This paper aims to compare the performance of different population-based meta-heuristics to train AdaBoost classifiers applied to detect platelets. AdaBoost classifiers are able to recognize complex patterns based on simple characteristics. We assessed three mono-objective techniques for AdaBoost training: Particle Swarm Optimization, Fish School Search and Genetic Algorithms. Our results show that the Genetic Algorithms outperformed the other two techniques for classifiers with just some few weak classifiers, while Particle Swarm Optimization achieved better results for classifiers with a higher number of weak classifiers, such as for twenty characteristics. We also tested two multi-objective optimizers, one based on Evolutionary Computation and another one based on Swarm Intelligence. The Multi-objective optimizers outperformed the mono-objective optimizers.

No abstract

ResumoA saúde pública é uma extensa área com problemas complexos e que constantemente necessita de bastantes investimentos. Frequentemente os órgãos governamentais enfrentam desafios para entender como oferecer melhores serviços de saúde e prevenir epidemias futuras. Métodos preventivos tem sido até o momento a melhor opção para controlar doenças e epidemias ou mesmo extingui-las. Este trabalho utilizou dados epidemiológicos provenientes do projeto 500 Cities e técnicas de agrupamento (clusterização) de dados para identificar comunidades com características relevantes para dar suporte na prevenção de epidemias e doenças. AbstractPublic health is a large area with complex problems and constantly needs huge investments. Frequently, government agencies face challenges in understanding how to deliver effective and targeted health services and prevent future epidemics. Prevention has so far been the best option to control diseases and epidemics or even extinguish them. This work used epidemiological data provided by the 500 Cities project along with data clustering techniques to identify communities with relevant characteristics to support epidemics and diseases prevention.