BMC Bioinformatics

Table 2 The predictive accuracy of testing samples

From: A combinational feature selection and ensemble neural network method for classification of gene expression data

	ALLAML Leukemia	Lung cancer	Prostate cancer
Bagged decision trees	91.18%	93.29%	73.53%
The best methods	97.06%	97.99%	73.53%
Our methods	100%	100%	97.06%
LOOCV on training samples	100%	100%	96.08%

* Note that the row of the best methods refer to the different method in different datasets

Back to article page

ISSN: 1471-2105

Contact us

General enquiries: journalsubmissions@springernature.com