Enhancing Deep Learning Networks Performance By Using B-Spline Activation Functions for Clutter Removal in GPR

Basit Öğe Kaydı
dc.contributor.authorKayacan, Yavuz Emre
dc.contributor.authorErer, Isin
dc.date.accessioned2025-03-09T10:57:33Z
dc.date.available2025-03-09T10:57:33Z
dc.date.issued2024
dc.departmentİstanbul Beykent Üniversitesi
dc.description32nd Telecommunications Forum, TELFOR 2024 -- 26 November 2024 through 27 November 2024 -- Belgrade -- 205822
dc.description.abstractTraditional clutter removal methods struggle with complex clutter and multiple targets in Ground-Penetrating Radar images. This study proposes using B-spline activation functions in the deep-learning models to improve clutter removal in GPR. Experimental results demonstrate that B-spline-enhanced models outperform their ReLU-based counterparts, with improvements of up to 2.20% in PSNR, 0.035% in MS-SSIM, and 15.83% in SCR, showcasing their potential for real-world GPR applications. © 2024 IEEE.
dc.description.sponsorshipMEKTAM; TUBITAK BILGEM Mine and Handmade Explosive Countermeasures Test and Research Center; Türkiye Bilimsel ve Teknolojik Araştırma Kurumu, TÜBİTAK, (120E234)
dc.identifier.doi10.1109/TELFOR63250.2024.10819108
dc.identifier.isbn979-835039105-3
dc.identifier.scopus2-s2.0-85216891208
dc.identifier.scopusqualityN/A
dc.identifier.urihttps://doi.org/10.1109/TELFOR63250.2024.10819108
dc.identifier.urihttps://hdl.handle.net/20.500.12662/4909
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherInstitute of Electrical and Electronics Engineers Inc.
dc.relation.ispartof2024 32nd Telecommunications Forum, TELFOR 2024 - Proceedings of Papers
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzKA_Scopus_20250310
dc.subjectB-splines
dc.subjectClutter removal
dc.subjectdeep learning
dc.subjectground-penetrating radar
dc.titleEnhancing Deep Learning Networks Performance By Using B-Spline Activation Functions for Clutter Removal in GPR
dc.typeConference Object

Dosyalar

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu