Multiobjective Network Optimization for Soil Monitoring of the Loess Hilly Region in China

Table 2

Summary results of the modified particle swarm optimization algorithm.

Variable	Objective	MKE + MSB^1	MKE^1	MSB^1	Sampling size	Convergence iteration	Running time (s)
SOM	MKE + MSB	0.482	0.344	0.906	341	378	782.19
	MKE	0.588	0.333	0.935	289	310	618.72
	MSB	0.632	0.498	0.725	300	332	636.85
SWC	MKE + MSB	0.618	0.589	0.917	313	320	763.85
	MKE	0.676	0.559	0.933	292	301	621.58
	MSB	0.775	0.781	0.772	300	332	636.80

1The values were normalized within the interval [0, 1].