Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Mandalika Mathematics and Educations Journal Journal of Mathematics, Computation and Statistics (JMATHCOS)
Ika Reskiana Adriani
Institut Teknologi Bacharuddin Jusuf Habibie
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; Ika Reskiana Adriani; Mega Sartika Hafid; Afif Budi Andy B; Muhammad Edy Rizal
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.
Quantifying Food Deficit Risk under Seasonal Climate Variability Using a Compound Periodic Poisson Process Ika Reskiana Adriani; Irmayani Irmayani; Husnul Hatimah; Putri Anatasya
Mandalika Mathematics and Educations Journal Vol 8 No 3 (2026): Edisi September
Publisher : FKIP Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jm.v8i3.12907

Abstract

Climate variability has increased the frequency of extreme weather events, leading to greater uncertainty in agricultural production and a higher risk of food production deficits. Existing studies predominantly employ deterministic or econometric approaches that estimate average production changes without explicitly quantifying stochastic production risk. This study proposes a compound periodic Poisson process framework to quantify climate induced food production risk by integrating periodic event occurrence, stochastic loss severity, aggregate production loss, and food deficit probability within a unified actuarial framework. The occurrence extreme rainfall events are modelled using a periodic Poisson process, while production loss severity follows a Lognormal distribution. Model parameters are estimated using Maximum Likelihood Estimation, and food deficit probabilities are evaluated analytically. The estimated seasonal intensity ranges from 25 to 53 events per month during the rainy season to 1 event per month during the dry season. The expected aggregate production loss is 18.420 tons per planting season. For a critical production loss threshold of 25.000 tons, the estimated probability of food production deficit is 17,6%, corresponding to a return period of 5,68 planting seasons. These results demonstrate that the proposed compound periodic Poisson process provides a robust probabilistic framework for agricultural risk assessment, food security analysis, and climate based agricultural insurance.
Co-Authors Afif Budi Andy B Husnul Hatimah Irmayani Irmayani Kusnaeni Kusnaeni Mega Sartika Hafid Muhammad Edy Rizal Putri Anatasya