Mochammad Adhi Buchori, . (2024) APLIKASI PENDETEKSI SAMPAH DAUR ULANG MENGGUNAKAN ALGORITMA CONVOLUTIONAL NEURAL NETWORK BERBASIS ANDROID. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK_2010511028.pdf Download (117kB) |
|
Text
AWAL_2010511028.pdf Download (4MB) |
|
Text
BAB I_2010511028.pdf Restricted to Repository UPNVJ Only Download (151kB) |
|
Text
BAB II_2010511028.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
BAB III_2010511028.pdf Restricted to Repository UPNVJ Only Download (318kB) |
|
Text
BAB IV_2010511028.pdf Restricted to Repository UPNVJ Only Download (13MB) |
|
Text
BAB V_2010511028.pdf Download (138kB) |
|
Text
DAFTAR PUSTAKA_2010511028.pdf Download (153kB) |
|
Text
DAFTAR RIWAYAT HIDUP_2010511028.pdf Restricted to Repository UPNVJ Only Download (272kB) |
|
Text
LAMPIRAN_2010511028.pdf Restricted to Repository UPNVJ Only Download (934kB) |
|
Text
HASIL PLAGIARISME_2010511028.pdf Restricted to Repository staff only Download (3MB) |
|
Text
ARTIKEL KI_2010511028.pdf Restricted to Repository staff only Download (1MB) |
Abstract
At the end of 2022, the Ministry of Environment and Forestry reported that the total national waste increased from 28.6 million tons to 34.4 million tons compared to the previous year. This increase, accompanied by the community's inability to effectively manage waste, can have detrimental consequences for the environment and public welfare. One solution is to encourage recycling, which allows waste to be reprocessed into something useful according to its type. Therefore, the utilization of digital image processing techniques to help people identify types of recyclable waste for more accurate sorting becomes important. This study aimed to build an Android-based recycling waste detector application using the Convolutional Neural Network (CNN) algorithm. The application is developed by utilizing a smartphone camera to detect recyclable waste based on the images taken to obtain information and ways to sort waste easily. The CNN model was developed using the Inception V3 architecture and trained with a dataset of 1,075 recyclable waste images, including 300 paper, 300 cardboard, 300 plastic, 50 glass, and 125 metal waste items. This study produces an Android-based recycling waste detector application that integrates the CNN model using TensorFlow Lite with a model accuracy of 88% and a prediction speed of around 1 second.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 2010511028] [Pembimbing: Nur Hafifah Matondang] [Penguji 1: Anita Muliawati] [Penguji 2: Ika Nurlaili Isnainiyah] |
| Uncontrolled Keywords: | Recycled Waste, Convolutional Neural Network (CNN), Android |
| Subjects: | T Technology > T Technology (General) |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | MOCHAMMAD ADHI BUCHORI |
| Date Deposited: | 05 Sep 2024 08:12 |
| Last Modified: | 05 Sep 2024 08:12 |
| URI: | http://repository.upnvj.ac.id/id/eprint/30326 |
Actions (login required)
 |
View Item |