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 11 The proposed methods compared with the mRMR 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	99.750	0.250	0.999	0.997	0.998	650	1200.011	0.251	1.000	0.000028	99.750
DNA CNV	91.819	79.699	12.120	0.746	0.688	0.689	505	2296.409	0.686	0.940	0.000529	79.699
Parkinson’s disease	74.617	73.011	1.606	0.500	0.515	0.479	145	61.005	0.017	0.659	0.002502	73.011
Dermatology diseases	95.508	95.075	0.433	0.950	0.908	0.919	15	3.996	0.002	0.995	0.000796	95.075
BreastEW	93.085	92.620	0.465	0.936	0.910	0.917	19	4.181	0.002	0.981	0.003358	92.620
SVM classifier
RNA gene	100.000	99.748	0.252	0.999	0.997	0.998	650	1200.011	0.382	1.000	0.000028	99.748
DNA CNV	92.486	83.848	8.638	0.845	0.747	0.766	505	2296.409	3.609	0.961	0.000559	83.848
Parkinson’s disease	75.661	72.379	3.282	0.435	0.497	0.443	145	61.005	0.142	0.639	0.004378	72.379
Dermatology diseases	52.793	52.185	0.608	0.325	0.463	0.363	15	3.996	0.053	0.948	0.002302	52.185
BreastEW	89.049	88.938	0.111	0.915	0.860	0.870	19	4.181	0.044	0.945	0.005405	88.938
RF classifier
RNA gene	100.000	99.627	0.373	0.998	0.996	0.997	650	1200.011	0.398	1.000	0.000036	99.627
DNA CNV	90.959	79.935	11.024	0.727	0.690	0.689	505	2296.409	0.534	0.942	0.001249	79.935
Parkinson’s disease	100.000	81.918	18.082	0.767	0.703	0.709	145	61.005	0.467	0.833	0.011138	81.918
Dermatology diseases	100.000	97.553	2.447	0.981	0.968	0.972	15	3.996	0.1000	0.999	0.000561	97.553
BreastEW	100.00	95.604	4.396	0.960	0.950	0.952	19	4.181	0.183	0.991	0.002693	95.604
Bagg classifier
RNA gene	99.961	98.746	1.215	0.991	0.984	0.986	650	1200.011	1.680	0.999	0.000430	98.746
DNA CNV	97.817	77.468	20.349	0.731	0.682	0.687	505	2296.409	1.135	0.910	0.000937	77.468
Parkinson’s disease	99.498	79.369	20.129	0.725	0.712	0.705	145	61.005	0.561	0.799	0.010620	79.369
Dermatology diseases	99.545	94.017	5.528	0.951	0.936	0.937	15	3.996	0.009	0.982	0.002412	94.017
BreastEW	99.642	93.684	5.958	0.943	0.928	0.931	19	4.181	0.042	0.980	0.002369	93.684

Back to article page

ISSN: 1756-0381

Contact us

General enquiries: journalsubmissions@springernature.com