Nowadays warehousing became one of the most important and critical part in supply chain systems due to the fact that it consumes a considerable part of logistic cost. Designing phase of warehousing system is the most important part in warehousing since most of the strategic and tactical decisions should be taken in this phase. Majority of academic papers are primarily analysis oriented and does not give a systematic method and techniques as a basis for warehouse redesign. So there is a need to develop a structured procedure that can be applied for different type of warehouses. Therefore the purpose of this thesis is to develop a process for redesigning production warehouses, and analyzing major problems during redesign steps. The thesis is designed as a case study, and a mix of quantitative and qualitative methods were used for data collection and data analysis. The methodology focuses around the warehousing process and redesign steps as described in the literature. Results of the thesis develop a seven steps procedure for redesigning of the production warehouse, also different problems and challenges are faced during redesign steps. It was tried to choose the best redesigning method which fit with the characteristics of the warehouse, in order to cover the space reduction of the warehouse with the consideration of existing facilities and reducing of cost. In addition, the performance of the current warehouse system was evaluated based on current design of the warehouse in order to avoid repeating of same mistake in redesign process. Storage assignment policy as one of the redesign steps was discussed and a framework for storage system of the components were suggested. The findings of the thesis to some extent can be applicable to other production warehouses. Further research is suggested for more specific results and new developed redesign methods for all types of warehouses.

Traditional relational database model does not have enough capability to cope with a great deal of data in finite time. To address these requirements, data warehouses and online analytical processing (OLAP) have emerged. Data warehouses improve the productivity of corporate decision makers through consolidation, conversion, transformation, and integration of operational data, and supports online analytical processing (OLAP). The data warehouse design is a complex and knowledge intensive process. It needs to consider not only the structure of the underlying operational databases (source-driven), but also the information requirements of decision makers (user-driven). Past research focused predominately on supporting the source-driven data warehouse design process, but paid less attention to supporting the user-driven data warehouse design process. Thus, the goal of this research is to propose a user-driven data warehouse design support system based on the knowledge discovery approach. Specifically, a Data Warehouse Design Support System was proposed and the generalization hierarchy and generalized star schemas were used as the data warehouse design knowledge. The technique for learning these design knowledge and reasoning upon them were developed. An empirical evaluation study was conducted to validate the effectiveness on the proposed techniques in supporting data warehouse design process. The result of empirical evaluation showed that this technique was useful to support data warehouse design especially on reducing the missing design and enhancing the potentially useful design.

Universiẗat Campus Duisburg, Diss.--Duisburg-Essen, 2007.

Univ., Diss.--Hamburg, 2007.

Bremen, Universiẗat, Diss., 2009.

Diss. Nr. 2424 Wirtschaftswiss. St. Gallen. / Literaturverz.

Diss. Nr. 3165 Wirtschaftswiss. St. Gallen, 2006. / Literaturverz.

Thesis (doctoral)--Universiẗat, Würzburg, 2003.

[pt] As organizações se deparam com uma necessidade cada vez maior de mudar e evoluir, mas para isso elas precisam tomar as decisões corretas. Para essa tomada de decisão, as empresas estão adotando os recursos disponibilizados pela Tecnologia da Informação (TI) como parte fundamental para apoiar suas decisões. Um componente de TI essencial para aprimorar o processo de tomada de decisão é o data warehouse. Para cumprir bem o seu papel, o data warehouse deve ser bem definido. Embora existam diversas abordagens que buscam melhorar a tarefa de identificação dos requisitos para data warehouses, poucas exploram as contribuições da Engenharia de Processos de Negócios (EPN) no processo de definição dos requisitos. Esta dissertação estuda um meio de aprimorar a tarefa de elicitação de requisitos para data warehouses, utilizando indicadores de desempenho aliados aos processos de negócio. Para isso é sugerido um conjunto de heurísticas que visam, a partir dos indicadores de desempenho, orientar a descoberta dos requisitos de data warehouse. A aplicação das heurísticas propostas é feita em um caso, facilitando a compreensão da abordagem sugerida nesse trabalho. / [en] Organizations need to change and evolve, but for that it is necessary to make the right decisions. For this decision, companies are using Information Technology (IT) as a fundamental part to support their decisions. An essential IT component to improve the process of decision making is the data warehouse. In order to fulfill its role well, the data warehouse must be well defined. There are various approaches that try to improve the task of identifying data warehouses requirements, but few explore the contributions of Business Processes Engineering (BPE) in the process of requirements gathering. This dissertation studies how to improve data warehouses requirements elicitation using performance indicators allied to business processes. For this it is suggested a set of heuristics designed to guide performance measures identification and data warehouse requirements discovery. The heuristics are applied in a case to facilitate understanding of suggested approach in this work.

