An Improved Monte Carlo Method Based on Neural Network and Fuzziness Analysis: A Case Study of the Nanpo Dump of the Chengmenshan Copper Mine

Table 2

Particle swarm optimization-extreme learning machine (PSO-ELM) algorithm program.

---

Algorithm: algorithmic flow of PSO-ELM

---

(1) Obtain the training and testing datasets
(2) Begin ELM training
(3) Set ELM parameters randomly
(4) Use the mean square error (MSE) as the fitness function
(5) Initialize PSO population (Inipop)
(6) Calculate the fitness value of each candidate solution
(7) S = global best solution
(8) For i = 1 to maximum iteration number do
(9)  For i = 1 to do
(10)   Update the velocity and position of the ith particle
(11)   Evaluate the fitness of the ith particle
1(2)   Update the personal best solution of the ith particle
(13)   S = current global best solution
(14)  End for
(15) End for
(16) End
(17) Obtain the optimal input weights and hidden biases of hidden layer neurons using S
(18) Use the optimal input weights and hidden layer neurons for ELM test

---