García Merino, José CarlosTobarra Abad, María de los LlanosRobles Gómez, AntonioPastor Vargas, RafaelVidal Balboa, PedroDionisio Rocha, AndréJardim Gonçalves, Ricardo2025-05-092025-05-092025-06García-Merino, J.C., Tobarra-Abad, Ll., Robles-Gómez, A., Pastor-Vargas, R., Dionisio-Rocha, A., Jardim-Gonçalves, R. (2025); Título: Assessing Feature Selection Techniques for AI-based IoT Network Intrusion Detection; Publicación: DCAI 2025 - Lecture Notes in Networks and Systems. ISSN: 2367-3370; Páginas 1-102367-3370https://hdl.handle.net/20.500.14468/26526This is the Accepted Manuscript of an article that will soon be published by Springer in "Lecture Notes in Networks and Systems", when the conference proceedings are published. Este es el manuscrito aceptado de un artículo que Springer publicará próximamente en "Lecture Notes in Networks and Systems", cuando se publiquen las actas de la conferencia.The widespread adoption of Internet of Things (IoT) technology in rural areas has led to qualitative leaps in fields such as agriculture, livestock farming, and transportation, giving rise to the concept of Smart Rural. However, Smart Rural IoT ecosystems are often vulnerable to cyberattacks. Although Artificial Intelligence (AI) based intrusion detection systems offer an effective solution to protect these environments, IoT devices are typically constrained in terms of memory and computation capabilities, making it essential to optimise the computational burden of AI models. This work explores different feature selection techniques to develop compact and fast Random Forest models for anomaly detection in IoT environments. The obtained results demonstrate that appropriate feature selection can reduce model size and inference time by at least 45% and 8%, respectively, without compromising predictive performance.eninfo:eu-repo/semantics/restrictedAccess33 Ciencias Tecnológicasactas de congresoInternet of Things (IoT)smart ruralcybersecurityArtificial Intelligence (AI)Intrusion Detection System (IDS)