Waste generation is a continuous process that needs to be managed effectively to ensure environmental safety and public health. The recent circular economy (CE) practices have brought a new shape for the waste management industry, creating value from the generated waste. The shift to a CE represents one of the most significant challenges, particularly in sorting and classifying generated waste. Addressing these challenges would facilitate the recycling industry and helps in promoting remanufacturing. But in the COVID times, most of the generated waste is getting mixed with conventional waste types, especially in the global south. The pandemic has resulted in colossal infectious waste generation. Its handling became the most significant challenge raising fears and concerns over sorting and classifying. Hence, this study proposes an Artificial Intelligence (AI) based automated solution for sorting COVID related medical waste streams from other waste types and, at the same time, ensures data-driven decisions for recycling in the context of CE. Metal, paper, glass waste categories, including the polyethylene terephthalate (PET) waste from the pandemic, are considered. The waste type classification is done based on the image-texture-dependent features, which provided an accurate sorting and classification before the recycling process starts. The features are fused using the proposed decision-level feature fusion scheme. The classification model based on the support vector machine (SVM) classifier performs best (with 96.5 % accuracy, 95.3 % sensitivity, and 95.9 % specificity) in classifying waste types in the context of circular manufacturing and exhibiting the abilities to manage the COVID related medical waste mixed.

废物产生是一个持续的过程，需要有效管理以确保环境安全和公众健康。最近的循环经济 (CE) 实践为废物管理行业带来了新的形态，从产生的废物中创造价值。向 CE 的转变代表了最重大的挑战之一，特别是在对产生的废物进行分类和分类方面。解决这些挑战将促进回收行业的发展，并有助于促进再制造。但是在 COVID 时代，大部分产生的废物都与传统的废物类型混合在一起，尤其是在全球南方。大流行导致了巨大的传染性废物产生。它的处理成为最重大的挑战，引起人们对分类和分类的恐惧和担忧。因此，这项研究提出了一种基于人工智能 (AI) 的自动化解决方案，用于从其他废物类型中对 COVID 相关医疗废物流进行分类，同时确保在 CE 背景下进行数据驱动的回收决策。金属、纸张、玻璃废物类别，包括大流行产生的聚对苯二甲酸乙二醇酯 (PET) 废物，都被考虑在内。废物类型分类是基于图像纹理相关的特征进行的，这在回收过程开始之前提供了准确的分类和分类。使用建议的决策级特征融合方案融合特征。基于支持向量机 (SVM) 分类器的分类模型表现最佳（准确率为 96.5%，灵敏度为 95.3%，灵敏度为 95.