Effective hybrid feature selection using different bootstrap enhances cancers classification performance

Abdelwahed, Noura Mohammed; El-Tawel, Gh. S.; Makhlouf, M. A.

doi:10.1186/s13040-022-00304-y

BioData Mining

Table 10 The proposed methods compared with the IGF method

From: Effective hybrid feature selection using different bootstrap enhances cancers classification performance

Datasets	Train Data %	Test Data %	Over-fitting Diff. %	Pre	Rec	F1-score	NO.F	F-Time (sec)	C-Time (sec)	AUC	Var.	ACC %
LR classifier
RNA gene	100.000	99.875	0.125	0.999	0.999	0.998	3576	1.182	2.121	1.000	0.000016	99.875
DNA CNV	93.115	81.310	11.805	0.782	0.706	0.705	3315	5.651	0.595	0.951	0.000576	81.310
Parkinson’s disease	77.822	76.984	0.838	0.680	0.576	0.566	396	0.093	0.057	0.710	0.001445	76.984
Dermatology diseases	97.784	97.260	0.524	0.973	0.968	0.969	25	0.032	0.0009	0.998	0.000677	97.260
BreastEW	94.170	93.674	0.496	0.942	0.928	0.931	22	0.064	0.001	0.989	0.002176	93.674
SVM classifier
RNA gene	100.000	99.750	0.250	0.999	0.997	0.998	3576	1.182	2.272	1.000	0.000028	99.750
DNA CNV	94.273	85.872	8.401	0.873	0.780	0.801	3315	5.651	3.142	0.969	0.000486	85.872
Parkinson’s disease	75.666	72.379	3.287	0.434	0.497	0.443	396	0.093	0.204	0.640	0.004378	72.379
Dermatology diseases	98.269	97.530	0.739	0.975	0.972	0.972	25	0.032	0.014	0.999	0.000752	97.530
BreastEW	92.007	91.569	0.438	0.930	0.895	0.904	22	0.064	0.021	0.979	0.004502	91.569
RF classifier
RNA gene	100.000	99.502	0.498	0.997	0.994	0.996	3576	1.182	0.826	0.999	0.000410	99.502
DNA CNV	92.558	81.139	11.419	0.773	0.714	0.721	3315	5.651	1.584	0.944	0.000531	81.139
Parkinson’s disease	100.000	83.733	16.267	0.793	0.726	0.734	396	0.093	0.719	0.860	0.009057	83.733
Dermatology diseases	100.000	96.997	3.003	0.973	0.962	0.964	25	0.032	0.098	0.999	0.000567	96.997
BreastEW	99.982	96.140	3.842	0.961	0.959	0.958	22	0.064	0.118	0.986	0.002280	96.140
Bagg classifier
RNA gene	99.940	99.126	0.814	0.996	0.990	0.992	3576	1.182	3.040	0.999	0.000260	99.126
DNA CNV	98.701	79.045	19.656	0.741	0.698	0.708	3315	5.651	1.095	0.911	0.000553	79.045
Parkinson’s disease	99.653	82.297	17.356	0.790	0.752	0.754	396	0.093	1.079	0.830	0.011270	82.297
Dermatology diseases	99.696	95.375	4.321	0.958	0.950	0.949	25	0.032	0.012	0.993	0.001466	95.375
BreastEW	99.636	95.253	4.383	0.957	0.946	0.948	22	0.064	0.029	0.987	0.001788	95.253

Back to article page

ISSN: 1756-0381

Contact us

General enquiries: journalsubmissions@springernature.com