementation of a rational control and surveillance program for Chagas disease in regions where R. pallescens is endemic.

Automatic syllabification for danish text-to-speech systems

In this paper, a rule-based automatic syllabifier for Danish is described using the Maximal Onset Principle. Prior success rates of rule-based methods applied to Portuguese and Catalan syllabification modules were on the basis of this work. The system was implemented and tested using a very small set of rules. The results gave rise to 96.9% and 98.7% of word accuracy rate, contrary to our initial expectations, being Danish a language with a complex syllabic structure and thus difficult to be rule-driven. Comparison with data-driven syllabification system using artificial neural networks showed a higher accuracy rate of the former system.

An automatic voice pleasantness classification system based on prosodic and acoustic patterns of voice preference

In the last few years the number of systems and devices that use voice based interaction has grown significantly. For a continued use of these systems the interface must be reliable and pleasant in order to provide an optimal user experience. However there are currently very few studies that try to evaluate how good is a voice when the application is a speech based interface. In this paper we present a new automatic voice pleasantness classification system based on prosodic and acoustic patterns of voice preference. Our study is based on a multi-language database composed by female voices. In the objective performance evaluation the system achieved a 7.3% error rate.

Automatic Small Bowel Tumor Diagnosis by Using Multi-Scale Wavelet-Based Analysis in Wireless Capsule Endoscopy Images

BACKGROUND: Wireless capsule endoscopy has been introduced as an innovative, non-invasive diagnostic technique for evaluation of the gastrointestinal tract, reaching places where conventional endoscopy is unable to. However, the output of this technique is an 8 hours video, whose analysis by the expert physician is very time consuming. Thus, a computer assisted diagnosis tool to help the physicians to evaluate CE exams faster and more accurately is an important technical challenge and an excellent economical opportunity. METHOD: The set of features proposed in this paper to code textural information is based on statistical modeling of second order textural measures extracted from co-occurrence matrices. To cope with both joint and marginal non-Gaussianity of second order textural measures, higher order moments are used. These statistical moments are taken from the two-dimensional color-scale feature space, where two different scales are considered. Second and higher order moments of textural measures are computed from the co-occurrence matrices computed from images synthesized by the inverse wavelet transform of the wavelet transform containing only the selected scales for the three color channels. The dimensionality of the data is reduced by using Principal Component Analysis. RESULTS: The proposed textural features are then used as the input of a classifier based on artificial neural networks. Classification performances of 93.1% specificity and 93.9% sensitivity are achieved on real data. These promising results open the path towards a deeper study regarding the applicability of this algorithm in computer aided diagnosis systems to assist physicians in their clinical practice.

Compliance with ESPGHAN Position on Complementary Feeding in a Multicultural European Community. Does Ethnicity Matter?

Introduction: In 2008, ESPGHAN published a position paper on complementary feeding providing recommendations to health care professionals. Cultural and socio-economic factors might affect the compliance to these orientations. Aim: To estimate the prevalence of inadequacies during complementary feeding (ESPGHAN, 2008) and its association with different ethnic backgrounds. Methods: Cross-sectional survey of a convenience sample of caretakers of children up to 24 months of age in a single community health centre in Greater Lisbon, through a volunteer, self-applied questionnaire. Results: From a sample of children with wide cultural diversity, 161 valid questionnaires were obtained (median child’s age 9 months, median mother’s age 32 years). The prevalence rate of at least one complementary feeding inadequacy was 46% (95%CI: 38.45-53.66). The commonest inadequacies were: avoiding lumpy solid foods after 10 months of age (66.7%), avoidance or delayed introduction of foods beyond 12 months (35.4%), introduction of gluten beyond 7 months (15.9%) or salt before 12 months (6.7%). For each increase of 1 month in the age of the child, the odds of inadequacies raised 36.7% (OR = 1.37; 95%CI: 1.20-1.56; p < 0.001). The odds for inadequacies in children of African or Brazilian offspring was three times higher that of Portuguese ancestry (OR = 3.31; 95%CI: 0.87-12.61; p = 0.079). The influence of grandparents was related to an increase in the odds of inadequacies (OR = 3.69; 95%CI: 0.96-14.18; p = 0.058).Conclusion: Inadequacies during complementary feeding are frequent and may be influenced by the cultural background.

Serum Trace Elements in Dysphagic Gastrostomy Candidates Before Endoscopic Gastrostomy for Long Term Enteral Feeding

BACKGROUND & AIMS: Patients who underwent endoscopic gastrostomy (PEG) present protein-energy malnutrition, but little is known about Trace Elements (TE), Zinc (Zn), Copper (Cu), Selenium (Se), Iron (Fe), Chromium (Cr). Our aim was the evaluation of serum TE in patients who underwent PEG and its relationship with serum proteins, BMI and nature of underlying disorder. METHODS: A prospective observational study was performed collecting: patient's age, gender, underlying disorder, NRS-2002, BMI, serum albumin, transferrin and TE concentration. We used ferrozine colorimetric method for Fe; Inductively Coupled Plasma-Atomic Emission Spectroscopy for Zn/Cu; Furnace Atomic Absorption Spectroscopy for Se/Cr. The patients were divided into head and neck cancer (HNC) and neurological dysphagia (ND). RESULTS: 146 patients (89 males), 21-95 years: HNC-56; ND-90. Low BMI in 78. Low values mostly for Zn (n = 122) and Fe (n = 69), but less for Se (n = 31), Cu (n = 16), Cr (n = 7); low albumin in 77, low transferrin in 94 and 66 with both proteins low. Significant differences between the groups of underlying disease only for Zn (t140.326 = -2,642, p < 0.01) and a correlation between proteins and TE respectively albumin and Zn (r = 0.197, p = 0.025), and albumin and Fe (r = 0.415, p = 0.000). CONCLUSIONS: When gastrostomy was performed, patients display low serum TE namely Zn, but also Fe, less striking regarding others TE. It was related with prolonged fasting, whatever the underlying disease. Low proteins were associated with low TE. Teams taking care of PEG-patients should use Zn supplementation and include other TE evaluation as part of the nutritional assessment of PEG candidates.

Customer Lifetime Value: a framework for application in the insurance industry - Building a Business Process to Generate and Maintain an Automatic Estimation Agent

Research Project submited as partial fulfilment for the Master Degree in Statistics and Information Management

Automatic information retrieval through text-mining

The dissertation presented for obtaining the Master’s Degree in Electrical Engineering and Computer Science, at Universidade Nova de Lisboa, Faculdade de Ciências e Tecnologia