Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Journal Zetroem (JUPI) Jurnal Pendidikan Indonesia
Mohammad Zainuddin
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Comparison of CNN, ResNet50, and Xception for Deepfake Image Detection Rachmat; Mohammad Zainuddin; Handini Arga Damar Rani
ZETROEM Vol 8 No 1 (2026): ZETROEM
Publisher : Prodi Teknik Elektro Universitas PGRI Banyuwangi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36526/ztr.v8i1.7524

Abstract

This study compares the performance of three deep learning architectures—Convolutional Neural Network , ResNet50, and Xception—for frame-based deepfake image detection and identifies the most effective model in terms of accuracy, precision, recall, F1-score, and generalization. The study followed the Knowledge Discovery in Databases (KDD) framework using the Deepfake Detection Dataset (DFD Entire Original) from Kaggle, which consists of 3,432 videos, including 3,068 fake and 364 real videos. Videos were converted into frames using OpenCV, followed by face detection and cropping using MTCNN. The resulting face images were resized to 224×224 pixels, normalized, augmented, and labeled. To reduce classification bias caused by class imbalance, the training data were balanced using random undersampling, resulting in real frames and  fake frames. The dataset was then split into training, validation, and testing sets using a stratified 60:20:20 ratio. The results show that Xception achieved the best performance among the three models, with an accuracy of 95.21%, precision of 0.95, recall of 0.95, and F1-score of 0.95, followed by ResNet50 with an accuracy of 93.42% and CNN with an accuracy of 87.65%. These findings indicate that transfer learning-based architectures, particularly Xception, are more effective than conventional CNNs for deepfake image detection under a consistent experimental setting. This study is limited to a single dataset and frame-based evaluation, thus future work will explore the potential of hybrid models, such as Vision Transformer (ViT) combined with Capsule Networks , to improve detection performance and address challenges like temporal analysis and cross-dataset validation.
TELAAH FILSAFAT PENDIDIKAN ISLAM DALAM PENDIDIKAN KARAKTER : STUDI FENOMENOLOGI DI SDN CURAHMALANG III Mochammad Ridho Alamsyah; Sigit Wibowo; Mohammad Zainuddin
(JUPI) Jurnal Pendidikan Indonesia Vol 3 No 1 (2025): Edisi Maret
Publisher : Lembaga Pendidikan dan Pelatihan Sindotech

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Pendidikan karakter merupakan pondasi penting untuk kesuksesan individu di masa depan. Namun, apakah pendidikan karakter yang dilakukan sudah sesuai dengan landasan filosofis pendidikan islam. Dalam penelitian ini dilakukan dengan metode studi fenomenologi pada SDN Curahmalang III. Dengan teknik pengumpulan data berupa wawancara, observasi langsung, dan studi dokumentasi. Analisis data dilakukan dengan mereduksi, penyajian data dalam bentuk naratif, dan menyimpulkan. Didapatkan hasil bahwa pendidikan karakter yang dilakukan pada SDN Curahmalang III tersebut sudah sesuai dengan landasan filosofis dari sudut pandang pendidikan islam dalam menjalankan upaya mendidik karakter siswa. Meliputi nilai-nilai kepemimpinan, kolaborasi, ukhuwah islamiyah, kedisiplinan, dan belajar sepanjang hayat. Dengan berbagai program yang dilakukan seperti baris - berbaris, melaksanakan piket rutin, melakukan sistem yang mendukung siswa untuk berkompetisi, dan melakukan kegiatan P5 dengan cara berkolaborasi dengan wali murid. Namun, masih ada kendala-kendala dalam pelaksanaan program-program tersebut seperti ketepatan waktu dari para wali murid dan jadwal pelaksanaan yang dibuat oleh para guru masih belum menentu dan dapat berubah-ubah.
Co-Authors Handini Arga Damar Rani Mochammad Ridho Alamsyah Rachmat Sigit Wibowo