Data mining approaches have been increasingly used in recent years in order to find patterns and regularities in large databases. In this study, the C4.5 decision tree approach was used for mining of Gene Logic database, containing biological data. The decision tree approach was used in order to identify the most relevant genes and risk factors involved in breast cancer, in order to separate healthy patients from breast cancer patients in the data sets used. Four different tests were performed for this purpose. Cross validation was performed, for each of the four tests, in order to evaluate the capacity of the decision tree approaches in correctly classifying ‘new’ samples. In the first test, the expression of 108 breast related genes, shown in appendix A, for 75 patients were used as input to the C4.5 algorithm. This test resulted in a decision tree containing only four genes considered to be the most relevant in order to correctly classify patients. Cross validation indicates an average accuracy of 89% in classifying ‘new’ samples. In the second test, risk factor data was used as input. The cross validation result shows an average accuracy of 87% in classifying ‘new’ samples. In the third test, both gene expression data and risk factor data were put together as one input. The cross validation procedure for this approach again indicates an average accuracy of 87% in classifying ‘new’ samples. In the final test, the C4.5 algorithm was used in order to indicate possible signalling pathways involving the four genes identified by the decision tree based on only gene expression data. In some of cases, the C4.5 algorithm found trees suggesting pathways which are supported by the breast cancer literature. Since not all pathways involving the four putative breast cancer genes are known yet, the other suggested pathways should be further analyzed in order to increase their credibility. In summary, this study demonstrates the application of decision tree approaches for the identification of genes and risk factors relevant for the classification of breast cancer patients

Este trabalho descreve experimentos realizados com Redes Neurais Artificiais e algoritmos de aprendizado simbólico. Também são investigados dois algoritmos de extração de conhecimento de Redes Neurais Artificiais. Esses experimentos são realizados com três bases de dados com o objetivo de comparar os desempenhos obtidos. As bases de dados utilizadas neste trabalho são: dados de falência de bancos brasileiros, dados do jogo da velha e dados de análise de crédito. São aplicadas sobre os dados três técnicas para melhoria de seus desempenhos. Essas técnicas são: partição pela menor classe, acréscimo de ruído nos exemplos da menor classe e seleção de atributos mais relevantes. Além da análise do desempenho obtido, também é feita uma análise da dificuldade de compreensão do conhecimento extraído por cada método em cada uma das bases de dados. / This work describes experiments carried out witch Artificial Neural Networks and symbolic learning algorithms. Two algorithms for knowledge extraction from Artificial Neural Networks are also investigates. This experiments are performed whit three data set with the objective of compare the performance obtained. The data set used in this work are: Brazilians banks bankruptcy data set, tic-tac-toe data set and credit analysis data set. Three techniques for data set performance improvements are investigates. These techniques are: partition for the smallest class, noise increment in the examples of the smallest class and selection of more important attributes. Besides the analysis of the performance obtained, an analysis of the understanding difficulty of the knowledge extracted by each method in each data bases is made.

This diploma thesis presents description on several algorithms for decision trees induction and software RapidMiner. The first part of the thesis deals with partition and terminology of decision trees. There’re described all algorithms for decision tree construction in RapidMiner. The second part deals with implementation and comparison of chosen algorithms. The application was developed in C++. Based on the real datesets the comparisson of different algorithms was realized using Rapid Miner 4.0.

Developing high quality software is the goal of every software development organization. Software quality models are commonly used to assess and improve the software quality. These models, based on the past releases of the system, can be used to identify the fault-prone modules for the next release. This information is useful to the open-source software community, including both developers and users. Developers can use this information to clean or rebuild the faulty modules thus enhancing the system. The users of the software system can make informed decisions about the quality of the product. This thesis builds quality models using logistic regression, neural networks, decision trees, and genetic algorithms and compares their performance. Our results show that an overall accuracy of 65 ? 85% is achieved with a type II misclassification rate of approximately 20 ? 35%. Performance of each of the methods is comparable to the others with minor variations.

No description available.

The goal of this master’s thesis is to identify and evaluate data mining algorithms which are commonly implemented in modern Medical Decision Support Systems (MDSS). They are used in various healthcare units all over the world. These institutions store large amounts of medical data. This data may contain relevant medical information hidden in various patterns buried among the records. Within the research several popular MDSS’s are analyzed in order to determine the most common data mining algorithms utilized by them. Three algorithms have been identified: Naïve Bayes, Multilayer Perceptron and C4.5. Prior to the very analyses the algorithms are calibrated. Several testing configurations are tested in order to determine the best setting for the algorithms. Afterwards, an ultimate comparison of the algorithms orders them with respect to their performance. The evaluation is based on a set of performance metrics. The analyses are conducted in WEKA on five UCI medical datasets: breast cancer, hepatitis, heart disease, dermatology disease, diabetes. The analyses have shown that it is very difficult to name a single data mining algorithm to be the most suitable for the medical data. The results gained for the algorithms were very similar. However, the final evaluation of the outcomes allowed singling out the Naïve Bayes to be the best classifier for the given domain. It was followed by the Multilayer Perceptron and the C4.5.

