Table 5.

Performance metrics for the convolutional neural network against each feature-selection technique.

Feature Selector	Statistics	Precision	Recall	F1-Score	Accuracy
iNCA	Minimum	98.536	98.534	98.535	98.534
	Maximum	99.078	99.077	99.077	99.077
	Average	98.810	98.806	98.808	98.806
iChi2	Minimum	98.915	98.914	98.914	98.914
	Maximum	99.133	99.132	99.132	99.131
	Average	99.026	99.023	99.024	99.023
iMRMR	Minimum	98.489	98.154	98.322	98.154
	Maximum	98.914	98.914	98.914	98.914
	Average	98.535	98.534	98.534	98.534

iNCA: iterative neighborhood component analysis; iChi2: iterative chi-square; iMRMR: iterative maximum relevance–minimum redundancy.