Data mining techniques to support the classification of MV electricity customers

This paper describes a methodology that was developed for the classification of Medium Voltage (MV) electricity customers. Starting from a sample of data bases, resulting from a monitoring campaign, Data Mining (DM) techniques are used in order to discover a set of a MV consumer typical load profile and, therefore, to extract knowledge regarding to the electric energy consumption patterns. In first stage, it was applied several hierarchical clustering algorithms and compared the clustering performance among them using adequacy measures. In second stage, a classification model was developed in order to allow classifying new consumers in one of the obtained clusters that had resulted from the previously process. Finally, the interpretation of the discovered knowledge are presented and discussed.

Role of malnutrition and parasite infections in the spatial variation in children’s anaemia risk in Northern Angola

Anaemia has a significant impact on child development and mortality and is a severe public health problem in most countries in sub-Saharan Africa. Nutritional and infectious causes of anaemia are geographically variable and anaemia maps based on information on the major aetiologies of anaemia are important for identifying communities most in need and the relative contribution of major causes. We investigated the consistency between ecological and individual-level approaches to anaemia mapping, by building spatial anaemia models for children aged ≤15 years using different modeling approaches. We aimed to a) quantify the role of malnutrition, malaria, Schistosoma haematobium and soil-transmitted helminths (STH) for anaemia endemicity in children aged ≤15 years and b) develop a high resolution predictive risk map of anaemia for the municipality of Dande in Northern Angola. We used parasitological survey data on children aged ≤15 years to build Bayesian geostatistical models of malaria (PfPR≤15), S. haematobium, Ascaris lumbricoides and Trichuris trichiura and predict small-scale spatial variation in these infections. The predictions and their associated uncertainty were used as inputs for a model of anemia prevalence to predict small-scale spatial variation of anaemia. Stunting, PfPR≤15, and S. haematobium infections were significantly associated with anaemia risk. An estimated 12.5%, 15.6%, and 9.8%, of anaemia cases could be averted by treating malnutrition, malaria, S. haematobium, respectively. Spatial clusters of high risk of anaemia (>86%) were identified. Using an individual-level approach to anaemia mapping at a small spatial scale, we found that anaemia in children aged ≤15 years is highly heterogeneous and that malnutrition and parasitic infections are important contributors to the spatial variation in anemia risk. The results presented in this study can help inform the integration of the current provincial malaria control program with ancillary micronutrient supplementation and control of neglected tropical diseases, such as urogenital schistosomiasis and STH infection.

Demand response programs definition supported by clustering and classification techniques

The growing importance and influence of new resources connected to the power systems has caused many changes in their operation. Environmental policies and several well know advantages have been made renewable based energy resources largely disseminated. These resources, including Distributed Generation (DG), are being connected to lower voltage levels where Demand Response (DR) must be considered too. These changes increase the complexity of the system operation due to both new operational constraints and amounts of data to be processed. Virtual Power Players (VPP) are entities able to manage these resources. Addressing these issues, this paper proposes a methodology to support VPP actions when these act as a Curtailment Service Provider (CSP) that provides DR capacity to a DR program declared by the Independent System Operator (ISO) or by the VPP itself. The amount of DR capacity that the CSP can assure is determined using data mining techniques applied to a database which is obtained for a large set of operation scenarios. The paper includes a case study based on 27,000 scenarios considering a diversity of distributed resources in a 33 bus distribution network.

Criação de valor, gestão de risco e as medidas de performance ajustadas ao risco: aplicação do RAROC - Risk Adjustment Return on Capital - ao grupo crédito agrícola

Mestrado em Contabilidade e Gestão das Instituições Financeiras

A long-term risk management tool for electricity markets using swarm intelligence

This paper addresses the optimal involvement in derivatives electricity markets of a power producer to hedge against the pool price volatility. To achieve this aim, a swarm intelligence meta-heuristic optimization technique for long-term risk management tool is proposed. This tool investigates the long-term opportunities for risk hedging available for electric power producers through the use of contracts with physical (spot and forward contracts) and financial (options contracts) settlement. The producer risk preference is formulated as a utility function (U) expressing the trade-off between the expectation and the variance of the return. Variance of return and the expectation are based on a forecasted scenario interval determined by a long-term price range forecasting model. This model also makes use of particle swarm optimization (PSO) to find the best parameters allow to achieve better forecasting results. On the other hand, the price estimation depends on load forecasting. This work also presents a regressive long-term load forecast model that make use of PSO to find the best parameters as well as in price estimation. The PSO technique performance has been evaluated by comparison with a Genetic Algorithm (GA) based approach. A case study is presented and the results are discussed taking into account the real price and load historical data from mainland Spanish electricity market demonstrating the effectiveness of the methodology handling this type of problems. Finally, conclusions are dully drawn.

Pediculus capitis infestation according to sex and social factors in Argentina

OBJECTIVE: To determine the intensity of Pediculus capitis infestation (abundance) among Argentinean schoolchildren. Children's sex and social stratum were analyzed as modifiers of the general prevalence and degree of parasitism. METHODS: The study included 1,370 schoolchildren (692 girls, 678 boys) from 26 schools of the province of La Rioja (21 public schools, five private schools). Classic prevalence was obtained as the percentage of children with nits and/or lice. Moreover, five degrees of parasitism were classified: 0) children with no signs of pediculosis; 0+) children with evidence of past infestation; 1) children with a recent infestation and low probability of active parasitism; 2) children with a recent infestation and high probability of active parasitism; 3) children with mobile lice (active pediculosis). RESULTS: The general prevalence was 61.4% (girls: 79%; boys: 44%, p<0.001). Private schools showed lower prevalence than public schools (p=0.02), especially due to the low prevalence in boys. Fifty percent of children were classified in classes 0 and 0+, 22% in class 1; and 28% in grades 2 and 3. The proportion of children in grade 3 was higher in public schools than in private schools. There were significant sexual differences in the intensity of parasitism for grades 2 and 3, where girls' rates exceeded twice those of boys'. CONCLUSIONS: Sex and social stratum are important modifiers of P. capitis general prevalence and degree of infestation. The classification of children by intensity of infestation allowed a more precise delimitation of this condition, which is especially important for disease surveillance and application of control measures.

Role of malnutrition and parasite infections in the spatial variation in children’s anaemia risk in northern Angola

Anaemia is known to have an impact on child development and mortality and is a severe public health problem in most countries in sub-Saharan Africa. We investigated the consistency between ecological and individual-level approaches to anaemia mapping by building spatial anaemia models for children aged ≤15 years using different modelling approaches. We aimed to (i) quantify the role of malnutrition, malaria, Schistosoma haematobium and soil-transmitted helminths (STHs) in anaemia endemicity; and (ii) develop a high resolution predictive risk map of anaemia for the municipality of Dande in northern Angola. We used parasitological survey data for children aged ≤15 years to build Bayesian geostatistical models of malaria (PfPR≤15), S. haematobium, Ascaris lumbricoides and Trichuris trichiura and predict small-scale spatial variations in these infections. Malnutrition, PfPR≤15, and S. haematobium infections were significantly associated with anaemia risk. An estimated 12.5%, 15.6% and 9.8% of anaemia cases could be averted by treating malnutrition, malaria and S. haematobium, respectively. Spatial clusters of high risk of anaemia (>86%) were identified. Using an individual-level approach to anaemia mapping at a small spatial scale, we found that anaemia in children aged ≤15 years is highly heterogeneous and that malnutrition and parasitic infections are important contributors to the spatial variation in anaemia risk. The results presented in this study can help inform the integration of the current provincial malaria control programme with ancillary micronutrient supplementation and control of neglected tropical diseases such as urogenital schistosomiasis and STH infections.

