Effective discovery of classification rules for the high dimensional data is becoming one of the hard search problems and hot research area. Heuristic search algorithms provide an approximate solution to hard search problems within the reasonable time. Inspired by the biological life cycle of nature, we introduce a Novel Adaptive Life Cycle Model (NALCM) which applies both Memetic Algorithms (MAs) and Particle Swarm Optimization (PSO) to create a well-performing hybrid heuristics for the discovery of rules. In the proposed model, candidate solutions are represented as individuals and based on the fitness, they can decide to become either a MA individual, a particle of a PSO. Results are compared with other search algorithms such as Particle Swarm Optimization and Genetic Algorithms. The proposed model achieves better performance.
展开▼
