Design and Implementation of a Machine Learning-Based Malware Detection System Based on healthcare systems
Tamjeed Journal of Healthcare Engineering and Science Technology · 30.06.2026 · 4 (1) · 53-76
DOI: 10.59785/733cpq03 ↗Kurz gefasst
Fachartikel in der Zeitschrift Tamjeed Journal of Healthcare Engineering and Science Technology, online erschienen am 30.06.2026. Verfasst von Yi Zhu Shi Liu. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The aim of this study is to design and evaluate a machine learning–based system for detecting malicious network traffic that leaks data from infected systems. A realistic dataset was constructed using packet capture (PCAP) files, from which 100 flow-based features were extracted using Python and Tshark. The final dataset comprised 16,221 network flows, including 14,629 normal and 1,592 malicious instances. Multiple machine learning and deep learning models—ANN, Deep Learning, SVM, kNN, Decision Tree, AdaBoost, Naïve Bayes, and Random Forest—were trained and evaluated using 10-fold cross-validation. Experimental results show that the Random Forest model achieved the best performance, with 99.8% accuracy, 99.6% recall, 0.1% false positive rate, and 99.8% ROC value. AdaBoost–Decision Tree and kNN also demonstrated strong performance with accuracies above 99%. In contrast, deep learning achieved only 39.6% recall despite high accuracy, mainly due to limited data size. The study concludes that ensemble-based machine learning models are highly effective for malware traffic detection and suitable for real-world deployment.
Zitieren
APA
Liu, Y. Z. S. (2026). Design and Implementation of a Machine Learning-Based Malware Detection System Based on healthcare systems. Tamjeed Journal of Healthcare Engineering and Science Technology, 4(1), 53-76. https://doi.org/10.59785/733cpq03
Vancouver
Liu YZS. Design and Implementation of a Machine Learning-Based Malware Detection System Based on healthcare systems. Tamjeed Journal of Healthcare Engineering and Science Technology. 2026;4(1):53-76. doi:10.59785/733cpq03
BibTeX
@article{Liu2026,
author = {Liu, Yi Zhu Shi},
title = {Design and Implementation of a Machine Learning-Based Malware Detection System Based on healthcare systems},
journal = {Tamjeed Journal of Healthcare Engineering and Science Technology},
year = {2026},
volume = {4},
number = {1},
pages = {53--76},
doi = {10.59785/733cpq03}
}
EUVIMED