Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal Sistemasi: Jurnal Sistem Informasi Journal of Embedded Systems, Security and Intelligent Systems
Resky Ayu Dewi Talasari
Universitas Fajar
Computer Science & IT Electrical & Electronics Engineering

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Analyzing the Impact of Data Filtering on Anomaly Detection under Distribution Shift Conditions Resky Ayu Dewi Talasari; Ayutri Wahyuni
Journal of Embedded Systems, Security and Intelligent Systems Vol 6, No 3 (2025): September 2025
Publisher : Program Studi Teknik Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jessi.v6i3.10051

Abstract

One of the main challenges in anomaly detection for Windows Event Logs and Sysmon is distribution shift, where changes in data distribution invalidate the model's learned normality reference. This study evaluates how data filtering setting value boundaries classified as normal affects the model's ability to handle distribution shifts across three experimental scenarios. This research is among the first to systematically quantify the trade-off between filtering efficiency and model adaptability across varying magnitudes of distribution shifts in anomaly detection systems. The experimental design employs three scenarios: Scenario 1 evaluates filtering under complete cross-environment shift using Dataset A for training and Dataset B for testing, Scenario 2 examines filtering with partial Dataset B training data, and Scenario 3 validates model adaptability without filtering constraints. The goal is to determine whether filtering improves performance under small, adaptable shifts and to measure its impact under large shifts that push the distribution far from the initial training data. Shift magnitude is measured using Jensen Shannon Divergence and Hellinger Distance, followed by evaluation of model performance through precision, recall and F1-score. Results show that filtering can help for minor shifts but substantially impairs adaptation under substantial distributional changes: filtered models remain constrained by prior baseline behavior and fail to learn new patterns, while unfiltered models adapt successfully and maintain accurate detection. These findings suggest critical implications for designing adaptive anomaly detection systems in dynamic operational environments where changes frequently alter normal behavior patterns. Future approaches should incorporate adaptive filtering mechanisms that dynamically adjust baseline boundaries rather than relying solely on static training data distributions.
Multi-Class Skin Disease Classification using Transfer Learning and Explainable AI Ayutri Wahyuni; Resky Ayu Dewi Talasari; Muhammad Syawal Idil Fitrah Baharuddin
SISTEMASI Vol 15, No 6 (2026): Sistemasi: Jurnal Sistem Informasi
Publisher : Universitas Islam Indragiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v15i6.6505

Abstract

This study investigates the application of transfer learning and Explainable Artificial Intelligence (XAI) for multi-class skin disease classification. The dataset was obtained from the Kaggle Skin Diseases Image Dataset and consists of 29,153 original images spanning 10 skin disease classes. To reduce the bias introduced by class imbalance, the dataset was balanced through directed undersampling, resulting in 12,000 images, with 1,200 images per class. Three pretrained convolutional neural network (CNN) architectures—EfficientNetB0, ResNet50, and DenseNet201—were implemented and evaluated using a confusion matrix, accuracy, precision, recall, and F1-score. The experimental results demonstrate that DenseNet201 achieved the highest classification performance, with an accuracy of 0.8779, precision of 0.8751, recall of 0.8748, and F1-score of 0.8745, outperforming ResNet50 (accuracy: 0.8629) and EfficientNetB0 (accuracy: 0.8269). Model interpretability was investigated using Grad-CAM, SHAP, and LIME. Grad-CAM highlighted that the models primarily focused on the central and peripheral regions of skin lesions during prediction. SHAP identified the dominant contribution of lesion regions and pigmentation patterns to the classification process, while LIME emphasized the importance of local superpixels associated with lesion boundaries, color, and texture in supporting the model's predictions. The findings indicate that combining transfer learning with Explainable AI provides a promising foundation for developing clinical decision support systems for dermatological image classification. Future research should incorporate external dataset validation, more robust class balancing strategies, and clinical interpretation by dermatology experts to facilitate the deployment of such systems in real-world healthcare settings.
Phishing URL Detection Using URL Characteristics: A Multi-Algorithm Machine Learning and Explainable AI (XAI) Approach Resky Ayu Dewi Talasari; Eka Alifia Kusnanti
Journal of Embedded Systems, Security and Intelligent Systems Vol 7 No 2 (2026): June 2026
Publisher : Program Studi Teknik Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jessi.v7i2.12398

Abstract

Purpose – This study aims to develop and evaluate a phishing URL detection system using URL-based characteristics and multiple machine learning algorithms, while integrating Explainable Artificial Intelligence (XAI) to improve model transparency. Design/methods/approach – The study used 24,390 URLs consisting of 4,878 phishing URLs and 19,512 legitimate URLs collected from a public Kaggle dataset and manually collected sources. Thirteen URL-based features were extracted, including URL length, protocol usage, number of subdomains, domain length, IP address usage, and suspicious keywords. Six machine learning algorithms were compared: Random Forest, XGBoost, Decision Tree, Support Vector Machine, Logistic Regression, and Naïve Bayes. The dataset was evaluated using an 80:20 stratified train-test split, and model performance was measured using accuracy, precision, recall, F1-score, and confusion matrix. XAI was implemented using model-based feature importance and SHAP local explanations. Findings – XGBoost achieved the best overall performance with 97.89% accuracy, 93.09% precision, 96.62% recall, and 94.82% F1-score for the phishing class, followed closely by Random Forest. Feature importance analysis showed that protocol usage, suspicious keywords, and domain length were the most influential features. SHAP explanations further demonstrated that phishing predictions were influenced by the combined contribution of multiple URL characteristics. Research implications/limitations – The findings indicate that ensemble-based machine learning combined with explainable output can support transparent phishing URL screening. However, the study was limited to URL-based features, a fixed train-test split, and manually validated URLs without systematic verification from external threat-intelligence platforms. Originality/value – This study contributes by combining multi-algorithm phishing URL detection, URL-characteristic-based feature analysis, SHAP-based explanation, whitelist checking, and typosquatting indicators within an interpretable cybersecurity detection approach.
Co-Authors Ayutri Wahyuni Eka Alifia Kusnanti Muhammad Syawal Idil Fitrah Baharuddin