Autonomy of long-stay psychiatric inpatients

OBJECTIVE: To assess personal autonomy of long-stay psychiatric inpatients, to identify those patients who could be discharged and to evaluate the impact of sociodemographic variables, social functioning, and physical disabilities on their autonomy was also assessed. METHODS: A total of 584 long-stay individuals of a psychiatric hospital (96% of the hospital population) in Southern Brazil was assessed between July and August 2002. The following instruments, adapted to the Brazilian reality, were used: independent living skills survey, social behavioral schedule, and questionnaire for assessing physical disability. RESULTS: Patients showed severe impairment of their personal autonomy, especially concerning money management, work-related skills and leisure, food preparation, and use of transportation. Autonomy deterioration was associated with length of stay (OR=1.02), greater physical disability (OR=1.54; p=0.01), and male gender (OR=3.11; p<0.001). The risk estimate of autonomy deterioration was 23 times greater among those individuals with severe impairment of social functioning (95% CI: 10.67-49.24). CONCLUSIONS: In-patients studied showed serious impairment of autonomy. While planning these patients' discharge their deficits should be taken into consideration. Assessment of patients' ability to function and to be autonomous helps in identifying their needs for care and to evaluate their actual possibilities of social reinsertion.

Exposure and genotoxicity assessment methodologies: the case of formaldehyde occupational exposure

Formaldehyde (FA) ranks 25th in the overall U.S. chemical production, with more than 5 million tons produced each year. Given its economic importance and widespread use, many people are exposed to FA occupationally. Recently, based on the correlation with nasopharyngeal cancer in humans, the International Agency for Research on Cancer (IARC) confirmed the classification of FA as a Group I substance. Considering the epidemiological evidence of a potential association with leukemia, the IARC has concluded that FA can cause this lymphoproliferative disorder. Our group has developed a method to assess the exposure and genotoxicity effects of FA in two different occupational settings, namely FAbased resins production and pathology and anatomy laboratories. For exposure assessment we applied simultaneously two different techniques of air monitoring: NIOSH Method 2541 and Photo Ionization Detection Equipment with simultaneously video recording. Genotoxicity effects were measured by cytokinesis-blocked micronucleus assay in peripheral blood lymphocytes and by micronucleus test in exfoliated oral cavity epithelial cells, both considered target cells. The two exposure assessment techniques show that in the two occupational settings peak exposures are still occurring. There was a statistical significant increase in the micronucleus mean of epithelial cells and peripheral lymphocytes of exposed individuals compared with controls. In conclusion, the exposure and genotoxicity effects assessment methodologies developed by us allowed to determine that these two occupational settings promote exposure to high peak FA concentrations and an increase in the micronucleus mean of exposed workers. Moreover, the developed techniques showed promising results and could be used to confirm and extend the results obtained by the analytical techniques currently available.

Dietary patterns and risk of oral cancer: a case-control study in São Paulo, Brazil

OBJECTIVE: To analyze the association between dietary patterns and oral cancer. METHODS: The study, part of a Latin American multicenter hospital-based case-control study, was conducted in São Paulo, Southeastern Brazil, between November 1998 and March 2002 and included 366 incident cases of oral cancer and 469 controls, frequency-matched with cases by sex and age. Dietary data were collected using a food frequency questionnaire. The risk associated with the intake of food groups defined a posteriori, through factor analysis (called factors), was assessed. The first factor, labeled "prudent," was characterized by the intake of vegetables, fruit, cheese, and poultry. The second factor, "traditional," consisted of the intake of rice, pasta, pulses, and meat. The third factor, "snacks," was characterized as the intake of bread, butter, salami, cheese, cakes, and desserts. The fourth, "monotonous," was inversely associated with the intake of fruit, vegetables and most other food items. Factor scores for each component retained were calculated for cases and controls. After categorization of factor scores into tertiles according to the distribution of controls, odds ratios and 95% confidence intervals were calculated using unconditional multiple logistic regression. RESULTS: "Traditional" factor showed an inverse association with cancer (OR=0.51; 95% CI: 0.32; 0.81, p-value for trend 0.14), whereas "monotonous" was positively associated with the outcome (OR=1.78; 95% CI: 1.78; 2.85, p-value for trend <0.001). CONCLUSIONS: The study data suggest that the traditional Brazilian diet, consisting of rice and beans plus moderate amounts of meat, may confer protection against oral cancer, independently of any other risk factors such as alcohol intake and smoking.

