Health Care Waste Classification Using Deep Learning Aligned with Nepal's Bin Color Guidelines

TL;DR

This paper evaluates deep learning models for health care waste classification in Nepal, achieving high accuracy and aligning with local bin color standards to improve waste segregation and safety.

Contribution

It benchmarks multiple state-of-the-art models for HCW classification and deploys the best model with local color coding standards in Nepal.

Findings

YOLOv5-s achieved 95.06% accuracy.

YOLOv8-n was faster but less accurate.

EfficientNet-B0 showed high accuracy but longer inference time.

Abstract

The increasing number of Health Care facilities in Nepal has added up the challenges on managing health care waste (HCW). Improper segregation and disposal of HCW leads to contamination, spreading of infectious diseases and risk for waste handlers. This study benchmarks the state of the art waste classification models: ResNeXt-50, EfficientNet-B0, MobileNetV3-S, YOLOv8-n and YOLOv5-s using stratified 5-fold cross-validation technique on combined HCW data. YOLOv5-s achieved the highest accuracy (95.06%) but fell short with the YOLOv8-n model in inference speed with few milliseconds. The EfficientNet-B0 showed promising results of 93.22% accuracy but took the highest inference time. Following a repetitive ANOVA test to confirm the statistical significance, the best performing model (YOLOv5-s) was deployed to the web with bin color mapped using Nepal's HCW management standards. Further work is suggested to address data limitation and ensure localized context.