Visual analytics using artificial intelligence (garbage classification by deep learning network)

• Main Author: Leow, Kang Kiat
• Other Authors: Yap Kim Hui
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2023
• Subjects: Engineering::Electrical and electronic engineering
• Online Access: https://hdl.handle.net/10356/167221
• Institution: Nanyang Technological University

Singapore has a growing population approaching 6 million. With the growth in population, it leads to the increasing amount of waste generated. In order to protect the earth’s ecological environment along with reducing the waste generated, Singapore have been sorting the waste to reuse and recycle these materials. Currently, waste classification is done manually which has some disadvantages such as low sorting efficiency, high labour intensity and poor working environment. With the advancement of technology, significant progress been made in image classification with the use of deep learning. Currently, most researchers are exploring the use of deep learning technology for garbage classification and have created different methods to identify the image detected in an attempt to improve sorting efficiency. In the early stage of this project, the author will investigate and analyse different types of deep learning technology and datasets available. Thereafter, two different datasets will be chosen and tested with the different deep learning technology for the project. After the testing of the different datasets and deep learning technology, the accuracy and loss rate of the result will be compared.