Made available in DSpace on 2016-08-17T14:53:04Z (GMT). No. of bitstreams: 1 Eduardo Werley Silva dos Angelos.pdf: 3115744 bytes, checksum: 6426e6a53fa69a9616988e00882cb314 (MD5) Previous issue date: 2009-08-07 / Conselho Nacional de Desenvolvimento Científico e Tecnológico / This work proposes a computational technique for classification of electricity consumption profiles. The approach is based on the assumption that it s possible to find out groups of consumers with similar patterns of energy use. So, given the found groups, which can be also viewed as a normal consumption profile, ones can associate a high chance of fraud or abnormality to that consumers lying more apart from the groups. The methodology comprises two steps. A fuzzy clustering c-means-based is done in order to search for consumers with similar consumption profiles, in the first one. Afterwards, a fuzzy classification is performed using a fuzzy membership matrix and the Euclidian distance to the cluster centers. Then, the distance measures are normalized and ordered, yielding an unitary index score, where the possible fraudulent or abnormal consumers are those with the higher scores. The approach was tested and validated with real data base, showing good performance in both fraud and metering defect detection tasks. / Este trabalho apresenta uma metodologia computacional para classificação de perfis anormais de consumo de energia elétrica. A abordagem parte da premissa que um dado cliente deve permanecer o mais próximo possível de seu padrão de consumo histórico, sendo que os desvios do padrão registrado representam possíveis fraudes de energia ou irregularidades de medição. A parte inicial da metodologia busca de consumidores com perfis de consumo semelhantes é efetuada por meio da técnica computacional de clusterização fuzzy. Já a tarefa de mensurar o desvio do padrão histórico é realizada por meio de uma metodologia de classificação nebulosa, baseada na matriz de partição fuzzy e distância dos elementos aos centros dos agrupamentos. Por fim, as distâncias para os grupos são normalizadas, gerando um índice no intervalo unitário, sendo que os elementos de maior chance de estarem irregular são aqueles com índices mais próximos de um. A metodologia foi validada com uma base de dados de uma concessionária local. Os resultados alcançados foram satisfatórios, sendo obtida adequada performance tanto no processo de detecção de fraudes quanto irregularidades na medição.

Made available in DSpace on 2016-08-17T14:53:19Z (GMT). No. of bitstreams: 1 dissertacao Joabe Amaral.pdf: 1492594 bytes, checksum: 667940ee64ccf9cbf29cbf0ed1db27a0 (MD5) Previous issue date: 2012-02-27 / Conselho Nacional de Desenvolvimento Científico e Tecnológico / In this dissertation, a robust fuzzy PID Takagi-Sugeno control methodology based on gain and phase margins specifications for dynamic systems with time delay in continuous time domain is proposed. A fuzzy model based on the Takagi-Sugeno structure is used to represent the dynamic system to be controlled. Thus, from the input and output data of the dynamic system, the Gustafson-Kessel fuzzy clustering algorithm is used to estimate the parameters of the antecedent proposition (input space) and the rules number of the fuzzy model, while the least mean squares algorithm is used to estimate the parameters of the sub-linear models of the consequent proposition (output space) of the fuzzy model. A mathematical formulation based on PDC (parallel and distributed compensation) strategy is defined from the gain and phase margins specifications for the calculation of PID controllers sub-parameters, in the robust fuzzy PID controller rule base, the linear sub-models parameters of the dynamic system model fuzzy rule base to be controlled. An analysis of necessary and sufficient conditions for robust fuzzy PID controller design, with the proposal of one axiom and two theorems are presented. Computational results to validation of the proposal compared to others control methods widely cited in the literature, with the application in the angular position control of a robotic manipulator, are also presented. / Nesta dissertação é proposta uma