Human Activity Recognition Based on Improved Artificial Bee Colony Algorithm

Support vector machine is a new machine learning method, and its classification performance mainly depends on the selection of related parameters. An improved artificial colony algorithm is proposed to optimize the parameters of SVM and applied to human activity recognition. Compared with other optimization algorithms including basic artificial colony algorithm, genetic algorithm and particle swarm algorithm on standard datasets, the proposed algorithm can acquire higher classification precision. Compared with artificial colony algorithm based on all dimensional search, the improved algorithm costs less running time. The proposed method is used as the classifier of human activity and a high classification precision is acquired.