Arabic Sign Language Recognition System for Alphabets Using Machine Learning Techniques

Table 13

The effect of neurons number in MLP network on the accuracy and time of classification.

Classifier name	Cross-validation with fold = 10				No. of repetitions = 100
	Correctly classified instances		Incorrectly classified instances		Root mean squared error	Kappa statistic
	Number (%)	Percentage	Number (%)	Percentage
C4.5	97.7143	2736	2.2857	64	0.9763	0.0372
MLP	94.5357	2647	5.4643	153	0.9433	0.0556
KNN	99.7143	2792	0.2857	08	0.997	0.0143
Naïve-Bayesian	86.3571	2418	13.6429	382	0.8585	0.0931