Enhanced spectrum sensing for 5G and LTE signals using advanced deep learning models and hyperparameter tuning

Abstract This paper introduces a novel approach to enhancing spectrum sensing accuracy for 5G and LTE signals using advanced deep learning models, with a particular focus on the impact of systematic hyperparameter tuning. By leveraging state-of-the-art neural network architecture, namely DenseNet121...

Full description

Saved in:
Bibliographic Details
Main Authors: Sally Mohamed Ali Elmorsy, Samah Mohamed Osman, Samah Adel Gamel
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-07837-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849342843992145920
author Sally Mohamed Ali Elmorsy
Samah Mohamed Osman
Samah Adel Gamel
author_facet Sally Mohamed Ali Elmorsy
Samah Mohamed Osman
Samah Adel Gamel
author_sort Sally Mohamed Ali Elmorsy
collection DOAJ
description Abstract This paper introduces a novel approach to enhancing spectrum sensing accuracy for 5G and LTE signals using advanced deep learning models, with a particular focus on the impact of systematic hyperparameter tuning. By leveraging state-of-the-art neural network architecture, namely DenseNet121 and InceptionV3—the study aims to overcome the limitations of traditional spectrum sensing methods in highly dynamic and noisy wireless environments. The research highlights that, through rigorous hyperparameter optimization, these models achieved substantial improvements in detection accuracy, reaching 97.3% and 98.2%, respectively, compared to initial performance levels of 93.0% and 95.0%. These performance improvements were particularly notable in controlled scenarios where low signal-to-noise ratio frames were excluded, with 60% of frames containing little or no information—highlighting the critical role of signal quality in both training and evaluation. It is worth noting that the models were trained and tested on a large and diverse dataset, including synthetic signals and real-world data, simulating a wide range of practical deployment conditions. This comprehensive database supports the generalizability of the proposed approach and its real-world applicability. The study also confirms that the models demonstrated competitive performance in various test scenarios, and that their integration into future wireless systems could significantly enhance smart spectrum management and real-time communication reliability in modern networks.
format Article
id doaj-art-4e3259ede7e543e68ec8dbefe8493af0
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-4e3259ede7e543e68ec8dbefe8493af02025-08-20T03:43:15ZengNature PortfolioScientific Reports2045-23222025-07-0115112210.1038/s41598-025-07837-2Enhanced spectrum sensing for 5G and LTE signals using advanced deep learning models and hyperparameter tuningSally Mohamed Ali Elmorsy0Samah Mohamed Osman1Samah Adel Gamel2High Institute of ManagementFaculty of Computer Studies, Arab Open UniversityFaculty of Engineering, Horus UniversityAbstract This paper introduces a novel approach to enhancing spectrum sensing accuracy for 5G and LTE signals using advanced deep learning models, with a particular focus on the impact of systematic hyperparameter tuning. By leveraging state-of-the-art neural network architecture, namely DenseNet121 and InceptionV3—the study aims to overcome the limitations of traditional spectrum sensing methods in highly dynamic and noisy wireless environments. The research highlights that, through rigorous hyperparameter optimization, these models achieved substantial improvements in detection accuracy, reaching 97.3% and 98.2%, respectively, compared to initial performance levels of 93.0% and 95.0%. These performance improvements were particularly notable in controlled scenarios where low signal-to-noise ratio frames were excluded, with 60% of frames containing little or no information—highlighting the critical role of signal quality in both training and evaluation. It is worth noting that the models were trained and tested on a large and diverse dataset, including synthetic signals and real-world data, simulating a wide range of practical deployment conditions. This comprehensive database supports the generalizability of the proposed approach and its real-world applicability. The study also confirms that the models demonstrated competitive performance in various test scenarios, and that their integration into future wireless systems could significantly enhance smart spectrum management and real-time communication reliability in modern networks.https://doi.org/10.1038/s41598-025-07837-25GSpectrum sensingDeep learningLTESpectrum managementBandwidth efficiency
spellingShingle Sally Mohamed Ali Elmorsy
Samah Mohamed Osman
Samah Adel Gamel
Enhanced spectrum sensing for 5G and LTE signals using advanced deep learning models and hyperparameter tuning
Scientific Reports
5G
Spectrum sensing
Deep learning
LTE
Spectrum management
Bandwidth efficiency
title Enhanced spectrum sensing for 5G and LTE signals using advanced deep learning models and hyperparameter tuning
title_full Enhanced spectrum sensing for 5G and LTE signals using advanced deep learning models and hyperparameter tuning
title_fullStr Enhanced spectrum sensing for 5G and LTE signals using advanced deep learning models and hyperparameter tuning
title_full_unstemmed Enhanced spectrum sensing for 5G and LTE signals using advanced deep learning models and hyperparameter tuning
title_short Enhanced spectrum sensing for 5G and LTE signals using advanced deep learning models and hyperparameter tuning
title_sort enhanced spectrum sensing for 5g and lte signals using advanced deep learning models and hyperparameter tuning
topic 5G
Spectrum sensing
Deep learning
LTE
Spectrum management
Bandwidth efficiency
url https://doi.org/10.1038/s41598-025-07837-2
work_keys_str_mv AT sallymohamedalielmorsy enhancedspectrumsensingfor5gandltesignalsusingadvanceddeeplearningmodelsandhyperparametertuning
AT samahmohamedosman enhancedspectrumsensingfor5gandltesignalsusingadvanceddeeplearningmodelsandhyperparametertuning
AT samahadelgamel enhancedspectrumsensingfor5gandltesignalsusingadvanceddeeplearningmodelsandhyperparametertuning