Um algoritmo de vida artificial para agrupamento de dados variantes no tempo

• Ano de defesa: 2012
• Autor(a) principal: Santos, Diego Gadens dos
• Orientador(a): Silva, Leandro Nunes de Castro
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Presbiteriana Mackenzie
• Palavras-chave em Português: vida artificial; computação natural; mineração de dados; agrupamento de dados; boids; dados variantes no tempo
• Palavras-chave em Inglês: artificial life; natural computing; data mining; data clustering; boids; time-varying data
• Área do conhecimento CNPq: CNPQ::ENGENHARIAS::ENGENHARIA ELETRICA
• Link de acesso: http://dspace.mackenzie.br/handle/10899/24343

Current technologies have made it possible to generate and store data in high volumes. To process and collect information in large databases is not always as easy as creating them. Therefore, this gap has stimulated the search for efficient techniques capable of extracting useful and non-trivial knowledge, which are intrinsic to these large data sets. The goal of this work is to propose a bioinspired algorithm, based on the Boids artificial life model, which will be used to group data in dynamic environments, i.e. in databases updated over time. The Bo-ids algorithm was originally created to illustrate the simulation of the coordinated movement observed in a flock of birds and other animals. Thus, to use this algorithm for data clustering, some modifications must be applied. These changes will be implemented in the classical rules of cohesion, separation and alignment of the Boids model in order to consider the distance (similarity/dissimilarity) among objects. Thus, it creates objects that stand and move around the space, representing the natural groups within the data, and it is expected that similar ob-jects tend to form dynamic clusters (groups) of Boids in the environment, while dissimilar objects tend to keep a larger distance between them. The results presented attest the robust-ness of the algorithm for clustering time-varying data under the light of different evaluation measures and in various databases from the literature.