Deep Learning-based Classification of Materials into Biodegradable and Non-Biodegradable

Abstract

 The collection of real-time data from  people, their cars, public transit, buildings, and other urban  infrastructures like the energy grid and waste management  systems are at the heart of the smart city concept. The  insights gathered from the data may be used by municipal  authorities to manage resources and services efficiently.  An important study topic at the same time is the sharp  increase in environmental degradation and deterioration  that causes ecological imbalance. Additionally, the  development of advanced waste management systems that  can categorize rubbish according to its level of  biodegradability is required for the worldwide expansion  of smart cities. Some of the more common ones are paper,  paper boxes, food, glass, and other garbage. A cost effective technique to separate the waste from the  enormous mountain of trash and garbage and classify the  waste items is to use computer vision-based technologies.  Recent developments in deep learning (DL) and deep  reinforcement learning (DRL) have made it possible to  categorize waste objects and identify and detect trash. In  this sense, the research creates an intelligence model for  smart cities. The technique's goal is to recognize and  classify rubbish objects using the DL and DRL approaches.  The two steps of the SYSTEM technique are objected classification based on DRL and object detection based on  Mask Regional Convolutional Neural Network (CNN)… The CNN model uses the DenseNet model as a baseline  model, and a deep learning network (DLN) is employed as  the classifier. A based hyperparameter optimizer is also  created to boost the efficiency of the DenseNet model.