metodologia de controle PID nebuloso robusto baseado nas especificações das margens de ganho e fase, para sistemas dinâmicos com atraso, no domínio do tempo contínuo. Um modelo nebuloso com estrutura Takagi-Sugeno é utilizado para representar o sistema dinâmico a ser controlado. Assim, a partir dos dados de entrada e saída do sistema dinâmico, o algoritmo de agrupamento nebuloso Gustafson-Kessel é utilizado para estimar os parâmetros da proposição no antecedente (espaço de entrada) e o número de regras do modelo nebuloso, enquanto que o algoritmo de mínimos quadrados é utilizado para estimar os parâmetros dos sub-modelos lineares da proposição no consequente (espaço de saída) do modelo nebuloso. Uma formulação matemática fundamentada na estratégia de Compensação Paralela e Distribuída (PDC) é definida, a partir das especificações das margens de ganho e fase, para o cálculo dos parâmetros dos sub-controladores PID, na base de regras do controlador PID nebuloso robusto, em função dos parâmetros dos sub-modelos lineares na base de regras do modelo nebuloso do sistema dinâmico a ser controlado. Uma análise das condições necessárias e suficientes de projeto do controlador PID nebuloso robusto, com a proposta de um axioma e dois teoremas, são apresentados. Resultados computacionais para a validação da metodologia proposta comparada a dois métodos de controle nebuloso propostos por Teixeira e Zak (1999) e Wang, Tanaka e Griffin (1996), amplamente utilizados na literatura, com aplicação ao problema de controle de posição angular de um manipulador robótico, também são apresentados.

Orientadores: Fernando Antonio Campos Gomide, Rosangela Ballini / Dissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Engenharia Eletrica e de Computação / Made available in DSpace on 2018-08-12T14:32:10Z (GMT). No. of bitstreams: 1 Lima_EltonMariode_M.pdf: 1259231 bytes, checksum: 7a910e84bfb43d6c13b2deb8b6f511c2 (MD5) Previous issue date: 2008 / Resumo: Este trabalho propõe um modelo fuzzy funcional evolutivo que utiliza uma aplicação do aprendizado participativo para a construção de uma base de regras. O aprendizado participativo é um modelo de aprendizado baseado na noção de compatibilidade para a atualização do conhecimento do sistema. O aprendizado participativo pode ser traduzido em um algoritmo de agrupamento não supervisionado conhecido como agrupamento participativo. O algoritmo intitulado Aprendizado Participativo Evolutivo é proposto para construir um modelo fuzzy funcional evolutivo no qual as regras são obtidas a partir de um algoritmo de agrupamento não supervisionado. O algoritmo utiliza uma versão do agrupamento participativo para a determinação de uma base de regras correspondente ao modelo funcional do tipo Takagi-Sugeno evolutivo. A partir de uma noção generalizada, o modelo proposto é aplicado em problemas de previsão de séries temporais e os resultados são obtidos para a conhecida série Box-Jenkis, além da previsão de uma série de carga horária de energia elétrica. Os resultados são comparados com o modelo Takagi-Sugeno evolutivo que utiliza a noção de função potencial para agrupar os dados dinâmicamente e com duas abordagens baseadas em redes neurais. Os resultados mostram que o modelo proposto é eficiente e parcimonioso, abrindo potencial para aplicações e estudos futuros. / Abstract: This work introduces an approach to develop evolving fuzzy rule-based models using participatory learning. Participatory learning assumes that learning and beliefs about a system depend on what the learning mechanism knows about the system itself. Participatory learning naturally augments clustering and yields an e_ective unsupervised fuzzy clustering algorithms for on-line, real time domains and applications. Clustering is an essential step to construct evolving fuzzy models and plays a key role in modeling performance and model quality. A least squares recursive approach to estimate the consequent parameters of the fuzzy rules for on-line modeling is emphasized. Experiments with the classic Box-Jenkins benchmark are conducted to compare the performance of the evolving participatory learning with the evolving fuzzy system modeling approach and alternative fuzzy modeling and neural methods. The experiments show the e_ciency of evolving participatory learning to handle the benchmark problem. The evolving participatory learning method is also used to forecast the average hourly load of an electric generation plant and compared against the evolving fuzzy system modeling using actual data. The results confirm the potential of the evolving fuzzy participatory method to solve real world modeling problems. / Mestrado / Automação Industrial / Mestre em Engenharia Elétrica

