Genetic Algorithm Based Optimization for AdaBoost

AdaBoost was proposed as an efficient algorithm of the ensemble learning field, it selects a set of weak classifiers and combines them into a final strong classifier. However, conventional AdaBoost is a sequential forward search procedure using the greedy selection strategy, redundancy can not be avoided. We proposed a post optimization procedure for the found classifiers and their coefficients based on genetic algorithm, which removes the redundancy classifiers and leads to shorter final classifiers and a speedup of classification. Our algorithm is tested on the UCI benchmark data sets, fewer weak classifiers and faster classification compared with conventional AdaBoost algorithm is experienced.