A New Binary Adaptive Elitist Differential Evolution Based Automatic k-Medoids Clustering for Probability Density Functions

Table 10

Comparison of performance of evolutionary algorithms only in terms of mean, standard deviation, result of Mann-Whitney test, and ranking by Kruskal-Wallis test.

Data set	Algorithm	Mean	Std.	Result of Mann-Whitney test	Rank by Kruskal-Wallis test	Time
						(Seconds)
7 normal PDFs	baeDE-CDF	1.000	0.000		-	0.340
	GA-CDF	0.991	0.065	-	-	7.054
	MILXPM-CDF	1.000	0.000	-	-	7.832
Brodatz images	baeDE-CDF	1.000	0.000		125.50	13.699
	GA	0.324	0.073	+	35.50	114.885
	MILXPM-CDF	0.132	0.000	+	65.50	126.987
UIUC images	baeDE-CDF	1.000	0.000		125.50	4.677
	GA-CDF	0.094	0.083	+	50.50	40.45
	MILXPM-CDF	0.094	0.083	+	50.50	37.72
CUReT images	baeDE-CDF	0.982	0.056		125.50	3.973
	GA-CDF	0.049	0.093	+	70.50	36.07
	MILXPM-CDF	-0.041	0.000	+	30.50	41.52
Traffic images	baeDE-CDF	0.909	0.131		114.06	62.958
	GA-CDF	0.087	0.051	+	26.940	551.573
	MILXPM-CDF	0.908	0.131	+	85.50	408.621