Building an accurate and reliable model for prediction for different application domains, is one of the most significant challenges in knowledge discovery and data mining. This thesis focuses on building and enhancing a generic predictive model for estimating a future value by extracting association rules (knowledge) from a quantitative database. This model is applied to several data sets obtained from different benchmark problems, and the results are evaluated through extensive experimental tests. The thesis presents an incremental development process for the prediction model with three stages. Firstly, a Knowledge Discovery (KD) model is proposed by integrating Fuzzy C-Means (FCM) with Apriori approach to extract Fuzzy Association Rules (FARs) from a database for building a Knowledge Base (KB) to predict a future value. The KD model has been tested with two road-traffic data sets. Secondly, the initial model has been further developed by including a diversification method in order to improve a reliable FARs to find out the best and representative rules. The resulting Diverse Fuzzy Rule Base (DFRB) maintains high quality and diverse FARs offering a more reliable and generic model. The model uses FCM to transform quantitative data into fuzzy ones, while a Multiple Support Apriori (MSapriori) algorithm is adapted to extract the FARs from fuzzy data. The correlation values for these FARs are calculated, and an efficient orientation for filtering FARs is performed as a post-processing method. The FARs diversity is maintained through the clustering of FARs, based on the concept of the sharing function technique used in multi-objectives optimization. The best and the most diverse FARs are obtained as the DFRB to utilise within the Fuzzy Inference System (FIS) for prediction. The third stage of development proposes a hybrid prediction model called Fuzzy Associative Classification Rule Mining (FACRM) model. This model integrates the ii improved Gustafson-Kessel (G-K) algorithm, the proposed Fuzzy Associative Classification Rules (FACR) algorithm and the proposed diversification method. The improved G-K algorithm transforms quantitative data into fuzzy data, while the FACR generate significant rules (Fuzzy Classification Association Rules (FCARs)) by employing the improved multiple support threshold, associative classification and vertical scanning format approaches. These FCARs are then filtered by calculating the correlation value and the distance between them. The advantage of the proposed FACRM model is to build a generalized prediction model, able to deal with different application domains. The validation of the FACRM model is conducted using different benchmark data sets from the University of California, Irvine (UCI) of machine learning and KEEL (Knowledge Extraction based on Evolutionary Learning) repositories, and the results of the proposed FACRM are also compared with other existing prediction models. The experimental results show that the error rate and generalization performance of the proposed model is better in the majority of data sets with respect to the commonly used models. A new method for feature selection entitled Weighting Feature Selection (WFS) is also proposed. The WFS method aims to improve the performance of FACRM model. The prediction performance is improved by minimizing the prediction error and reducing the number of generated rules. The prediction results of FACRM by employing WFS have been compared with that of FACRM and Stepwise Regression (SR) models for different data sets. The performance analysis and comparative study show that the proposed prediction model provides an effective approach that can be used within a decision support system. / Applied Science University (ASU) of Jordan

