<![CDATA[Plastic waste is a significant environmental concern, constituting a major portion of the global waste stream. Improper disposal and accumulation have led to severe environmental challenges, including pollution, harm to marine life, and contributions to climate change. Effective waste management strategies are essential to mitigate these issues. However, manual sorting methods are both time-consuming and costly, requiring substantial human effort and financial investment. To address these limitations, automated solutions utilizing advanced technologies like artificial intelligence have gained increasing attention. Deep learning-based method can automatically identify and classify various types of plastic waste using computer-captured image patterns. This study explores the application of ResNet50, a state-of-the-art deep learning model, for the classification of plastic and non-plastic waste. A robust dataset comprising 4,000 diverse images of waste materials was employed for model training and validation. ResNet50, with its advanced architecture designed for image recognition tasks, demonstrated exceptional performance, achieving an accuracy, precision, recall, and F1-score of 0.99. These results highlight the model’s ability to precisely and reliably differentiate between plastic and non-plastic waste categories. The findings of this research underscore the potential of deep learning-based approaches in revolutionizing waste management practices. By leveraging automated classification methods, waste sorting can become significantly faster, more accurate, and cost-effective. This has far-reaching implications reducing environmental harm and fostering a more sustainable future. The results demonstrate that integrating AI technologies into waste management systems can lead to efficient and environmentally friendly solutions for tackling plastic waste challenges.]]>
