[pt] A maioria dos laboratórios não conta com um sistema informatizado para gestão dos procedimentos pertinentes a cada caso. A administração e controle das amostras é feito manualmente, através de diversas fichas que são preenchidas desde o colhimento do material biológico, no hospital, até a identificação final da bactéria no laboratório. Dessa forma, a organização das informações fica limitada, uma vez que, estando as informações escritas à mão e guardadas em livros, é quase impossível a extração de conhecimento útil que possa servir não só no apoio à decisão, como também, na formulação de simples estatísticas. Esta dissertação teve dois objetivos principais. O desenvolvimento de um sistema Web, intitulado BCIWeb (Bacterial Classification and Identification for Web), que fosse capaz de auxiliar na identificação bacteriológica e prover a tecnologia necessária para a administração e controle de amostras clínicas oriundas de hospitais. E a descoberta de conhecimento na base de dados do sistema, através da mineração de dados utilizando os métodos de Mapas Auto-Organizáveis (SOM: Self-Organizing Maps) e Redes Multilayer Perceptrons (MLP) para classificação e identificação de bactérias. A partir do desenvolvimento desta ferramenta amigável, no estudo de caso, os dados históricos do LDCIC (Laboratório de Difteria e Corinebactérias de Importância Clínica) do Departamento de Biologia da UERJ foram inseridos no sistema. Os métodos inteligentes propostos para classificação e identificação de bactérias foram analisados e apresentaram resultados promissores na área. / [en] Most laboratories do not have a computerized system for management procedures. The administration and control of the samples are made manualy through many forms of data sheets which are filled from the beginning, when the samples of biological materials are gathered at the hospital, up to the final identification at the laboratory. In this context, the organization of the information become very limited, while the information writting by hands and stored in books, its almost impossible to extract useful knowledge, which could help not only supporting decisions but also in the formulations of simples statistics. This thesis had two objectives. The development of a web system called BCIWeb (Bacterial Classifiation and Identification for Web) that could assist in bacterial identification and provide the technology necessary for the administration and control of clinical specimen coming from the hospitals and the discovery of knowledge in database system, through data mining methods using SOM (Self Organizing Maps) and Multilayer Perceptron Neural Networks (MLP) for classification and identificatin of bactéria. From the development of this friendly tool, in the case study, the historical data from LDCIC (Laboratório de Difteria e Corinebactérias de Importância Clínica) of UERJ Biology Department were entered into the system. The proposed intelligent methods for classification and identification of bacteria were analysed and showed promising results.

This paper deals with application of neural networks in image segmentation. First part is an introduction to image processing and neural networks, second part describes an implementation of segmentation system and presents results of experiments. The segmentation system enables to use different types of classifiers, various image features extraction and also to evaluate the success of segmentation. Two classifiers were created - a neural network (self-organizing map) and an algorithm K-means. Colour (RGB and HSV) and texture features and their combinations were used for classification. Texture features were extracted using a set of Gabor filters. Experiments with designed classifiers and feature extractors were carried out and results were compared.

Recognition of handwritten digits is a problem, which could serve as model task for multiclass recognition of image patterns. This thesis studies different kinds of algoritms (Self-Organizing Maps, Randomized tree and AdaBoost) and methods for increasing accuracy using fusion (majority voting, averaging log likelihood ratio, linear logistic regression). Fusion methods were used for combine classifiers with indentical train parameters, with different training methods and with multiscale input.

In today's society, companies are trying to find ways to utilize all the data they have, which considers valuable information and insights to make better decisions. This includes data used to keeping track of timber that flows between forest and industry. The growth of Artificial Intelligence (AI) and Machine Learning (ML) has enabled the development of ML modes to automate the measurements of timber on timber trucks, based on images. However, to improve the results there is a need to be able to get information from unlabeled images in order to decide weather and lighting conditions. The objective of this study is to perform an extensive for classifying unlabeled images in the categories, daylight, darkness, and snow on the load. A comparative study between partitional clustering and competitive learning is conducted to investigate which method gives the best results in terms of different clustering performance metrics. It also examines how dimensionality reduction affects the outcome. The algorithms K-means and Kohonen Self-Organizing Map (SOM) are selected for the clustering. Each model is investigated according to the number of clusters, size of dataset, clustering time, clustering performance, and manual samples from each cluster. The results indicate a noticeable clustering performance discrepancy between the algorithms concerning the number of clusters, dataset size, and manual samples. The use of dimensionality reduction led to shorter clustering time but slightly worse clustering performance. The evaluation results further show that the clustering time of Kohonen SOM is significantly higher than that of K-means.

Following the significant transition from the traditional production industry to an informationbased economy, the telecommunications industry was faced with an explosion of innovation, resulting in a continuous change in user behaviour. The industry has made efforts to adapt to a more datadriven future, which has given rise to larger and more complex systems. Therefore, troubleshooting systems such as anomaly detection and root cause analysis are essential features for maintaining service quality and facilitating daily operations. This study aims to explore the possibilities, benefits, and drawbacks of implementing cluster analysis for anomaly detection in hybrid fibercoaxial networks. Based on the literature review on unsupervised anomaly detection and an assumption regarding the anomalous behaviour in hybrid fibercoaxial network data, the kmeans, SelfOrganizing Map, and Gaussian Mixture Model were implemented both with and without Principal Component Analysis. Analysis of the results demonstrated an increase in performance for all models when the Principal Component Analysis was applied, with kmeans outperforming both SelfOrganizing Map and Gaussian Mixture Model. On this basis, it is recommended to apply Principal Component Analysis for clusteringbased anomaly detection. Further research is necessary to identify whether cluster analysis is the most appropriate unsupervised anomaly detection approach. / Följt av övergången från den traditionella tillverkningsindustrin till en informationsbaserad ekonomi stod telekommunikationsbranschen inför en explosion av innovation. Detta skifte resulterade i en kontinuerlig förändring av användarbeteende och branschen tvingades genomgå stora ansträngningar för att lyckas anpassa sig till den mer datadrivna framtiden. Större och mer komplexa system utvecklades och således blev felsökningsfunktioner såsom anomalidetektering och rotfelsanalys centrala för att upprätthålla servicekvalitet samt underlätta för den dagliga driftverksamheten. Syftet med studien är att utforska de möjligheterna, för- samt nackdelar med att använda klusteranalys för anomalidetektering inom HFC- nätverk. Baserat på litteraturstudien för oövervakad anomalidetektering samt antaganden för anomalibeteenden inom HFC- data valdes algritmerna k- means, Self- Organizing Map och Gaussian Mixture Model att implementeras, både med och utan Principal Component Analysis. Analys av resultaten påvisade en uppenbar ökning av prestanda för samtliga modeller vid användning av PCA. Vidare överträffade k- means, både Self- Organizing Maps och Gaussian Mixture Model. Utifrån resultatanalysen rekommenderas det således att PCA bör tillämpas vid klusterings- baserad anomalidetektering. Vidare är ytterligare forskning nödvändig för att avgöra huruvida klusteranalys är den mest lämpliga metoden för oövervakad anomalidetektering.

Financial reporting fraud leads to not only significant investment risks for external stockholders, but also financial crises for the capital market. Although the issue of fraudulent financial reporting has drawn much attention, relevant research is much less than issues of predicting financial distress or bankruptcy. Furthermore, one purpose of exploring the financial reporting fraud with various forms is to obtain a better understand of the corporate through investigating its financial and corporate governance indicators. This study addresses the challenge with proposing an approach with the following four phases: (1) to identify a set of financial and corporate governance indicators that are significantly correlated with the financial reporting fraud; (2) to use the Growing Hierarchical Self-Organizing Map (GHSOM) to cluster the normal and fraud listed corporate data; (3) to extract knowledge about the financial reporting fraud through observing the hierarchical relationship displayed in the trained GHSOM; and (4) to make the justification of the extracted knowledge. The proposed approach is feasible because researchers claim that the GHSOM can discover the hidden hierarchical relationship from data with high dimensionality.