Η ραγδαία ανάπτυξη που παρουσιάστηκε τα τελευταία χρόνια σε διάφορους τομείς της πληροφορικής με την αύξηση της ισχύος επεξεργασίας και της δυνατότητας αποθήκευσης ενός τεράστιου όγκου δεδομένων έδωσε νέα ώθηση στον τομέα διαχείρισης, αναζήτησης, σύνοψης και εξαγωγής της πληροφορίας από ένα βίντεο. Για την διαχείριση αυτής της πληροφορίας αναπτύχθηκαν τεχνικές περίληψης βίντεο. Η περίληψη ενός βίντεο υπό μορφή μιας στατικής ακολουθίας χαρακτηριστικών καρέ, μειώνει τον απαραίτητο όγκο της πληροφορίας που απαιτείται σε συστήματα αναζήτησης, ενώ διαμορφώνει την βάση για την αντιμετώπιση του σημασιολογικού περιεχομένου του σε εφαρμογές ανάκτησης. Το ερευνητικό αντικείμενο της παρούσας διδακτορικής διατριβής αναφέρεται σε τεχνικές αυτόματης περίληψης βίντεο με χρήση της θεωρίας γράφων, για την ανάπτυξη μη επιβλεπόμενων αλγόριθμων ομαδοποίησης. Κάθε καρέ της ακολουθίας του βίντεο δεν αντιμετωπίζεται ως ένα διακριτό στοιχείο, αλλά λαμβάνεται υπόψη ο βαθμός συσχέτισης μεταξύ τους. Με αυτόν τον τρόπο το πρόβλημα της ομαδοποίησης ανάγεται από μια τυπική διαδικασία αναγνώρισης ομάδων σε ένα σύστημα ανάλυσης της δομής που περιέχεται στο σύνολο των δεδομένων. Ακόμη παρουσιάζεται μια νέα τεχνική βελτίωσης του βαθμού ομοιότητας των καρέ, η οποία βασίζεται στο θεωρητικό φορμαλισμό τεχνικών ημί-επιβλεπόμενης εκμάθησης, με χρήση όμως αλγόριθμων δυναμικής συμπίεσης, για την αναπαράσταση του οπτικού περιεχομένου τους. Τα αναλυτικά πειραματικά αποτελέσματα που παρατίθενται, αποδεικνύουν την βελτίωση της απόδοσης των προτεινόμενων μεθόδων σε σχέση με γνωστές τεχνικές περίληψης. Τέλος, προτείνονται κάποιες μελλοντικές κατευθύνσεις έρευνας στο αντικείμενο που πραγματεύεται η παρούσα διατριβή, με άμεσες επεκτάσεις στο πεδίο ανάκτησης εικόνας και βίντεο. / The rapid development witnessed in the recent years enabling the storage and processing of a huge amount of data, in various fields of computer technology and image/video understanding, has given new impetus to the field of video manipulation, browsing, indexing, and retrieval. Video summarization, as a static sequence of key frames, reduces the amount of information required for video searching, while provides the basis for understanding the semantic content in video retrieval applications. The research subject of this doctoral thesis is the incorporation of graph theory and unsupervised clustering algorithms in Automatic Video Summarization applications of large video sequences. In this context, every frame from a video sequence is not processed as a discrete element, but the relations between the frames are considered. Thus, the clustering problem is transformed from a typical computation procedure, to the problem of data structure analysis. Detailed experimental results demonstrate the performance improvement provided by the proposed methods in comparison with well-known video summarization techniques from the literature. Finally, future research directions are proposed, directly applicable to the fields of image and video retrieval.

台灣在過去的數十年內，罹患失智症人口逐漸增多，其中的多數皆有接受了各層面的照護，舉凡藥物治療、醫護治療、復健治療以及職能治療，然其中的成效與需求之研究仍相當缺乏。故本研究採以質性與量性研究方法，以便於探索目前失智症患者家屬照護時所面臨的實際抉擇歷程與主要需求，並同時探索個案醫院內的治療效果與病患入院時狀況之關係，本研究希望藉由中部地區失智症病患照護的需求及機構之供給的角度來探索研究所能增進其醫療服務品質之處。 在質性研究方法部分，本研究以民族誌決策樹研究法來洞悉與探索家屬在面臨照護失智症病患時是否要採行機構式照護的決策歷程以及決策條件。藉由深度訪談結果粹取出的判斷準則發現，影響家屬決策之最主要考量為失智症病患者的失智程度，其餘包含道德規範、照護負擔、病患是否需要騎他的專業醫療照護以及照護中心的軟硬體環境。本研究整合考量這些判斷準則的優先順序、輕重緩急以及因果關係後將之建立決策樹，並以另外五十名家屬驗證該模型之預測力，得到預測準確率為92%。 此外，本研究再以量性方法來探索治療對於不同失智症病患的成效。