Made available in DSpace on 2017-07-10T16:41:32Z (GMT). No. of bitstreams: 1 Dissertacao Altamira Queiroz2.pdf: 2299194 bytes, checksum: 07ecb127ebc11ad21a0cb551e23c2f1b (MD5) Previous issue date: 2016-02-19 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / One of the main problems currently faced by electric utilities is the occurrence of energy losses in the distribution network caused by fraud and electricity theft. Because of the financial losses and risks to public safety, the development of solutions to detect and combat fraud in the distribution networks is of the utmost importance. This work presents an analysis of computational intelligence algorithms to extract knowledge in databases with information from monthly energy consumption to identify consumption patterns with anomalies which could represent fraud. The algorithms Artificial Neural Networks and Support Vector Machines were tested to see which one perform better on the identification consumption patterns with abnormalities. Tests have shown that the algorithms used are able to detect patterns in electricity consumption curves, including special situations of fraud that manual techniques did not detect. / Um dos principais problemas que enfrentam atualmente as empresas concessionárias de energia elétrica é a ocorrência de perdas de energia na rede de distribuição, causadas por fraudes e furtos de energia elétrica. Sendo que tais problemas provocam prejuízos financeiros e também colocam em risco a segurança pública, é de grande interesse das concessionárias encontrar soluções para detectar e combater fraudes nas redes de distribuição de energia elétrica. Neste conceito, o presente trabalho apresenta uma análise dos algoritmos de Inteligência Computacional para extrair conhecimento de bases de dados de informações de consumo mensal de energia elétricas de usuários de uma determinada concessionária, a fim de identificar padrões de consumo com anomalias que representem possíveis fraudes nas redes de distribuição de energia elétrica. Para detectar padrões nas curvas de consumo, foram utilizados algoritmos de Redes Neurais Artificiais e Máquinas de Vetores de Suporte. Após a criação dos modelos, estes foram testados para verificar qual seria o melhor algoritmo para a detecção de padrões de consumo com anomalias, e os resultados obtidos, foram então, comparados com uma base de dados fornecida pela concessionária com a verificação manual dos usuários. Os testes demonstraram que os algoritmos utilizados são capazes de detectar padrões nas curvas de consumo de energia elétrica, inclusive detectando situações especiais de fraudes que técnicas manuais não detectaram.

O disco intervertebral é uma estrutura cuja função é receber, amortecer e distribuir o impacto das cargas impostas sobre a coluna vertebral. O aumento da idade e a postura adotada pelo indivíduo podem levar à degeneração do disco intervertebral. Atualmente, a Ressonância Magnética (RM) é considerada o melhor e mais sensível método não invasivo de avaliação por imagem do disco intervertebral. Neste trabalho foram desenvolvidos métodos quantitativos computadorizados para auxílio ao diagnóstico da degeneração do disco intervertebral em imagens de ressonância magnética ponderadas em T2 da coluna lombar, de acordo com a escala de Pfirrmann, uma escala semi-quantitativa, com cinco graus de degeneração. Os algoritmos computacionais foram testados em um conjunto de dados que consiste de imagens de 300 discos, obtidos de 102 indivíduos, com diferentes graus de degeneração. Máscaras binárias de discos segmentados manualmente foram utilizadas para calcular seus centroides, visando criar um ponto de referência para possibilitar a extração de atributos. Uma análise de textura foi realizada utilizando a abordagem proposta por Haralick. Para caracterização de forma, também foram calculados os momentos invariantes definidos por Hu e os momentos centrais para cada disco. A classificação do grau de degeneração foi realizada utilizando uma rede neural artificial e o conjunto de atributos extraídos de cada disco. Uma taxa média de acerto na classificação de 87%, com erro padrão de 6,59% e uma área média sob a curva ROC (Receiver Operating Characteristic) de 0,92 indicam o potencial de aplicação dos algoritmos desenvolvidos como ferramenta de apoio ao diagnóstico da degeneração do disco intervertebral. / The intervertebral disc is a structure whose function is to receive, absorb and transmit the impact loads imposed on the spine. Increasing age and the posture adopted by the individual can lead to degeneration of the intervertebral disc. Currently, Magnetic Resonance Imaging (MRI) is considered the best and most sensitive noninvasive method to imaging evaluation of the intervertebral disc. In this work were developed methods for quantitative computer-aided diagnosis of the intervertebral disc degeneration in MRI T2 weighted images of the lumbar column according to Pfirrmann scale, a semi-quantitative scale with five degrees of degeneration. The algorithms were tested on a dataset of 300 images obtained from 102 subjects with varying degrees of degeneration. Binary masks manually segmented of the discs were used to calculate their centroids, to create a reference point to enable extraction of attributes. A texture analysis was performed using the approach proposed by Haralick. For the shape characterization, invariant moments defined by Hu and central moments were also calculated for each disc. The rating of the degree of degeneration was performed using an artificial neural network and the set of extracted attributes of each disk. An average rate of correct classification of 87%, with standard error 6.59% and an average area under the ROC curve (Receiver Operating Characteristic) of 0.92 indicates the potential application of the algorithms developed as a diagnostic support tool to the degeneration of the intervertebral disc.

