1Department of Computer Science, Universitas Brawijaya, Indonesia
2Faculty of Computer Science, Universitas Brawijaya, Jl. Veteran No.8, Ketawanggede, Kec. Lowokwaru, Kota Malang, Indonesia 65145, Indonesia
BibTex Citation Data :
@article{JTSISKOM14045, author = {William Hutamaputra and Rifky Krisnabayu and Marrisaeka Mawarni and Novanto Yudistira and Fitra Bachtiar}, title = {Perbandingan Convolutional Neural Network VGG16 dan ResNet34 pada Sistem Klasifikasi Sampah Botol}, journal = {Jurnal Teknologi dan Sistem Komputer}, volume = {10}, number = {2}, year = {2022}, keywords = {klasifikasi; CNN; VGG16; ResNet34}, abstract = {Hampir semua botol minuman kemasan yang beredar di masyarakat terbuat dari bahan plastik dikarenakan plastik merupakan bahan yang murah dan mudah dibentuk. Plastik adalah bahan non-organik yang sulit diuraikan sehingga botol plastik dapat menyebabkan pencemaran lingkungan. Sehingga diperlukan suatu solusi yang efektif untuk mengatasi kerusakan lingkungan yang disebabkan oleh sampah botol plastik. Salah satu solusi yag dapat dilakukan yaitu melakukan klasifikasi dan daur ulang sampah botol plastik. Pengklasifikasian sampah botol plastik dan sampah botol bukan plastik ke dalam kategori yang ditentukan sesuai dengan persyaratan kemudian didaur ulang agar dapat diolah kembali agar tidak merusak lingkungan. Artikel ini mengusulkan model VGG16 dan ResNet34 berbasis deep learning menggunakan CNN (Convolutional Neural Network) untuk mengidentifikasi dan mengklasifikasikan sampah botol. Berdasarkan hasil pengujian menggunakan Convolutional Neural Network, arsitektur VGG16 memiliki akurasi sebesar 90% dan ResNet34 memiliki akurasi sebesar 50% pada klasifikasi botol plastik dan bukan botol plastik. Masing-masing arsitektur menggunakan 10 epoch, 32 batch, 1655 gambar.}, issn = {2338-0403}, pages = {136--142} doi = {10.14710/jtsiskom.2021.14045}, url = {https://jtsiskom.undip.ac.id/article/view/14045} }
Refworks Citation Data :
Article Metrics:
Last update:
Last update: 2024-12-23 09:16:10
Starting from 2021, the author(s) whose article is published in the JTSiskom journal attain the copyright for their article and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. By submitting the manuscript to JTSiskom, the author(s) agree with this policy. No special document approval is required.
The author(s) guarantee that:
The author(s) retain all rights to the published work, such as (but not limited to) the following rights:
Suppose the article was prepared jointly by more than one author. Each author submitting the manuscript warrants that all co-authors have given their permission to agree to copyright and license notices (agreements) on their behalf and notify co-authors of the terms of this policy. JTSiskom will not be held responsible for anything arising because of the writer's internal dispute. JTSiskom will only communicate with correspondence authors.
Authors should also understand that their articles (and any additional files, including data sets and analysis/computation data) will become publicly available once published. The license of published articles (and additional data) will be governed by a Creative Commons Attribution-ShareAlike 4.0 International License. JTSiskom allows users to copy, distribute, display and perform work under license. Users need to attribute the author(s) and JTSiskom to distribute works in journals and other publication media. Unless otherwise stated, the author(s) is a public entity as soon as the article is published.