Prediction of Coal /Gas Outbursts Based on Selective Ensemble Learning

For the purpose of achieving accurate and reliable coal /gas outbursts prediction, a coal /gas outbursts prediction algorithm based on selective ensemble learning is presented. The component learners consisted of RS-PNN network, and the redundant component learners were removed from the ensemble learners using a ensemble learning algorithm based on variable similarity cluster technology, and voting to the retained based learners was used as the output of the ensemble learners, which effectively improved both the diversity of component learners an generalization performance of ensemble learners. The result show that the method can made use of small sample data, inherited the advantages of strong ensemble learners, and effectively improved the classification accuracy, and it has a high application value.