Network-based data classification: combining K-associated optimal graphs and high-level prediction

Journal of the Brazilian Computer Society

Table 4 Comparative results obtained by HL-KAOG, CART, KNN, and SVM on ten real-world data sets

	HL-KAOG	CART	KNN	SVM
Data set	Acc. ± Std.	Acc. ± Std.	Acc. ± Std.	Acc. ± Std.
Iris	97.33 ± 3.52 (λ₁)	93.60 ± 5.59	96.37 ± 4.63	96.28 ± 4.02
Glass	70.78 ± 9.16 (λ₁)	64.12 ± 9.33	72.64 ± 8.09	68.61 ± 7.78
Balance	95.71 ± 2.40 (λ₁)	88.20 ± 4.25	89.77 ± 1.96	99.97 ± 0.08
Monks-2	96.53 ± 2.43 (λ₁)	95.67 ± 2.48	81.26 ± 5.02	93.79 ± 3.22
Ecoli	84.90 ± 5.73 (λ₂)	80.78 ± 5.55	85.99 ± 5.11	87.23 ± 5.22
Append.	83.54 ± 7.27 (λ₁)	77.24 ± 9.95	86.99 ± 8.71	85.72 ± 8.15
Thyroid	97.30 ± 3.16 (λ₁)	96.64 ± 2.95	93.58 ± 4.74	97.19 ± 2.59
Sonar	83.75 ± 8.07 (λ₁)	74.14 ± 9.69	81.78 ± 8.08	86.06 ± 7.43
Digits	98.75 ± 0.35 (λ₁)	90.27 ± 1.27	98.79 ± 0.37	99.26 ± 0.33
SPECTF	80.07 ± 5.42 (λ₂)	75.41 ± 6.20	77.90 ± 6.78	78.01 ± 3.92

‘Acc’ and ‘Std’. denote, respectively, the average of accuracy and the standard deviation over 30 runs using the stratified 10-fold cross-validation process. In HL-KAOG, the classification result is obtained from the best value between λ₁ = 0.2 and λ₂ = 0.6. Italic values denote the best predictive performance among the techniques for each data set.