結果顯示入住時狀況較好的失智症住民會以更積極的態度來接受職能治療，也因此他們擁有較大的改善或控制病情的機會，然而當住民以消極的態度接受職能治療時，則其治療效果遠不及積極治療者，也因此病情退步的機會較大，主要原因在於多數情況較差的住民具有攻擊、抗拒治療的傾向，使得照護工作變得更為艱鉅，故本研究建議家屬應重視職能治療以及與病人互動之重要性，不論是在居家照護亦或是機構式照護 / Over the past decade, the number of long-term care (LTC) residents has increased, and many have accepted treatments such as medication, rehabilitation and occupational therapy. This study employs both qualitative and quantitative techniques in order to discuss senile dementia patient care in long-term care institutions, and we use a supply and demand viewpoint to explore what services are really necessary for the patient and their family. In qualitative method, the main purpose of this stage is to use the ethnographic decision tree model to understand and explore the decision criteria of the subject. Our study found that the degree of dementia of the patient always affects the decisions made by family members – in fact, this is the most important of all criteria elicited from the interviews with family members. There are also ethical constraints, care burden, norm of filial obligation, patient need professional medical care and institutional environment, etc. which mentioned by families. We linked together the decision criteria considered most important in accounting for the decision-making sequence of family members to be the ethnographic decision tree model which predictive power is 92%. In quantitative stage, our study discussed the effectiveness of occupational therapy when given to dementia patients of different contexts. The results of this stage showed that patients of a good condition in the first stage present a more positive attitude towards participation in the occupational therapy designed by the institution; therefore, they have a greater chance of their condition improving or remaining the same. However, patients of an average condition have a more passive attitude towards taking part in any therapy; therefore, they have a greater chance of their condition deteriorating, because of their violent tendencies and their resistance to care, the task of caring for these patients is more difficult than caring for patients in the other groups. Above all, we suggest that families adopt the therapies no matter in homecare or institutionalization, as early as possible in order to improve the likelihood of being able to control the patient’s condition. It is understandable that accepting more therapies and interaction in the early stage of dementia, having higher chance to go well, however, by waiting until then they also miss the best opportunity to attempt to improve the patient’s condition, it is really not the good way we suggest to be.

Current studies of the highly complex pathobiology and molecular signatures of human disease require the analysis of large sets of high-throughput data, from clinical to genetic expression experiments, containing a wide range of information types. A number of computational techniques are used to analyse such high-dimensional bioinformatics data. In this thesis we focus on the development of a novel soft clustering technique, DifFUZZY, a fuzzy clustering algorithm applicable to a larger class of problems than other soft clustering approaches. This method is better at handling datasets that contain clusters that are curved, elongated or are of different dispersion. We show how DifFUZZY outperforms a number of frequently used clustering algorithms using a number of examples of synthetic and real datasets. Furthermore, a quality measure based on the diffusion distance developed for DifFUZZY is presented, which is employed to automate the choice of its main parameter. We later apply DifFUZZY and other techniques to data from a clinical study of children from The Gambia with different types of severe malaria. The first step was to identify the most informative features in the dataset which allowed us to separate the different groups of patients. This led to us reproducing the World Health Organisation classification for severe malaria syndromes and obtaining a reduced dataset for further analysis. In order to validate these features as relevant for malaria across the continent and not only in The Gambia, we used a larger dataset for children from different sites in Sub-Saharan Africa. With the use of a novel network visualisation algorithm, we identified pathobiological clusters from which we made and subsequently verified clinical hypotheses. We finish by presenting conclusions and future directions, including image segmentation and clustering time-series data. We also suggest how we could bridge data modelling with bioinformatics by embedding microarray data into cell models. Towards this end we take as a case study a multiscale model of the intestinal crypt using a cell-vertex model.

