Harmonic extreme learning machine for data clustering

Unsupervised Extreme Learning Machine (US-ELM) is the one type of neural network which modified from Extreme Learning Machine (ELM) for handle the clustering problem. Nevertheless, US-ELM has problem with nonfulfillment of solution due to K-Mean algorithm was used to cluster which made the accuracy of solution was unstable when training many times. In this paper, K-Harmonic mean algorithm was proposed to instead of K-Mean algorithm to improve the accuracy of solution and more stable gained called, Harmonic Extreme Learning Machine (Harm-ELM) likewise the experiment result compared with state-of-the-art show that Harm-ELM can overcome to 75% of all datasets that used to attempt.