Phasmatodea population evolution algorithm and its application in length-changeable incremental extreme learning machine

Abstract

Extreme learning machine (ELM) is an effective classification and prediction learning algorithm based on feedforward neural network (FNN). This paper presents the Phasmatodea (stick insect) population evolution algorithm (PPE), which is different from other algorithms, in which each solution represents a population and has two attributes: quantity and growth rate. Combining the concept of similar evolution and the model of population competition, it is a new local search method. The algorithm is compared with the other algorithms on benchmark functions and engineering problems. Then use it to enhance a variant of the ELM model. The results show that the proposed algorithm has a certain competitiveness.