AMPSO: A New Particle Swarm Method for Nearest Neighborhood Classification

摘要: Nearest prototype methods can be quite successful on many pattern classification problems. In these methods, a collection of prototypes has to found that accurately represents the input patterns. The classifier then assigns classes based nearest in this collection. paper, we first use standard particle swarm optimizer (PSO) algorithm find those prototypes. Second, present new algorithm, called adaptive Michigan PSO (AMPSO) order reduce dimension search space and provide more flexibility than former application. AMPSO is different approach swarms as each single solution. does not converge solution; instead, local classifier, whole taken solution problem. It uses modified equations with both competition cooperation dynamic neighborhood. As an additional feature, AMPSO, number represented able adapt problem, increasing needed make We compared results several benchmark problems from University California, Irvine, data sets always better PSO. also it was improve Neighbor classifiers, competitive some algorithms most commonly used for classification.