Table 10 Performance analysis of proposed model with meta-heuristic based on database 1 (70% variation in training rate).

From: Attention-based hybrid deep learning model with CSFOA optimization and G-TverskyUNet3+ for Arabic sign language recognition

Approaches

Accuracy

Precision

Sensitivity

Specificity

MCC

NPV

F-measure

FPR

FNR

CSFOA (Proposed)

0.98142

0.99201

0.97857

0.98583

0.98328

0.97132

0.97066

0.02235

0.01673

ASO

0.96582

0.95712

0.96245

0.96028

0.95864

0.96172

0.95968

0.03821

0.03755

DHO

0.96045

0.95387

0.95832

0.95714

0.95469

0.95911

0.95609

0.04286

0.04168

PSO

0.95487

0.94895

0.95176

0.95042

0.94839

0.95288

0.95034

0.04958

0.04824

Back to article page