As can be seen from Figure 4, this iteration is iteratively implemented on the training set. It can be seen from the iterative graph that the convergence of the method in this paper is the best among the five algorithms, the error rate is the lowest among the five algorithms, followed by GWO-KELM, WOA-KELM, CBA-KLEM, and finally PSO- KELM, and the method proposed in this paper completed the iteration in the third time, which is obviously superior to the other four methods.
正在翻译中..