Submitted by Silvana Teresinha Dornelles Studzinski (sstudzinski) on 2015-05-04T17:25:43Z No. of bitstreams: 1 Rodrigo Morais.pdf: 5083865 bytes, checksum: 69563cc7178422ac20ff08fe38ee97de (MD5) / Made available in DSpace on 2015-05-04T17:25:43Z (GMT). No. of bitstreams: 1 Rodrigo Morais.pdf: 5083865 bytes, checksum: 69563cc7178422ac20ff08fe38ee97de (MD5) Previous issue date: 2013 / Nenhuma / A área de Mineração de Opiniões e Análise de Sentimentos surgiu da necessidade de processamento automatizado de informações textuais referentes a opiniões postadas na web. Como principal motivação está o constante crescimento do volume desse tipo de informação, proporcionado pelas tecnologia trazidas pela Web 2.0, que torna inviável o acompanhamento e análise dessas opiniões úteis tanto para usuários com pretensão de compra de novos produtos quanto para empresas para a identificação de demanda de mercado. Atualmente, a maioria dos estudos em Mineração de Opiniões e Análise de Sentimentos que fazem o uso de mineração de dados se voltam para o desenvolvimentos de técnicas que procuram uma melhor representação do conhecimento e acabam utilizando técnicas de classificação comumente aplicadas, não explorando outras que apresentam bons resultados em outros problemas. Sendo assim, este trabalho tem como objetivo uma investigação empírica e comparativa da aplicação do modelo clássico de Redes Neurais Artificiais (RNAs), o multilayer perceptron , no problema de Mineração de Opiniões e Análise de Sentimentos. Para isso, bases de dados de opiniões são definidas e técnicas de representação de conhecimento textual são aplicadas sobre essas objetivando uma igual representação dos textos para os classificadores através de unigramas. A partir dessa reresentação, os classificadores Support Vector Machines (SVM), Naïve Bayes (NB) e RNAs são aplicados considerandos três diferentes contextos de base de dados: (i) bases de dados balanceadas, (ii) bases com diferentes níveis de desbalanceamento e (iii) bases em que a técnica para o tratamento do desbalanceamento undersampling randômico é aplicada. A investigação do contexto desbalanceado e de outros originados dele se mostra relevante uma vez que bases de opiniões disponíveis na web normalmente apresentam mais opiniões positivas do que negativas. Para a avaliação dos classificadores são utilizadas métricas tanto para a mensuração de desempenho de classificação quanto para a de tempo de execução. Os resultados obtidos sobre o contexto balanceado indicam que as RNAs conseguem superar significativamente os resultados dos demais classificadores e, apesar de apresentarem um grande custo computacional para treinamento, proporcionam tempos de classificação significantemente inferiores aos do classificador que apresentou os resultados de classificação mais próximos aos dos resultados das RNAs. Já para o contexto desbalanceado, as RNAs se mostram sensíveis ao aumento de ruído na representação dos dados e ao aumento do desbalanceamento, se destacando nestes experimentos, o classificador NB. Com a aplicação de undersampling as RNAs conseguem ser equivalentes aos demais classificadores apresentando resultados competitivos. Porém, podem não ser o classificador mais adequado de se adotar nesse contexto quando considerados os tempos de treinamento e classificação, e também a diferença pouco expressiva de acerto de classificação. / The area of Opinion Mining and Sentiment Analysis emerges from the need for automated processing of textual information about reviews posted in the web. The main motivation of this area is the constant volume growth of such information, provided by the technologies brought by Web 2.0, that makes impossible the monitoring and analysis of these reviews that are useful for users, who desire to purchase new products, and for companies to identify market demand as well. Currently, the most studies of Opinion Mining and Sentiment Analysis that make use of data mining aims to the development of techniques that seek a better knowledge representation and using classification techniques commonly applied and they not explore others classifiers that work well in other problems. Thus, this work aims a comparative empirical research of the ap-plication of the classical model of Artificial Neural Networks (ANN), the multilayer perceptron, in the Opinion Mining and