An improved Harris Hawk optimization algorithm and its application to Extreme Learning Machine

Abstract

The Harris Hawk optimization (HHO) algorithm is an excellent swarm intelligence optimization algorithm which has the advantages of high efficiency in finding the best, ease of implementation and wide application. It also has some disadvantages such as the possibility of convergence too fast and the tendency to fall into local optima. This paper combines an improved escape energy update approach and the leader update operator of the Salp Swarm Algorithm to improve the HHO, named IMHHO. The experiments show that the improvements have improved the algorithm's ability to find the best. IMHHO was also used in the parameter optimization of the Extreme Learning Machine, which also enables the ELM to find the right weights and bias values and to regress the data more accurately.