A Household Solid Waste Sorting And Recognition Recycling System

• Main Author: Yew, Jia Yie
• Format: Undergraduates Project Papers
• Language: English
• Published: 2022
• Subjects: QA75 Electronic computers. Computer science; QA76 Computer software
• Online Access: http://umpir.ump.edu.my/id/eprint/40178/1/CA19068.pdf; http://umpir.ump.edu.my/id/eprint/40178/

Low recycling and low sorting rate are the long-term problems not only in Malaysia but all the developing country like Vietnam and Thailand. However, this project was focused on the recycling and sorting problem in Malaysia only. The proposed application is specially designed for Malaysian. With a population of 32 million, Malaysia generates more than 28000 metric tonnes of solid waste everyday. Surprisingly, only 10% of it are collected for recycling purpose. What is more, the single-stream recycling system practiced among Malaysia results in more contamination and low quality of recyclable solid waste. Hence, the proposed application is developed to stop these two problems. The objectives of this project are to identify the current limitation of the existing application of the recycling system, develop a mobile application that helps provide information regarding sorting recycled solid waste into categories based on image recognition using a neural network and evaluate the functionalities of the proposed system. After research done on three existing applications, it can be found that the existing applications will only focus more in sorting the household solid waste. However, for this proposed application, the Places API is implemented so that nearby recycling location are provided to the users and they can know where to send their recyclable waste. For those recyclable waste that cannot send by the user themselves, they can book a doorstep collection from the recycling center. Agile methodology consisting of requirements phase, design phase, develop phase, test phase, and deploy phase will be implemented for the development of the proposed application. Lastly, a User Acceptance Test were conducted in order to detect any defects of the proposed application. Current market in Malaysia still lack of this kind of recycling and sorting mobile application that helps push forward the milestones of recycling and sorting. That why I am here to contribute my effort to do so. The proposed application's expected outcome is to witness an increase in the number of persons participating in recycling activities. Perhaps these can reduce the household solid waste generated by Malaysian and indirectly contribute to a clean and safe environment. The second expected outcome is to public involved in the dual-stream recycling system and help collect more pure material and higher recycled waste recovery. Future work that needs to be done includes increasing dataset of machine learning training model of household solid waste from 30 to 100 so that diverse household solid waste can be scanned by the user. The second improvement can be let the user manual adjust the searching area (radius) of nearby recycling location.