Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal ILKOM Jurnal Ilmiah Journal of Mathematics, Computation and Statistics (JMATHCOS)
Hafid, Mega Sartika
Unknown Affiliation
Computer Science & IT Mathematics

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

Found 2 Documents
Search

 1 
Deepfake Image Classification Using ResNet50 Feature Extraction and XGBoost Learning Model Kusnaeni, Kusnaeni; Adriani, Ika Reskiana; Hafid, Mega Sartika; Andy B, Afif Budi; Rizal, Muhammad Edy
Journal of Mathematics, Computations and Statistics Vol. 8 No. 2 (2025): Volume 08 Nomor 02 (Oktober 2025)
Publisher : Jurusan Matematika FMIPA UNM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35580/jmathcos.v8i2.8387

Abstract

Deepfake is an artificial intelligence-based media manipulation technology that realistically fabricates a person's face, voice, and movements in both video and audio formats. The increasing use of deepfakes in the creation of various forms of deceptive content, including pornography, fake news, and fraud, has led to an urgent need for effective detection methods. One of the main challenges in detecting deepfakes is the high quality and realism of synthetic media, which renders conventional detection techniques less effective. Therefore, machine learning techniques capable of recognizing subtle patterns in visual data that are imperceptible to the human eye are required. This study aims to develop a deepfake image detection system using a hybrid machine learning approach that combines ResNet50 for feature extraction and XGBoost for classification. The pre-trained ResNet50 model, originally trained on the large-scale ImageNet dataset, is utilized to extract visual representations from images in the form of feature vectors. These features are then classified using XGBoost to distinguish between authentic and AI-generated images based on subtle patterns embedded within the extracted features. The results demonstrate that this hybrid approach achieves an accuracy of 94.6% in detecting deepfake images by leveraging the deep representation power of CNNs and the advanced classification capabilities of XGBoost. This method is not only computationally efficient but also highly relevant for integration into adaptive digital security systems.
A Hybrid Deep Learning–Machine Learning Approach for the Identification of Active Compounds in Blumea balsamifera (Sembung Leaves) Kusnaeni, Kusnaeni; Prihatin, Prihatin; Rahmatullah, Rahmatullah; Hafid, Mega Sartika; Nisardi, Muhammad Rifki; Nurmalasari, Nurmalasari; Andy B, Afif Budi
ILKOM Jurnal Ilmiah Vol 18, No 1 (2026)
Publisher : Prodi Teknik Informatika FIK Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/ilkom.v18i1.3195.165-179

Abstract

Blumea balsamifera (sembung) is a medicinal plant with well-documented antibacterial, anti-inflammatory, and analgesic properties. However, the systematic identification of its bioactive compounds remains a significant challenge due to the complexity and high dimensionality of LC–MS (Liquid Chromatography–Mass Spectrometry) data. This study aims to develop a robust computational framework for automated compound identification using a hybrid modeling approach.A hybrid model integrating Long Short-Term Memory (LSTM) and Extreme Gradient Boosting (XGBoost) was employed to enhance feature extraction and classification performance. The LSTM component was utilized to capture sequential dependencies in spectral data, while XGBoost performed optimized classification through gradient boosting. This integration enables efficient handling of complex spectral patterns and improves predictive accuracy.The proposed model achieved an accuracy of 91%, demonstrating strong performance in classifying and identifying bioactive compounds. Feature importance analysis identified several key compounds contributing to the model predictions, including Luteolin-7-methyl-ether, Umbelliferone, Blumeatin, Dihydroquercetin-7,4′-dimethylether, Chrysosplenol C, Blumealactone B, and Blumeaene E. These compounds are associated with known pharmacological activities, supporting the therapeutic relevance of B. balsamifera.The proposed hybrid LSTM–XGBoost framework provides an effective and scalable approach for LC–MS-based compound identification. This method reduces analytical complexity, enhances classification reliability, and offers a data-driven strategy for accelerating phytochemical research and bioactive compound validation
Co-Authors Adriani, Ika Reskiana Andy B, Afif Budi Kusnaeni Kusnaeni, Kusnaeni Muhammad Edy Rizal Muhammad Rifki Nisardi Nurmalasari Nurmalasari Prihatin Prihatin, Prihatin Rahmatullah Rahmatullah