[pt] Esta dissertação investiga a aplicação de Redes Neurais e Algoritmos Genéticos como ferramentas para retirar conhecimentos, em forma de regras, de um Banco de Dados. Essa nova área, KDD (knowledge Discovery in Database), surgiu com a necessidade de se desenvolver ferramentas que possam, de forma automática e inteligente, ajudar aos analistas de dados a transformar grandes volumes de dados em informações e organizar estas informações em conhecimentos úteis. A pesquisa aqui resumida é portanto, um desenvolvimento na área de sistemas de computação (desenvolvimento de sistemas) e na área de inteligência computacional (data mining, algoritmos genéticos, redes neurais, interfaces inteligentes, sistemas de apoio a decisão, criação de bases de conhecimentos) O trabalho de tese foi dividido em cinco partes principais: um estudo sobre o processo KDD; um estudo da estrutura dos sistemas de KDD encontrados na literatura; o desenvolvimento de sistemas de KDD, um utilizando algoritmos Genéticos e os outros utilizando Redes Neurais; o estudo de casos e a análise de desempenho dos sistemas desenvolvidos. O processo de KDD serve para que se possa retirar novos conhecimentos (padrões, tendências, fatos, probabilidade, associações) de um determinado banco de dados. Basicamente o KDD consiste em oito etapas, que são: Definição do problema, Seleção dos dados, Limpeza dos dados, enriquecimento dos dados, Pré-processamento dos dados, Codificação dos dados, Mineração dos dados (data mining) e o relatório contendo a interpretação dos resultados. A mineração dos dados é freqüentemente vista como elemento chave do processo de KDD. A extração do conhecimento, propriamente dita, se dá na Mineração dos dados, onde toda técnica que ajude a extrair mais informações dos dados é útil. Assim na Mineração de dados podemos lançar mão de um grupo heterogêneo de técnicas, como por exemplo, Técnicas de estatísticas, visualização dos dados, redes neurais e algoritmos genéticos. Portanto os estudos do processo inclui estudos sobre Data Mining, aprendizado de máquinas, data warehouse, o processo e o ambiente do KDD, aspectos formais dos algoritmos de aprendizado, inteligência artificial, e algumas aplicações na vida real. Dentre os vários sistemas de KDD encontrados na literatura que foram estudados e analisados, podemos citar sistemas que utilizaram, na etapa de mineração dos dados, uma ou mais das seguintes técnicas de computação para extrair padrões e associações nos dados, uma ou mais das seguintes técnicas de computação para extrair padrões e associações nos dados tais como: Visualização dos dados, ferramenta de consulta, técnicas de estatísticas, processamento analítico on-line (OLAP), Árvore de decisão, regras de associação, redes neurais e algoritmos genéticos. Neste trabalho foram desenvolvidos dois sistemas de KDD. Em cada um dos modelos desenvolvidos utilizou-se uma técnica de visualização dos dados para garantir a interação do sistema com o analista dos dados. Além disso utilizou-se, na etapa mineração dos dados, num dos modelos Algoritmos genéticos, e no outro Redes Neurais Backpropagation. Também para efeito de comparação e de apoio, se desenvolveu um sistema utilizando Técnicas de Estatísticas. Com o modelo utilizando Algoritmos Genéticos se encontra a melhor regra de produção relacionada a um banco de dados, que responde a uma pergunta específica. E com os modelos utilizando Redes Neurais se obtém resultados para serem comparados. A fase de aplicação consistiu em analisar dois diferentes bancos de dados, um contendo dados dos meninos e meninas de rua, e o outro contendo dados dos alunos que se matricularam no vestibular. Na análise dos bancos de dados se utilizou os sistemas de KDD aqui desenvolvidos, tendo como objetivo encontrar, com o auxílio de Algoritmos genéticos, ou de redes ne / [en] This dissertation investigates the genetic algorithms and neural networks as applications tools to find knowledge, in the form of rules, from a database. This new area, KDD (Knowledge Discovery in Database) appeared with the need of developing tools that can, in automatic and intelligent way, help the data analysis to transform great volumes of data in information and to organize these information in useful knowledge. The research here summarized is therefore, a development in the area of computational systems (development of systems) and in the area of intelligence computational (data mining, genetic algoriths, neural networks, intelligence interfaces, decision support systems and creation of knowledge bases). The thesis work was divided in five main parts: A study of the KDD process: a study of the structure of the KDD systems found in the literature; the development of KDD systems, one using genetic algorithms and the others using neural networks; the study of cases and the analysis of the performance of the developed systems. The KDD process is able to find new knowledge (patterns, tendencies, facts, probability and associations) from a certain database. Basically KDD involves eight steps, that are: problem definition, data selection, cleaning, enrichment, preprocessing, coding, data mining and the reporting containing the interpretation of the results. The Data Mining is frequently seen as the key element of the KDD process. The extraction of the knowledge, itself, happens in the Data mining, where any technique that helps extract more information out of your data is useful. In Data Mining we can make use of a heterogeneous group of techiques, for example, Statistical techniques, Visualization techniques, Neural Networks and Genetic algorithms. Therefore the studies of the KDD process included studies on data mining, machine learning, data warehouse, the KDD process and the KDD environment, formal aspects of the learning algoriths, artificial intelligence, and some applications in the real life. In several KDD systems found in the literature that were studied and analyzed, we can mention systems that uses, in the data mining step, one or more of following computation techniques to extract patterns and associations from data as: visualization techniques, query tools, statistical techniques, online analytical processing (OLAP), decision trees, association rules, neural networks and genetic algorithms. In this work two KDD systems wer developed. In each one of the developed models a visualization techniques was used, to guarantee the interaction of the system with the data analyst. And in the Data Mining step, genetic algorithms was used in one of the models, and Backpropagation Neural Networks in the other. For comparison and support effect, a system was developed using Statistical techniques. The genetic algorithm model is to find the best production rule related to a database, that answers to a specific question. And the results of the Neural Networks model is to be compared with the results of the genetic algorithm model. The application phase consisted of analyzing two different databases, one with the boys´data that lives in the street, and the other with the students´data that makes the university admission test. In the analysis of the databases it was used the KDD system here developed, with the objective to find, with genetic algorithms, or Neural Network, the best production rule, related to the databases, that answers a specific question. Two types of question. Two types of question were considered, the ones that look for characteristic of a group of data, for example, Which the boys characteristics that live in the streets? And Which the characteristics of a group of individuals that were classified but they didn´t enroll in the university? And that associates groups of data, for example, What differentiate the boys, with similar economic situation, tha