2026-05-10T08:07:02.684Z http://ezaposleni.singidunum.ac.rs/rest/sciNaucniRezultati/oai

ezaposleni.singidunum.ac.rs/rest/sciNaucniRezultati/oai:3:9801 2024-12-03T20:10:47Z 3

XGBoost Tuned by Hybridized SCA Metaheuristics for Intrusion Detection in Healthcare 4.0 IoT Systems, Chapter in AIS Algorithms for Intelligent Systems: ICEAI 2023: Evolutionary Artificial Intelligence, Springer 2024 http://ezaposleni.singidunum.ac.rs/rest/sciNaucniRezultati/oai/record/3/9801 https://link.springer.com/chapter/10.1007/978-981-99-8438-1_1 M. Zivkovic L. Jovanovic N. Bacanin A. Petrovic N. Savanovic M. Dobrojevic Internet of Things (IoT) system advancements have facilitated their extensive incorporation into our daily lives. In particular, real-time monitoring systems are highly valuable in domains like healthcare, where prompt actions can significantly impact outcomes. However, despite the widespread adoption of IoT, a crucial obstacle hinders its broader integration. For IoT to support sustainable healthcare, it must deliver well-organized healthcare services to the population while ensuring minimal harm to the environment. Security emerges as a pivotal aspect in maintaining the sustainability of IoT systems, necessitating the timely detection and remediation of security issues. This study addresses security challenges directly by employing an XGBoost model, tuned by a hybridized sine cosine (SCA) metaheuristics algorithm, to identify security vulnerabilities in applied IoT appliances in healthcare 4.0. bookPart Springer, Singapore 1 16 10.1007/978-981-99-8438-1_1 AIS Algorithms for Intelligent Systems: ICEAI 2023: Evolutionary Artificial Intelligence