Rama Danudinata, . (2025) PERANCANGAN APLIKASI ANDROID UNTUK REKOMENDASI DAUR ULANG BERDASARKAN DETEKSI SAMPAH PLASTIK MENGGUNAKAN ALGORITMA YOLOv9. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![]() |
Text
ABSTRAK.pdf Download (80kB) |
![]() |
Text
AWAL.pdf Download (615kB) |
![]() |
Text
BAB 1.pdf Restricted to Repository UPNVJ Only Download (240kB) |
![]() |
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (1MB) |
![]() |
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (560kB) |
![]() |
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (8MB) |
![]() |
Text
BAB 5.pdf Download (134kB) |
![]() |
Text
DAFTAR PUSTAKA.pdf Download (142kB) |
![]() |
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (110kB) |
![]() |
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (2MB) |
![]() |
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (25MB) |
![]() |
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (999kB) |
Abstract
Plastic waste is difficult to decompose and causes various environmental damages. Poor plastic waste management has become a significant environmental issue in Indonesia, mainly due to the public's limited ability to sort and recycle plastic waste into reusable products. This research aims to design an Android application capable of providing recycling recommendations based on the automatic detection of plastic waste using the YOLOv9 algorithm. The research stages include training the YOLOv9 model with an annotated plastic waste dataset, converting the model to TensorFlow Lite (TFLite) format, developing the Android application, and integrating the model into the application using the Kotlin programming language. The trained YOLOv9 model demonstrated good detection performance with an mAP50 of 0.93 and mAP50-95 of 0.85. The YOLOv9 model was successfully integrated into the application with an average prediction speed of 2190.1 ms (without GPU) and 2713.8 ms (with GPU). Functional testing showed that all features worked as intended, with a user acceptance rate of 89.28% and a detection success rate of 83.3%, based on Black Box Testing, Cross-Device Testing, and User Acceptance Testing (UAT). These results indicate that the application is effective and compatible across various Android devices.
Item Type: | Thesis (Skripsi) |
---|---|
Additional Information: | [No.Panggil: 2110511096] [Pembimbing 1: Tjahjanto] [Pembimbing 2: Nurul Afifah Arifuddin] [Penguji 1: Musthofa Galih Pradana] [Penguji 2: Kharisma Wiati Gusti] |
Uncontrolled Keywords: | YOLOv9, Android, TFLite, Plastic Waste, Recycling |
Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software |
Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
Depositing User: | RAMA DANUDINATA |
Date Deposited: | 25 Aug 2025 06:23 |
Last Modified: | 25 Aug 2025 06:23 |
URI: | http://repository.upnvj.ac.id/id/eprint/37327 |
Actions (login required)
![]() |
View Item |