Enhanced 6G Network Slicing Classification Using PSO-Based Feature Selection and Ensemble Learning

Basit Öğe Kaydı
dc.contributor.authorGüllü, Merve
dc.contributor.authorKüçük, Bayram
dc.contributor.authorSöǧüt, Esra
dc.date.accessioned2026-07-01T11:36:27Z
dc.date.available2026-07-01T11:36:27Z
dc.date.issued2025
dc.departmentDüzce Üniversitesi
dc.descriptionIEEE International Conference on Electrical, Computer and Energy Technologies, ICECET 2025 -- 3 July 2025 through 6 July 2025 -- Paris -- 222255
dc.description.abstractIn parallel with technological developments, mobile and wireless communication technologies are advancing rapidly. Today, 5G technology is widely used, while studies on 6G continue. As a result of these developments, the use of internet-connected devices is increasing both in daily life and in industrial areas. This increase in the number of devices brings critical requirements such as additional resources and energy consumption in networks, communication prioritization, and reliable data transmission. In response to these needs, 6G technology offers dynamic, flexible, and scenario-based resource allocation based on network slicing. Network slicing makes it possible to support innovative services such as super-eMBB, massive-MTC, and super-URLLC. In this paper, PSO-based feature selection and ensemble learning methods are used to solve the network slicing classification problem in 6G networks. In addition, the LIME method is applied to help better interpret model predictions and make reliable decisions.The main objective of this study is to contribute to the development of autonomous and seamless network systems that are suitable for the dynamic and complex nature of 6G. Thus, it aims to create reliable, flexible, and efficient network solutions by making the best use of the innovations offered by 6G. © 2025 IEEE.
dc.description.sponsorshipThe Scientific a nd T echnological Research Council of Türkiye; Türkiye Bilimsel ve Teknolojik Araştırma Kurumu, TUBITAK; 1515 Frontier R&D Laboratories Support Program for Türk Telekom 6G R&D Lab, (5249902) -- Aksaray University; IEEE
dc.identifier.doi10.1109/ICECET63943.2025.11471894
dc.identifier.isbn979-833153559-9
dc.identifier.scopus2-s2.0-105037105083
dc.identifier.scopusqualityN/A
dc.identifier.urihttps://doi.org/10.1109/ICECET63943.2025.11471894
dc.identifier.urihttps://hdl.handle.net/20.500.12684/23038
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherInstitute of Electrical and Electronics Engineers Inc.
dc.relation.ispartofInternational Conference on Electrical, Computer, and Energy Technologies, ICECET 2025
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzKA_Scopus_20260623
dc.subject6G
dc.subjectEnsemble Learning
dc.subjectLIME
dc.subjectNetwork Slicing
dc.subjectPSO
dc.titleEnhanced 6G Network Slicing Classification Using PSO-Based Feature Selection and Ensemble Learning
dc.typeConference Object

Dosyalar

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu