Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Coreid Journal Smatika Jurnal : STIKI Informatika Jurnal
Muhammad Deden Firdaus
UIN Sunan Gunung Djati Bandung
Computer Science & IT

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

Found 2 Documents
Search

 1 
Klasifikasi Fake dan Real Menggunakan Vision Transformer dan EfficientNet-B0 pada Gambar Asli dan Generatif AI M. Syahrul Anwar Aria; Cepy Slamet; Muhammad Deden Firdaus
SMATIKA JURNAL : STIKI Informatika Jurnal Vol 15 No 01 (2025): SMATIKA Jurnal : STIKI Informatika Jurnal
Publisher : LPPM UBHINUS MALANG

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32664/smatika.v15i01.1531

Abstract

Advances in artificial intelligence (AI) technology have enabled the creation of synthetic images that resemble real images, posing challenges in detecting and classifying such images. This study aims to develop an EfficientNet-B0 and Vision Transformer (ViT) based classification model to distinguish between real images and images generated by generative AI. The data used consists of 30,401 original images from the MSCOCO 2017 dataset and 30,401 generative AI-generated images from the SyntheticEye AI-Generated Images Dataset on Kaggle. The results showed that the ViT model achieved 98% accuracy and EfficientNet-B0 achieved 96% accuracy in classifying the images. The conclusion of this research is that both models have great potential in detecting digital media manipulation, with ViT showing superior performance. The practical implication of this research is the development of more advanced technologies for detecting generative images, which can be used in various real applications such as digital security and media verification.
Comparison of Long Short-Term Memory and Recurrent Neural Network For Stock Market Price Movement Classification in Islamic Bank Finance Rijki Rijki; Yana Aditia Gerhana; Gitarja Sandi; Muhammad Deden Firdaus; Eva Nurlatifah
CoreID Journal Vol. 4 No. 1 (2026): March 2026
Publisher : CV. Generasi Intelektual Digital

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60005/coreid.v4i1.152

Abstract

This study addresses the importance of accurate stock price prediction in the Islamic finance sector, where reliable forecasting supports better investment decisions and market stability. Despite the growing use of deep learning methods, comparative studies on sequential models in this domain remain limited. Therefore, this research compares the performance of Long Short-Term Memory (LSTM) and Recurrent Neural Network (RNN) models for classifying stock price movement direction of Islamic banks in Indonesia. The dataset was sourced from two Islamic banks in Indonesia, covering the period from 2022 to mid-2024, with features such as Open, High, Low, Close, Adjusted Close, and Volume. The CRISP-DM method was applied for data processing, and testing was performed with data splits of 60:40, 70:30, and 80:20, as well as epoch variations (30, 50, 80). Results indicate that RNN outperforms LSTM, with the highest accuracy of 58% for RNN and 53% for LSTM. Evaluation metrics also included precision, recall, and F1-score. In conclusion, RNN performs better for stock movement classification direction, while LSTM is more effective for minimizing prediction error.
Co-Authors Cepy Slamet Eva Nurlatifah Gitarja Sandi M. Syahrul Anwar Aria Rijki Rijki Yana Aditia Gerhana