Skip to main content
[Preprint]. 2025 May 15:arXiv:2505.09993v1. [Version 1]

Table 1.

The table summarizes the model’s performance metrics across all five classes regarding precision, recall, and F1-score. Class 0 and Class 4 achieved perfect scores (1.0) across all metrics, indicating flawless classification. Class 1 and Class 3 were also predicted with high accuracy, with F1-scores of 0.98 and 0.97, respectively. Class 2 had the lowest performance but achieved solid values (0.91 for all three metrics). The overall model performance was strong, with an accuracy of 0.98. The macro and weighted averages confirm consistent and balanced performance across the dataset.

Precision Recall F1-Score Support
Class 0 1.0 1.0 1.0 27
Class 1 0.97 0.98 0.98 61
Class 2 0.91 0.91 0.91 11
Class 3 1.0 0.95 0.97 19
Class 4 1.0 1.0 1.0 8
accuracy 0.98 126
macro avg 0.98 0.97 0.97 126
weighted avg 0.98 0.98 0.98 126