Goal of this work is to make acquaintance and study meta-learningu methods, program algorithm and compare with other machine learning methods.

O tema deste estudo abrange duas áreas do conhecimento: a Medicina e a Ciência da Computação. Consiste na aplicação do processo de descoberta de conhecimento em base de Dados (KDD - Knowledge Discovery in Databases), a um banco de dados real na área médica denominado Registro Desire. O Registro Desire é o registro mais longevo da cardiologia intervencionista mundial, unicêntrico e acompanha por mais de 13 anos 5.614 pacientes revascularizados unicamente pelo implante de stents farmacológicos. O objetivo é criar por meio desta técnica um modelo que seja descritivo e classifique os pacientes quanto ao risco de ocorrência de eventos cardíacos adversos maiores e indesejáveis, e avaliar objetivamente seu desempenho. Posteriormente, apresentar as regras extraídas deste modelo aos usuários para avaliar o grau de novidade e de concordância do seu conteúdo com o conhecimento dos especialistas. Foram criados modelos simbólicos de classificação pelas técnicas da árvore de decisão e regras de classificação utilizando para a etapa de mineração de dados os algoritmos C4.5, Ripper e CN2, em que o atributo-classe foi a ocorrência ou não do evento cardíaco adverso. Por se tratar de uma classificação binária, os modelos foram avaliados objetivamente pelas métricas associadas à matriz de confusão como acurácia, sensibilidade, área sob a curva ROC e outras. O algoritmo de mineração processa automaticamente todos os atributos de cada paciente exaustivamente para identificar aqueles fortemente associados com o atributo-classe (evento cardíaco) e que irão compor as regras. Foram extraídas as principais regras destes modelos de modo indireto, por meio da árvore de decisão ou diretamente pela regra de classificação, que apresentaram as variáveis mais influentes e preditoras segundo o algoritmo de mineração. Os modelos permitiram entender melhor o domínio de aplicação, relacionando a influência de detalhes da rotina e as situações associadas ao procedimento médico. Pelo modelo, foi possível analisar as probabilidades da ocorrência e da não ocorrência de eventos em diversas situações. Os modelos induzidos seguiram uma lógica de interpretação dos dados e dos fatos com a participação do especialista do domínio. Foram geradas 32 regras das quais três foram rejeitadas, 20 foram regras esperadas e sem novidade, e 9 foram consideradas regras não tão esperadas, mas que tiveram grau de concordância maior ou igual a 50%, o que as tornam candidatas à investigação para avaliar sua eventual importância. Tais modelos podem ser atualizados ao aplicar novamente o algoritmo de mineração ao banco com os dados mais recentes. O potencial dos modelos simbólicos e interpretáveis é grande na Medicina quando aliado à experiência do profissional, contribuindo para a Medicina baseada em evidência. / The main subject of this study comprehends two areas of knowledge, the Medical and Computer Science areas. Its purpose is to apply the Knowledge Discovery Database-KDD to the DESIRE Registry, an actual Database in Medical area. The DESIRE Registry is the oldest world\'s registry in interventional cardiology, is unicentric, which has been following up 5.614 resvascularized patients for more then 13 years, solely with pharmacological stent implants. The goal is to create a model using this technique that is meaningful to classify patients as the risk of major adverse cardiac events (MACE) and objectively evaluate their performance. Later present rules drawn from this model to the users to assess the degree of novelty and compliance of their content with the knowledge of experts. Symbolic classification models were created using decision tree model, and classification rules using for data mining step the C4.5 algorithms, Ripper and CN2 where the class attribute is the presence or absence of a MACE. As the classification is binary, the models where objectively evaluated by metrics associated to the Confusion Matrix, such as accuracy, sensitivity, area under the ROC curve among others. The data mining algorithm automatically processes the attributes of each patient, who are thoroughly tested in order to identify the most predictive to the class attribute (MACE), whom the rules will be based on. Indirectly, using decision tree, or directly, using the classification rules, the main rules of these models were extracted to show the more predictable and influential variables according to the mining algorithm. The models allowed better understand the application range, creating a link between the influence of the routine details and situations related to the medical procedures. The model made possible to analyse the probability of occurrence or not of events in different situations. The induction of the models followed an interpretation of the data and facts with the participation of the domain expert. Were generated 32 rules of which only three were rejected, 20 of them were expected rules and without novelty and 9 were considered rules not as expected but with a degree of agreement higher or equal 50%, which became candidates for an investigation to assess their possible importance. These models can be easily updated by reapplying the mining process to the database with the most recent data. There is a great potential of the interpretable symbolic models when they are associated with professional background, contributing to evidence-based medicine.

