Dian Ayu Setiawati, . (2025) KLASIFIKASI CITRA SAMPAH ELEKTRONIK MENGGUNAKAN ALGORITMA CONVOLUTIONAL NEURAL NETWORK ARSITEKTUR RESNET-50 DENGAN HYPERPARAMETER TUNING. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (237kB) |
|
Text
AWAL.pdf Download (918kB) |
|
Text
BAB 1.pdf Restricted to Repository UPNVJ Only Download (453kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (822kB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (2MB) |
|
Text
BAB 5.pdf Download (432kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (444kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (135kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (4MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (22MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (1MB) |
Abstract
The rapid development of technology has increased the demand and use of electronic products, which also contributes to the growing volume of electronic waste. Indonesia ranked fourth in Asia and first in Southeast Asia as the largest e-waste producing country in 2022, with a total production of 1.9 billion kg. However, e-waste management in Indonesia remains suboptimal. A major challenges lies in the collection and recycling processes, which are still conducted without proper classification due to the lack of systematic and technological approaches. In fact, classification based on waste type is a crucial initial stage once e-waste enters the recycling industry. In response to this issue, this study aimed to develop an electronic waste image classification system to accurately identify waste categories. This study applied the Convolutional Neural Network (CNN) with the ResNet-50 architecture and hyperparameter tuning to optimize model performance. Experiments were conducted in six scenarios with variations of original data, undersampling, and augmentation, along with manual and automated hyperparameter selection approaches using Random Searchand Bayesian Optimization. The best result was achieved using augmented data and Bayesian Optimization, resulting in 94.24% test accuracy and 19.73% loss. These findings highlight the importance of data diversity and effective tuning strategies.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 2110511107] [Pembimbing 1: Ridwan Raafi'udin] [Pembimbing 2: Catur Nugrahaeni Puspita Dewi] [Penguji 1: Neny Rosmawarni] [Penguji 2: Nurul Afifah Arifuddin] |
| Uncontrolled Keywords: | Convolutional Neural Network, Hyperparameter Tuning, Klasifikasi Citra, ResNet-50, Sampah Elektronik |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software T Technology > T Technology (General) T Technology > TD Environmental technology. Sanitary engineering |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | DIAN AYU SETIAWATI |
| Date Deposited: | 06 Aug 2025 06:41 |
| Last Modified: | 06 Aug 2025 06:41 |
| URI: | http://repository.upnvj.ac.id/id/eprint/37370 |
Actions (login required)
 |
View Item |