Fig 1.
Initial population generated by 3 kinds of maps in 1000 iterations.
(a) Rand, (b) Tent map, (c) Chebyshev map, (d) Gauss map.
Fig 2.
Probability generation of whale social behavior.
(a) Early iteration, b) Mid-iteration, c) Late iteration.
Fig 3.
Original parameter a-value, -value and
-value under 1000 iterations.
Fig 4.
Modified parameter a-value, -value and
-value under 1000 iterations.
Fig 5.
Majority voting criteria.
Table 1.
Benchmark functions used and their details.
Table 2.
Datasets used and their details.
Table 3.
Parameter settings of IWOA and other selected algorithms.
Fig 6.
Logarithmic mean convergence curves of different algorithms.
(a)F1(Sphere function), b)F3(Schwefel 1.2 function), (c)F5(Rastrigin function), d)F7(Weierstrass function), (e)F1(30D), (f)F3(30D), (g)F5(30D), (h)F7(30D). (i)F1(100D), (j)F3(100D), (k)F5(100D), (l)F7(100D).
Table 4.
The comparison of obtained solutions for 8 benchmark functions.
Fig 7.
Average running time of different algorithms.
(a) 30D Average running time(s), (b) 100D Average running time(s).
Table 5.
p-value of the Wilcoxon test for the optimization results of IWOA and other algorithms based 8 benchmark functions (p> = 0.5 are in bold).
Table 6.
Friedman test results of benchmark functions with different dimensions.
Table 7.
The comparison of classification accuracy of different strategies.
Table 8.
The comparison of classification accuracy of different classifiers.
Table 9.
Parameter settings of IWOAIKFS and other selected algorithms.
Table 10.
Comparison between IWOAIKFS with other competitor optimizers based on accuracy (k = 5 and best are in bold).
Fig 8.
Total mean accuracy of IWOAIKFS compared to other algorithms under all datasets.
Fig 9.
The accuracy of IWOAIKFS compared to other optimizers.
Fig 10.
The selection ratio of IWOAIKFS compared to other optimizers.
Fig 11.
Convergence curve of IWOAIKFS versus other algorithms over all datasets (k = 5).
(a) Birds, (b) Blood, (c) Breast_cancer, (d) Bupa, (e) Car, (f) Chart, (g) Digits, (h) Glass, (i) Heart_disease, (j) Indian, (k) Ionosphere, (l) Iris, (m) Planning, (n) Wine, (o) Zoo.
Table 11.
p-value of the Wilcoxon test for the classification accuracy results of IWOAIKFS and other optimizers (k = 5 and p > = 0.5 are in bold).
Table 12.
Friedman test results for datasets.
Fig 12.
Boxplot of IWOAIKFS versus other algorithms over all datasets (k = 5).
(a) Birds, (b) Blood, (c) Breast_cancer, (d) Bupa, (e) Car, (f) Chart, (g) Digits, (h) Glass, (i) Heart_disease, (j) Indian, (k) Ionosphere, (l) Iris, (m) Planning, (n) Wine, (o) Zoo.