O tema deste estudo abrange duas áreas do conhecimento: a Medicina e a Ciência da Computação. Consiste na aplicação do processo de descoberta de conhecimento em base de Dados (KDD - Knowledge Discovery in Databases), a um banco de dados real na área médica denominado Registro Desire. O Registro Desire é o registro mais longevo da cardiologia intervencionista mundial, unicêntrico e acompanha por mais de 13 anos 5.614 pacientes revascularizados unicamente pelo implante de stents farmacológicos. O objetivo é criar por meio desta técnica um modelo que seja descritivo e classifique os pacientes quanto ao risco de ocorrência de eventos cardíacos adversos maiores e indesejáveis, e avaliar objetivamente seu desempenho. Posteriormente, apresentar as regras extraídas deste modelo aos usuários para avaliar o grau de novidade e de concordância do seu conteúdo com o conhecimento dos especialistas. Foram criados modelos simbólicos de classificação pelas técnicas da árvore de decisão e regras de classificação utilizando para a etapa de mineração de dados os algoritmos C4.5, Ripper e CN2, em que o atributo-classe foi a ocorrência ou não do evento cardíaco adverso. Por se tratar de uma classificação binária, os modelos foram avaliados objetivamente pelas métricas associadas à matriz de confusão como acurácia, sensibilidade, área sob a curva ROC e outras. O algoritmo de mineração processa automaticamente todos os atributos de cada paciente exaustivamente para identificar aqueles fortemente associados com o atributo-classe (evento cardíaco) e que irão compor as regras. Foram extraídas as principais regras destes modelos de modo indireto, por meio da árvore de decisão ou diretamente pela regra de classificação, que apresentaram as variáveis mais influentes e preditoras segundo o algoritmo de mineração. Os modelos permitiram entender melhor o domínio de aplicação, relacionando a influência de detalhes da rotina e as situações associadas ao procedimento médico. Pelo modelo, foi possível analisar as probabilidades da ocorrência e da não ocorrência de eventos em diversas situações. Os modelos induzidos seguiram uma lógica de interpretação dos dados e dos fatos com a participação do especialista do domínio. Foram geradas 32 regras das quais três foram rejeitadas, 20 foram regras esperadas e sem novidade, e 9 foram consideradas regras não tão esperadas, mas que tiveram grau de concordância maior ou igual a 50%, o que as tornam candidatas à investigação para avaliar sua eventual importância. Tais modelos podem ser atualizados ao aplicar novamente o algoritmo de mineração ao banco com os dados mais recentes. O potencial dos modelos simbólicos e interpretáveis é grande na Medicina quando aliado à experiência do profissional, contribuindo para a Medicina baseada em evidência. / The main subject of this study comprehends two areas of knowledge, the Medical and Computer Science areas. Its purpose is to apply the Knowledge Discovery Database-KDD to the DESIRE Registry, an actual Database in Medical area. The DESIRE Registry is the oldest world\'s registry in interventional cardiology, is unicentric, which has been following up 5.614 resvascularized patients for more then 13 years, solely with pharmacological stent implants. The goal is to create a model using this technique that is meaningful to classify patients as the risk of major adverse cardiac events (MACE) and objectively evaluate their performance. Later present rules drawn from this model to the users to assess the degree of novelty and compliance of their content with the knowledge of experts. Symbolic classification models were created using decision tree model, and classification rules using for data mining step the C4.5 algorithms, Ripper and CN2 where the class attribute is the presence or absence of a MACE. As the classification is binary, the models where objectively evaluated by metrics associated to the Confusion Matrix, such as accuracy, sensitivity, area under the ROC curve among others. The data mining algorithm automatically processes the attributes of each patient, who are thoroughly tested in order to identify the most predictive to the class attribute (MACE), whom the rules will be based on. Indirectly, using decision tree, or directly, using the classification rules, the main rules of these models were extracted to show the more predictable and influential variables according to the mining algorithm. The models allowed better understand the application range, creating a link between the influence of the routine details and situations related to the medical procedures. The model made possible to analyse the probability of occurrence or not of events in different situations. The induction of the models followed an interpretation of the data and facts with the participation of the domain expert. Were generated 32 rules of which only three were rejected, 20 of them were expected rules and without novelty and 9 were considered rules not as expected but with a degree of agreement higher or equal 50%, which became candidates for an investigation to assess their possible importance. These models can be easily updated by reapplying the mining process to the database with the most recent data. There is a great potential of the interpretable symbolic models when they are associated with professional background, contributing to evidence-based medicine.

This paper describes how feature extraction on ancient pottery can be combined with recent developments in artificial intelligence to draw up an automated, but still flexible classification system. These features include for instance several dimensions of the vessel's body, ratios thereof, an abstract representation of the overall shape, the shape of vessel segments and the number and type of attachments such as handles, lugs and feet. While most traditional approaches to classification are based on statistical analysis or the search for fuzzy clusters in high-dimensional spaces, we apply machine learning techniques, such as decision tree algorithms and neural networks. These methods allow for an objective and reproducible classification process. Conclusions about the "typability" of data, the evolution of types and the diagnostic attributes of the types themselves can be drawn as well.