Waste Classification Using Artificial Intelligence Techniques:Literature Review

Abstract

waste is the total remnants of domestic, agricultural, industrial and productive human activities, all the trash left somewhere, the neglect of which threatens and harms public safety. Waste is divided into many types such as: Non-biodegradable waste, Hazardous waste, Industrial waste, Municipal solid waste, Agricultural waste.
 Organic waste: It is fermentable waste such as food scraps and garden waste. Inorganic waste: It is waste that does not contain organic compounds, such as plastic, metals, and clothes. Also Solid waste: like mineral or glass materials, and it results from domestic, industrial and agricultural waste. It needs hundreds of years to decompose, and its presence poses an environmental threat. The efficiency and accuracy of conventional trash classification techniques are both low, Waste classification is the process of identifying and categorizing different types of waste based on their characteristics. Accurate waste classification is important for a number of reasons, including supporting recycling and other forms of resource recovery, protecting the environment and human health, and reducing the costs of waste management. Additionally, because of the vast amount of waste, unskilled people separate rubbish, which is less exact, takes more time, and isn't entirely practicable. Artificial intelligence and image processing, two powerful computing techniques, have advanced and now offer a variety of solutions. However, the current waste classification models still have several issues, such as poor classification accuracy or lengthy run times, because various wastes require various methods of disposal. The existing waste classification models driven by deep learning are not easy to achieve accurate results and still need to be improved due to the various architecture networks adopted. Aimed at solving these problems. Several methods and modules have been reviewed with the advantages of each are listed in Table 1.