<![CDATA[Biomedical waste carries infectious and hazardous risk that makes accurate automated sorting valuable, and object detection offers a path toward automation, yet published studies rarely measure how much online data augmentation contributes once training images carry offline augmentation and mean Average Precision alone can conceal how augmentation shifts the balance between missed detections and false alarms.This study measures the incremental effect of Mosaic, MixUp, and Copy-Paste augmentation on YOLOv11n trained for biomedical waste detection, and verifies whether each augmentation executes as configured. We designed a 2×2×2 factorial ablation across eight configurations, trained YOLOv11n three times per configuration with different random seeds on a 14-class biomedical waste dataset and evaluated each run's best checkpoint on a held-out test set using mean Average Precision, precision, recall, and a corrected confusion matrix retaining the background class. We verified framework behavior through prediction-level identity, loss-level comparison, and instrumented tracing. Configurations combining Mosaic and MixUp raised mean Average Precision by 0.0053 over baseline, MixUp alone raised recall from 0.8950 to 0.9071, and Mosaic with MixUp raised precision to 0.9650. False negatives outnumbered false positives three to one across every configuration, identifying class-versus-background rather than inter-class confusion as the dominant failure mode. Copy-Paste showed zero measurable effect once verified, consistent with its restriction to segmentation tasks in the underlying framework. Online augmentation produces modest but distinguishable, metric-specific gains on pre-augmented biomedical waste data, and verifying framework behavior before attributing results to an augmentation strategy is necessary for reliable reporting.]]>