Submitted by Maria Aparecida (cidazen@gmail.com) on 2017-08-24T11:30:17Z No. of bitstreams: 1 Fernanda Lima.pdf: 9275191 bytes, checksum: 7f56bba066e97503f4da03ab7ab861c9 (MD5) / Made available in DSpace on 2017-08-24T11:30:17Z (GMT). No. of bitstreams: 1 Fernanda Lima.pdf: 9275191 bytes, checksum: 7f56bba066e97503f4da03ab7ab861c9 (MD5) Previous issue date: 2015-08-31 / A fuzzy project Takagi-Sugeno (TS) with robust stability based on the specifications of the gain and phase margins via multi-objective genetic algorithm in continuos time domain is proposed in this master thesis. A Fuzzy C-means (FCM) clustering algorithm is used to estimate the antecedent parameters and rules number of a fuzzy TS model by means of the input and output experimental data of the plant to be controlled, while minimum squares algorithm estimate the consequent parameters. A multi-objective genetic strategy is defined to adjust the parameters of a fuzzy PID controller, so that, the gain and phase margins of the fuzzy control system are close to the specified values. Two theorems are proposed to analyse the necessary and sufficient conditions for the fuzzy PID controller design to ensure the robust stability in the close-loop control. The fuzzy PID controller was simulated in the Simulink environment and compared with lead and delay compensator. Experimental results obtained in a control platform in real time to validation the methodology proposed are presented and compared with fuzzy PID controller obtained by the Ziegler Nichols method. The results demonstrate the effectiveness and practical feasibility of the proposed methodology. / Um projeto de controle nebuloso Takagi-Sugeno(TS) com estabilidade robusta baseado nas especificações das margens de ganho e fase via algoritmo genético multiobjetivo no domínio do tempo contínuo é proposto nesta dissertação. Um algoritmo de agrupamento Fuzzy C-Means (FCM) é usado para estimar os parâmetros do antecedente e o número da regras de um modelo nebuloso TS, por meio dos dados experimentais de entrada e de saída da planta a ser controlada, enquanto que o algoritmo de mínimos quadrados estima os parâmetros do consequente. Uma estratégia genética multiobjetiva é definida para ajustar os parâmetros de um controlador PID nebuloso, de modo que, as margens de ganho e fase do sistema de controle nebuloso estejam próximos dos valores especificados. São propostos dois teoremas que analisam as condições necessárias e suficientes para o projeto do controlador PID nebuloso de modo a garantir a estabilidade robusta na malha de controle. O controlador PID nebuloso foi simulado no ambiente Simulink e comparado com compensadores de avanço e de atraso e os resultados analisados. Resultados experimentais obtidos em uma plataforma de controle, em tempo real, para validação da metodologia proposta são apresentados e comparado com controlador PID nebuloso obtido pelo método de Ziegler Nichols. Os resultados obtidos demonstram a eficácia e viabilidade prática da metodologia proposta.

模糊理論開始於 1960 年代中期,關於這方面的研究與發展均已獲得相當不錯的成果.其中尤以在群落分析應用上的專題研究更是廣泛.Bezdek 提出的模糊分類演算法,乃根據 Dunn 的C平均法所作的一改良方法.但仍有其缺點,例如,未考慮權重且以靜態資料為主. 有鑑於此,本研究對 Bezdek 之方法加以改進推廣,提出加權模糊分類法.對於評價因素為多變量時,應加入模糊權重的考量.此外更結合時間因素,使準則函數成為動態的模式,將傳統的模糊分類法由靜態資料轉為動態資料形式,以反映真實 的情況. / Research on the theory of fuzzy sets has been growing steadily since itsinception during the mid-1960s. The literature especially dealing with fuzzycluster analysis is quite extensive. But the research on FCM still has somedisadvantages. For instance, the

在一般的研究過程中均可能有離群觀測值產生，只要有離群觀測值存在， 就可能對研究結果產生極重大的影響。在統計學上常用的參數估計式中， 有許多極易受離群觀測值影響。因此本研究採用模糊族群分析混合最大概 似估計演算法運用在參數估計上，以去除離群觀測值對分析結果的影響。 本研究主要針對相關係數與迴歸係數的估計進行探討，利用演算法中所求 得之隸屬度，計算穩健相關係數和穩健迴歸係數，以期能正確估計參數值 。