This report delves into the application of a Deep Neural Network (DNN) architecture for enhancing food waste segregation through automated systems. It begins by outlining the societal impact of food wastage, the challenges faced by manual labor in waste management, and the potential of recycling food waste for various purposes like animal feed and energy generation. The study then highlights the problems associated with manual waste segregation and proposes a DNN-based automated system as a solution. The research aims to assess the feasibility of creating such a system, determine the types of classification it should perform, and identify the most suitable deep learning architecture. The report includes a literature review on artificial neural networks and convolutional neural networks (CNNs), explaining their advantages in food waste segregation. It details the methodology of the CNN architecture, emphasizing how deep learning addresses the research objectives. The proposal covers the background of the study, problem statement, research rational, aims and objectives, research questions, research hypothesis, literature review, research methods, and the implementation and deployment of the automated system. The report concludes with research findings, and a timeline of the study.
![[object Object]](/_next/static/media/star-bottom.7253800d.svg)
