Constrained voting extreme learning machine and its application

Extreme learning machine (ELM) has been proved to be an effective pattern classification and regression mechanism by researchers. However, its good performance is based on a large number of hidden layer nodes. With the increase nodes in layers, computation cost greatly increased. In this paper, we propose novel algorithm, named constrained voting extreme (CV-ELM). Compared with traditional ELM, CV-ELM determines input weight bias differences between-class samples. At same time, improve accuracy proposed method, selection introduced. The method evaluated public benchmark datasets. experimental results show that algorithm superior original ELM algorithm. Further, apply superheat degree (SD) state aluminum electrolysis industry, recognition rate reaches 87.4%, demonstrate more robust than existing state-of-the-art identification methods.