Neste trabalho, um novo enfoque para detecção e diagnóstico de falhas (DDF) em robôs manipuladores é apresentado. Um robô com falhas pode causar sérios danos e pode colocar em risco o pessoal presente no ambiente de trabalho. Geralmente, os pesquisadores têm proposto esquemas de DDF baseados no modelo matemático do sistema. Contudo, erros de modelagem podem ocultar os efeitos das falhas e podem ser uma fonte de alarmes falsos. Aqui, duas redes neurais artificiais são utilizadas em um sistema de DDF para robôs manipuladores. Um perceptron multicamadas treinado por retropropagação do erro é usado para reproduzir o comportamento dinâmico do manipulador. As saídas do perceptron são comparadas com as variáveis medidas, gerando o vetor de resíduos. Em seguida, uma rede com função de base radial é usada para classificar os resíduos, gerando a isolação das falhas. Quatro algoritmos diferentes são empregados para treinar esta rede. O primeiro utiliza regularização para reduzir a flexibilidade do modelo. O segundo emprega regularização também, mas ao invés de um único termo de penalidade, cada unidade radial tem um regularização individual. O terceiro algoritmo emprega seleção de subconjuntos para selecionar as unidades radiais a partir dos padrões de treinamento. O quarto emprega o mapa auto-organizável de Kohonen para fixar os centros das unidades radiais próximos aos centros dos aglomerados de padrões. Simulações usando um manipulador com dois graus de liberdade e um Puma 560 são apresentadas, demostrando que o sistema consegue detectar e diagnosticar corretamente falhas que ocorrem em conjuntos de padrões não-treinados. / In this work, a new approach for fault detection and diagnosis in robotic manipulators is presented. A faulty robot could cause serious damages and put in risk the people involved. Usually, researchers have proposed fault detection and diagnosis schemes based on the mathematical model of the system. However, modeling errors could obscure the fault effects and could be a false alarm source. In this work, two artificial neural networks are employed in a fault detection and diagnosis system to robotic manipulators. A multilayer perceptron trained with backpropagation algorithm is employed to reproduce the robotic manipulator dynamical behavior. The perceptron outputs are compared with the real measurements, generating the residual vector. A radial basis function network is utilized to classify the residual vector, generating the fault isolation. Four different algorithms have been employed to train this network. The first utilizes regularization to reduce the flexibility of the model. The second employs regularization too, but instead of only one penalty term, each radial unit has a individual penalty term. The third employs subset selection to choose the radial units from the training patterns. The forth algorithm employs the Kohonen’s self-organizing map to fix the radial unit center near to the cluster centers. Simulations employing a two link manipulator and a Puma 560 manipulator are presented, demonstrating that the system can detect and isolate correctly faults that occur in nontrained pattern sets.

No description available.

This research created a new theoretical Soft Computing (SC) hybridized network intrusion detection diagnostic system including complex hybridization of a 3D full color Self-Organizing Map (SOM), Artificial Immune System Danger Theory (AISDT), and a Fuzzy Inference System (FIS). This SOM+ diagnostic archetype includes newly defined intrusion types to facilitate diagnostic analysis, a descriptive computational model, and an Invisible Mobile Network Bridge (IMNB) to collect data, while maintaining compatibility with traditional packet analysis. This system is modular, multitaskable, scalable, intuitive, adaptable to quickly changing scenarios, and uses relatively few resources.

The strong variation in carbonate content of the geological formations in the basin of Sprimont, Belgium, implies different groundwater behaviours in the substratum. The existence of carbonated materials such as limestone is responsible for the existence of a well-developed karstic system restricted to the Carboniferous materials which has a strong impact on the local hydrology and hydrogeology. Surface streams lose through local sinkholes to resurface at the spring of Trou Bleu, the only outlet of the basin and the drainage point of local aquifers. The study focuses on the assessment of existing links between surface losing streams and the spring, and on the tracing of any anthropogenic contamination, by using hydrochemical parameters (major ions, nitrogen forms, organic carbon…), isotopic compositions (δ15N-NO3, δ18O-NO3 and δ11B), pharmaceutical substances (caffeine, paracetamol…) and natural fluorescence as tools. Results strongly support each other regarding evidences of sewage contamination and agriculture and livestock farming waste occurrence in the basin, while reflecting the strong heterogeneity of landuse as observed on-site. Previous knowledge on hydrological dynamics is supported by collected data and reinforced by stream-by-stream discussions and estimate of the relative contribution of each surface streams to the spring water composition. / Erasmus+ traineeship at University of Liège