Unveiling the power of features: A comparative study of machine learning and deep learning for modulation recognition

Basit Öğe Kaydı
dc.contributor.authorLeblebici, Merih
dc.contributor.authorÇalhan, Ali
dc.contributor.authorCicioǧlu, Murtaza
dc.date.accessioned2025-10-11T20:45:21Z
dc.date.available2025-10-11T20:45:21Z
dc.date.issued2025
dc.departmentDüzce Üniversitesien_US
dc.description.abstractWireless communication systems rely on amplitude, frequency, and phase parameters for signal transmission. Traditional modulation recognition (MR) techniques, employing likelihood-based (LB) and feature-based (FB) methods, struggle with accurate classification, particularly at low signal-to-noise ratios (SNR) and increasing modulation complexity. Machine learning (ML) and deep learning (DL) algorithms, which efficiently utilize in-phase/quadrature (IQ) and r-radius/θ-angle (rθ) data representations to enhance MR performance. DL, utilizing artificial neural networks (ANN), minimizes the need for extensive feature engineering, making it adept at handling diverse modulation types and challenging SNR conditions. This study systematically examines dataset generation parameters to reveal their impact on MR performance. By focusing on these underlying parameters, the analysis provides deeper insights into how data characteristics influence model performance, offering a foundational understanding for optimizing dataset configurations in MR tasks. Evaluating ML and DL models across datasets, results show DL model consistently outperforms ML models, achieving up to 79.41 % accuracy on IQ-based datasets. DL's hierarchical feature extraction enhances adaptability, particularly with larger datasets, reduced window lengths (WL), and specific θ ranges (e.g., radians or smaller degree intervals). For ML models, datasets based on IQ, rθ, and IQrθ parameters yield better results but remain below 70 % accuracy. Overall, DL model exhibits robust adaptability to complex signal environments, highlighting their effectiveness in advancing modulation recognition for next-generation wireless communication systems. © 2025 Elsevier B.V., All rights reserved.en_US
dc.identifier.doi10.1016/j.phycom.2025.102791
dc.identifier.issn1874-4907
dc.identifier.scopus2-s2.0-105011750120en_US
dc.identifier.scopusqualityQ2en_US
dc.identifier.urihttps://doi.org/10.1016/j.phycom.2025.102791
dc.identifier.urihttps://hdl.handle.net/20.500.12684/21304
dc.identifier.volume72en_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherElsevier B.V.en_US
dc.relation.ispartofPhysical Communicationen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.snmzKA_Scopus_20250911
dc.subjectArtificial Intelligenceen_US
dc.subjectDeep Learningen_US
dc.subjectMachine Learningen_US
dc.subjectModulation Recognitionen_US
dc.subjectWireless Communicationen_US
dc.subjectComplex Networksen_US
dc.subjectLearning Algorithmsen_US
dc.subjectLearning Systemsen_US
dc.subjectNeural Networksen_US
dc.subjectSignal To Noise Ratioen_US
dc.subjectWireless Networksen_US
dc.subjectDeep Learningen_US
dc.subjectIn-phase/quadratureen_US
dc.subjectLearning Modelsen_US
dc.subjectMachine Learning Modelsen_US
dc.subjectMachine-learningen_US
dc.subjectModulation Recognitionen_US
dc.subjectPerformanceen_US
dc.subjectPoweren_US
dc.subjectWireless Communication Systemen_US
dc.subjectWireless Communicationsen_US
dc.titleUnveiling the power of features: A comparative study of machine learning and deep learning for modulation recognitionen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu