Real-time intelligent recycle waste detection and classification using you only look once version 5 / Aiman Syafwan Amran
Recycle waste is an integral part of our daily lives. It generates various type of waste materials in our homes, workplaces and communities. With a growing population and urbanization, it is crucial to prioritize responsible waste management practices to address the environmental challenges faced by...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | en |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://ir.uitm.edu.my/id/eprint/88976/1/88976.pdf https://ir.uitm.edu.my/id/eprint/88976/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1833079690706812928 |
|---|---|
| author | Amran, Aiman Syafwan |
| author_facet | Amran, Aiman Syafwan |
| author_sort | Amran, Aiman Syafwan |
| building | Tun Abdul Razak Library |
| collection | Institutional Repository |
| content_provider | Universiti Teknologi Mara |
| content_source | UiTM Institutional Repository |
| continent | Asia |
| country | Malaysia |
| description | Recycle waste is an integral part of our daily lives. It generates various type of waste materials in our homes, workplaces and communities. With a growing population and urbanization, it is crucial to prioritize responsible waste management practices to address the environmental challenges faced by the country. In Malaysia, the traditional approach to recycle waste detection and classification primarily relies on manual sorting and visual inspection by waste management personnel. When recyclable waste arrives at recycling centers or facilities, workers manually separate the materials based on their visual appearance and physical characteristics. Because of that, this project aims to detect and classify a typed of recycled waste such paper, plastic and metal. It uses YOLOv5 object detection and classification algorithm. This project uses the images of paper, plastic and metal gathered from Kaggle and GitHub dataset. This system was put to two tests of testing which were functionality testing of the whole system and the metric evaluation of the object detection and classification model. The object detection and classification algorithm achieved 91.9% mean average precision in metric evaluation. The system was developed as a web-based system in order to make it easily accessible by the target user which the governance body from any public nor private sectors. The recommendation on the future work is to improve the detection model for it to be able to detect small size object from the image to make the system more reliable. |
| format | Thesis |
| id | my.uitm.ir-88976 |
| institution | Universiti Teknologi Mara |
| language | en |
| publishDate | 2023 |
| record_format | eprints |
| spelling | my.uitm.ir-889762024-03-19T07:07:20Z https://ir.uitm.edu.my/id/eprint/88976/ Real-time intelligent recycle waste detection and classification using you only look once version 5 / Aiman Syafwan Amran Amran, Aiman Syafwan TD Environmental technology. Sanitary engineering Recycle waste is an integral part of our daily lives. It generates various type of waste materials in our homes, workplaces and communities. With a growing population and urbanization, it is crucial to prioritize responsible waste management practices to address the environmental challenges faced by the country. In Malaysia, the traditional approach to recycle waste detection and classification primarily relies on manual sorting and visual inspection by waste management personnel. When recyclable waste arrives at recycling centers or facilities, workers manually separate the materials based on their visual appearance and physical characteristics. Because of that, this project aims to detect and classify a typed of recycled waste such paper, plastic and metal. It uses YOLOv5 object detection and classification algorithm. This project uses the images of paper, plastic and metal gathered from Kaggle and GitHub dataset. This system was put to two tests of testing which were functionality testing of the whole system and the metric evaluation of the object detection and classification model. The object detection and classification algorithm achieved 91.9% mean average precision in metric evaluation. The system was developed as a web-based system in order to make it easily accessible by the target user which the governance body from any public nor private sectors. The recommendation on the future work is to improve the detection model for it to be able to detect small size object from the image to make the system more reliable. 2023 Thesis NonPeerReviewed text en https://ir.uitm.edu.my/id/eprint/88976/1/88976.pdf Real-time intelligent recycle waste detection and classification using you only look once version 5 / Aiman Syafwan Amran. (2023) Degree thesis, thesis, Universiti Teknologi MARA, Melaka. <http://terminalib.uitm.edu.my/88976.pdf> |
| spellingShingle | TD Environmental technology. Sanitary engineering Amran, Aiman Syafwan Real-time intelligent recycle waste detection and classification using you only look once version 5 / Aiman Syafwan Amran |
| title | Real-time intelligent recycle waste detection and classification using you only look once version 5 / Aiman Syafwan Amran |
| title_full | Real-time intelligent recycle waste detection and classification using you only look once version 5 / Aiman Syafwan Amran |
| title_fullStr | Real-time intelligent recycle waste detection and classification using you only look once version 5 / Aiman Syafwan Amran |
| title_full_unstemmed | Real-time intelligent recycle waste detection and classification using you only look once version 5 / Aiman Syafwan Amran |
| title_short | Real-time intelligent recycle waste detection and classification using you only look once version 5 / Aiman Syafwan Amran |
| title_sort | real-time intelligent recycle waste detection and classification using you only look once version 5 / aiman syafwan amran |
| topic | TD Environmental technology. Sanitary engineering |
| url | https://ir.uitm.edu.my/id/eprint/88976/1/88976.pdf https://ir.uitm.edu.my/id/eprint/88976/ |
| url_provider | http://ir.uitm.edu.my/ |