Particle Swarm Optimization Based Selective Ensemble of Online Sequential Extreme Learning Machine

Algorithm 1

Input:

A training set , hidden node output function

, and the number of hidden nodes .

Steps:

(1) Assign parameters of hidden nodes randomly, .

(2) Calculate the hidden layer output matrix .

(3) Calculate the output weight = , where is the Moore-Penrose generalized

inverse of hidden layer output matrix .