Sentiment Analysis problem. For this, reviews datasets are defined and techniques for textual knowledge representation applied to these aiming an equal texts rep-resentation for the classifiers. From this representation, the classifiers Support Vector Machines (SVM), Naïve Bayes (NB) and ANN are applied considering three data context: (i) balanced datasets, (ii) datasets with different unbalanced ratio and (iii) datasets with the application of random undersampling technique for the unbalanced handling. The unbalanced context inves-tigation and of others originated from it becomes relevant once datasets available in the web ordinarily contain more positive opinions than negative. For the classifiers evaluation, metrics both for the classification perform and for run time are used. The results obtained in the bal-anced context indicate that ANN outperformed significantly the others classifiers and, although it has a large computation cost for the training fase, the ANN classifier provides classification time (real-time) significantly less than the classifier that obtained the results closer than ANN. For the unbalanced context, the ANN are sensitive to the growth of noise representation and the unbalanced growth while the NB classifier stood out. With the undersampling application, the ANN classifier is equivalent to the others classifiers attaining competitive results. However, it can not be the most appropriate classifier to this context when the training and classification time and its little advantage of classification accuracy are considered.

Esta tese propõe uma metodologia de detecção de anomalias por meio da otimização da extração, seleção e classificação de características relacionadas ao tráfego de redes Real Time Ethernet (RTE). Em resumo, dois classificadores são treinados usando características que são extraídas do tráfego por meio da técnica de janela deslizante e posteriormente selecionadas de acordo com sua correlação com o evento a ser classificado. O número de características relevantes pode variar de acordo com os indicadores de desempenho de cada classificador. Reduzindo a dimensionalidade do evento a ser classificado com o menor número de características possíveis que o represente, são garantidos a redução do esforço computacional, ganho de tempo, dentre outros benefícios. Posteriormente, os classificadores são comparados em função dos indicadores de desempenho: acurácia, taxa de falsos positivos, taxa de falsos negativos, tempo de processamento e erro relativo. A metodologia proposta foi utilizada para identificar quatro diferentes eventos (três anomalias e o estado normal de operação) em redes PROFINET reais e com configurações distintas entre si; também foi aplicada em três eventos (duas anomalias e o estado normal de operação) em redes SERCOS III. O desempenho de cada classificador é analisado em suas particularidades e comparados com pesquisas correlatas. Por fim, é explorada a possibilidade de aplicação da metodologia proposta para outros protocolos baseados em RTE. / This thesis proposes an anomaly detection methodology by optimizing extraction, selection and classification of characteristics related to Real Time Ethernet (RTE) network traffic. In summary, two classifiers are trained using features which are extracted from network traffic through the sliding window technique and selected according to their correlation with the event being classified. The number of relevant characteristics could vary according to performance indicators of each classifier. Reducing the dimensionality of the event to be classified using the smallest number of characteristics which represent it, guarantees reduction in computational effort, processing time, among other benefits. The classifiers are compared according to performance indicators: accuracy, false positive rate, false negative rate, processing time and relative error. The proposed methodology was used to identify four different events (three anomalies and normal operation) in real PROFINET networks, using different configurations. It was also applied in 3 events (two anomalies and normal operation) in SERCOS III networks. The results obtained are analyzed in its particularities and compared with related research. Finally, the possibility of applying the proposed methodology for other protocols based on RTE is explored.

Artificial neural networks have been widely used for machine learning and optimization. A neuro ensemble is a collection of neural networks that works cooperatively on a problem. In the literature, it has been shown that by combining several neural networks, the generalization of the overall system could be enhanced over the separate generalization ability of the individuals. Evolutionary computation can be used to search for a suitable architecture and weights for neural networks. When evolutionary computation is used to evolve a neuro ensemble, it is usually known as evolutionary neuro ensemble. In most real-world problems, we either know little about these problems or the problems are too complex to have a clear vision on how to decompose them by hand. Thus, it is usually desirable to have a method to automatically decompose a complex problem into a set of overlapping or non-overlapping sub-problems and assign one or more specialists (i.e. experts, learning machines) to each of these sub-problems. An important feature of neuro ensemble is automatic problem decomposition. Some neuro ensemble methods are able to generate networks, where each individual network is specialized on a unique sub-task such as mapping a subspace of the feature space. In real world problems, this is usually an important feature for a number of reasons including: (1) it provides an understanding of the decomposition nature of a problem; (2) if a problem changes, one can replace the network associated with the sub-space where the change occurs without affecting the overall ensemble; (3) if one network fails, the rest of the ensemble can still function in their sub-spaces; (4) if one learn the structure of one problem, it can potentially be transferred to other similar problems. In this thesis, I focus on classification problems and present a systematic study of a novel evolutionary neuro ensemble approach which I call cooperative coevolutionary mixture of experts (CCME). Cooperative coevolution (CC) is a branch of evolutionary computation where individuals in different populations cooperate to solve a problem and their fitness function is calculated based on their reciprocal interaction. The mixture of expert model (ME) is a neuro ensemble approach which can generate networks that are specialized on different sub-spaces in the feature space. By combining CC and ME, I have a powerful framework whereby it is able to automatically form the experts and train each of them. I show that the CCME method produces competitive results in terms of generalization ability without increasing the computational cost when compared to traditional training approaches. I also propose two different mechanisms for visualizing the resultant decomposition in high-dimensional feature spaces. The first mechanism is a simple one where data are grouped based on the specialization of each expert and a color-map of the data records is visualized. The second mechanism relies on principal component analysis to project the feature space onto lower dimensions, whereby decision boundaries generated by each expert are visualized through convex approximations. I also investigate the regularization effect of learning by forgetting on the proposed CCME. I show that learning by forgetting helps CCME to generate neuro ensembles of low structural complexity while maintaining their generalization abilities. Overall, the thesis presents an evolutionary neuro ensemble method whereby (1) the generated ensemble generalizes well; (2) it is able to automatically decompose the classification problem; and (3) it generates networks with small architectures.

The electro-oculogram (EOG) is the most widely used technique for recording eye movements in clinical settings. It is inexpensive, practical, and non-invasive. Use of EOG is usually restricted to horizontal recordings as vertical EOG contains eyelid artefact (Oster & Stern, 1980) and blinks. The ability to analyse two dimensional (2D) eye movements may provide additional diagnostic information on pathologies, and further insights into the nature of brain functioning. Simultaneous recording of both horizontal and vertical EOG also introduces other difficulties into calibration of the eye movements, such as different gains in the two signals, and misalignment of electrodes producing crosstalk. These transformations of the signals create problems in relating the two dimensional EOG to actual rotations of the eyes. The application of an artificial neural network (ANN) that could map 2D recordings into 2D eye positions would overcome this problem and improve the utility of EOG. To determine whether ANNs are capable of correctly calibrating the saccadic eye movement data from 2D EOG (i.e. performing the necessary inverse transformation), the ANNs were first tested on data generated from mathematical models of saccadic eye movements. Multi-layer perceptrons (MLPs) with non-linear activation functions and trained with back propagation proved to be capable of calibrating simulated EOG data to a mean accuracy of 0.33° of visual angle (SE = 0.01). Linear perceptrons (LPs) were only nearly half as accurate. For five subjects performing a saccadic eye movement task in the upper right quadrant of the visual field, the mean accuracy provided by the MLPs was 1.07° of visual angle (SE = 0.01) for EOG data, and 0.95° of visual angle (SE = 0.03) for infrared limbus reflection (IRIS®) data. MLPs enabled calibration of 2D saccadic EOG to an accuracy not significantly different to that obtained with the infrared limbus tracking data.

本研究嘗試整合類神經網路與法則基礎（rule-based）系統技術，以建立S&P 500指數期貨的交易策略。本研究不同於先前研究之處有下列二方面：一、本研究採用法則基礎系統的方式提供神經網路的訓練範例；二、本研究以理解神經網路（Reasoning Neural Networks）取代後向傳導網路（Back propagation networks）以解決局部最小值與隱藏結點數未知的困境，而實證結果也顯示理解神經網路之表現優於後向傳導網路。首先，由期貨的日價格資料計算出十種技術分析指標值，用這些指標值來表示期貨市場內的各種可能狀況（case）。接著，我們提出FFM（Futures Forecast Model）與EFFM（Extended Futures Forecast Model）來處理市場的各種狀況，預測出隔日的期貨價格改變方向。以法則基礎方法所建立的FFM是用來處理明顯的狀況（obvious cases），並且提供類神經網路好的訓練範例。而EFFM包括四個理解神經網路系統與一個決策機置（voting mechanism），它被用來處理那些不明顯的狀況（non-obvious cases）。從實證模擬的結果顯示，在預測市場時FFM與EFFM有良好的合作 關係。因此，我們以FFM與EFFM為基礎建立一個整合的期貨交易系統（Integrated Futures Trading System，IFTS），並將它用於S&P 500 指數期貨市場作模擬交易，結果我們發現在1988到1993年的測試期間，IFTS 的投資報酬率高於買入持有投資策略。 / This research adopts a hybrid approach to implementing the trading strategies in the S&P 500 index futures market. The hybrid approach integrates both the rule-based systems technique and the neural networks technique. Our methodology is different from previous studies in two aspects. First, we employ Reasoning Neural Networks (RN) instead of back propagation networks to resolve the undesired predicaments of local minimum and the unknown of the number of hidden nodes. Second, the rule-based systems approach is applied to provide neural networks with good training examples. We, first, categorize the daily conditions of the futures market into a variety of cases through processing futures historical data. Then, the dual-forecast models, FFM (futures forecast model) and EFFM (extended futures forecast model), are proposed to predict the direction of daily price changes. The rule-based model, FFM, is designed to deal with the obvious cases and to provide the neural network-based model, EFFM, with good training examples. Meanwhile, EFFM, which consists of four RNs and a voting mechanism, is designed to handle the non-obvious cases. The simulation results show that the cooperation of FFM and EFFM does a good job in predicting the direction of daily price change of S&P 500 index futures. Based on FFM and EFFM, the integrated futures trading system (IFTS) is developed and employed to trade the S&P 500 index futures contracts. The results show that IFTS outperforms the passive buy-and-hold investment strategy over the six-year testing period from 1988 to 1993.