Risk-factors for antepartum fetal deaths in the city of São Paulo, Brazil

OBJECTIVE: To assess risk factors for antepartum fetal deaths. METHODS: A population-based case-control study was carried out in the city of São Paulo from August 2000 to January 2001. Subjects were selected from a birth cohort from a linked birth and death certificate database. Cases were 164 antepartum fetal deaths and controls were drawn from a random sample of 313 births surviving at least 28 days. Information was collected from birth and death certificates, hospital records and home interviews. A hierarchical conceptual framework guided the logistic regression analysis. RESULTS: Statistically significant factors associated with antepartum fetal death were: mother without or recent marital union; mother's education under four years; mothers with previous low birth weight infant; mothers with hypertension, diabetes, bleeding during pregnancy; no or inadequate prenatal care; congenital malformation and intrauterine growth restriction. The highest population attributable fractions were for inadequacy of prenatal care (40%), hypertension (27%), intrauterine growth restriction (30%) and absence of a long-standing union (26%). CONCLUSIONS: Proximal biological risk factors are most important in antepartum fetal deaths. However, distal factors - mother's low education and marital status - are also significant. Improving access to and quality of prenatal care could have a large impact on fetal mortality.

Automatic vehicle detection and classification

This paper presents a proposal for an automatic vehicle detection and classification (AVDC) system. The proposed AVDC should classify vehicles accordingly to the Portuguese legislation (vehicle height over the first axel and number of axels), and should also support profile based classification. The AVDC should also fulfill the needs of the Portuguese motorway operator, Brisa. For the classification based on the profile we propose:he use of Eigenprofiles, a technique based on Principal Components Analysis. The system should also support multi-lane free flow for future integration in this kind of environments.

Classification and staging of chronic liver disease from multimodal data

Chronic liver disease (CLD) is most of the time an asymptomatic, progressive, and ultimately potentially fatal disease. In this study, an automatic hierarchical procedure to stage CLD using ultrasound images, laboratory tests, and clinical records are described. The first stage of the proposed method, called clinical based classifier (CBC), discriminates healthy from pathologic conditions. When nonhealthy conditions are detected, the method refines the results in three exclusive pathologies in a hierarchical basis: 1) chronic hepatitis; 2) compensated cirrhosis; and 3) decompensated cirrhosis. The features used as well as the classifiers (Bayes, Parzen, support vector machine, and k-nearest neighbor) are optimally selected for each stage. A large multimodal feature database was specifically built for this study containing 30 chronic hepatitis cases, 34 compensated cirrhosis cases, and 36 decompensated cirrhosis cases, all validated after histopathologic analysis by liver biopsy. The CBC classification scheme outperformed the nonhierachical one against all scheme, achieving an overall accuracy of 98.67% for the normal detector, 87.45% for the chronic hepatitis detector, and 95.71% for the cirrhosis detector.

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.

The usefulness of ultrasound in the classification of chronic liver disease

Chronic Liver Disease is a progressive, most of the time asymptomatic, and potentially fatal disease. In this paper, a semi-automatic procedure to stage this disease is proposed based on ultrasound liver images, clinical and laboratorial data. In the core of the algorithm two classifiers are used: a k nearest neighbor and a Support Vector Machine, with different kernels. The classifiers were trained with the proposed multi-modal feature set and the results obtained were compared with the laboratorial and clinical feature set. The results showed that using ultrasound based features, in association with laboratorial and clinical features, improve the classification accuracy. The support vector machine, polynomial kernel, outperformed the others classifiers in every class studied. For the Normal class we achieved 100% accuracy, for the chronic hepatitis with cirrhosis 73.08%, for compensated cirrhosis 59.26% and for decompensated cirrhosis 91.67%.