<p>A Real-Time Brain-Computer Interface is a technical system classifying increased or decreased brain activity in Real-Time between different body movements, actions performed by a person. Focus in this thesis will be on testing algorithms and settings, finding the initial time interval and how increased activity in the brain can be distinguished and satisfyingly classified. The objective is letting the system give an output somewhere within 250ms of a thought of an action, which will be faster than a persons reaction time. </p><p>Algorithms in the preprocessing were Blind Signal Separation and the Fast Fourier Transform. With different frequency and time interval settings the algorithms were tested on an offline Electroencephalographic data file based on the "Ten Twenty" Electrode Application System, classified using an Artificial Neural Network. </p><p>A satisfying time interval could be found between 125-250ms, but more research is needed to investigate that specific interval. A reduction in frequency resulted in a lack of samples in the sample window preventing the algorithms from working properly. A high frequency is therefore proposed to help keeping the sample window small in the time domain. Blind Signal Separation together with the Fast Fourier Transform had problems finding appropriate correlation using the Ten-Twenty Electrode Application System. Electrodes should be placed more selectively at the parietal lobe, in case of requiring motor responses.</p>

<p>The aim of this thesis was to test the capability of Artificial Neural Networks (ANN) to estimate respiratory mechanics during mechanical ventilation (MV). ANNs are universal function approximators and can extract information from complex signals. </p><p>We evaluated, in an animal model of acute lung injury, whether ANN can assess respiratory system resistance (R_RS) and compliance (C_RS) using the tracings of pressure at airways opening (P_AW), inspiratory flow (V’) and tidal volume, during an end-inspiratory hold maneuver (EIHM). We concluded that ANN can estimate C_RS and R_RS during an EIHM. We also concluded that the use of tracings obtained by non-biological models in the learning process has the potential of substituting biological recordings.</p><p>We investigated whether ANN can extract C_RS using tracings of P_AW and V’, without any intervention of an inspiratory hold maneuver during continuous MV. We concluded that C_RS can be estimated by ANN during volume control MV, without the need to stop inspiratory flow.</p><p>We tested whether ANN, fed by inspiratory P_AWand V’, are able to measure static total positive end-expiratory pressure (PEEP_tot,stat) during ongoing MV. In an animal model we generated dynamic pulmonary hyperinflation by shortening expiratory time. Different levels of external PEEP (PEEP_APP) were applied. Results showed that ANN can estimate PEEP_tot,stat reliably, without any influence from the level of PEEP_APP.</p><p>We finally compared the robustness of ANN and multi-linear fitting (MLF) methods in extracting C_RS when facing signals corrupted by perturbations. We observed that during the application of random noise, ANN and MLF maintain a stable performance, although in these conditions MLF may show better results. ANN have more stable performance and yield a more robust estimation of C_RS than MLF in conditions of transient sensor disconnection.</p><p>We consider ANN to be an interesting technique for the assessment of respiratory mechanics.</p>

The aim of this thesis was to test the capability of Artificial Neural Networks (ANN) to estimate respiratory mechanics during mechanical ventilation (MV). ANNs are universal function approximators and can extract information from complex signals. We evaluated, in an animal model of acute lung injury, whether ANN can assess respiratory system resistance (RRS) and compliance (CRS) using the tracings of pressure at airways opening (PAW), inspiratory flow (V’) and tidal volume, during an end-inspiratory hold maneuver (EIHM). We concluded that ANN can estimate CRS and RRS during an EIHM. We also concluded that the use of tracings obtained by non-biological models in the learning process has the potential of substituting biological recordings. We investigated whether ANN can extract CRS using tracings of PAW and V’, without any intervention of an inspiratory hold maneuver during continuous MV. We concluded that CRS can be estimated by ANN during volume control MV, without the need to stop inspiratory flow. We tested whether ANN, fed by inspiratory PAW and V’, are able to measure static total positive end-expiratory pressure (PEEPtot,stat) during ongoing MV. In an animal model we generated dynamic pulmonary hyperinflation by shortening expiratory time. Different levels of external PEEP (PEEPAPP) were applied. Results showed that ANN can estimate PEEPtot,stat reliably, without any influence from the level of PEEPAPP. We finally compared the robustness of ANN and multi-linear fitting (MLF) methods in extracting CRS when facing signals corrupted by perturbations. We observed that during the application of random noise, ANN and MLF maintain a stable performance, although in these conditions MLF may show better results. ANN have more stable performance and yield a more robust estimation of CRS than MLF in conditions of transient sensor disconnection. We consider ANN to be an interesting technique for the assessment of respiratory mechanics.