A Hybrid Approach to Reliable Jamming Identification in UAV Communications Using Combined DNNs and ML Algorithms

Deep Neural Networks (DNNs) have gained prominence due to their remarkable accomplishments across various domains, including telecommunications and security. Their integration into decision-making processes within 5G telecommunication systems and UAV security is noteworthy. However, the iterative na...

Full description

Saved in:
Bibliographic Details
Main Authors: Hamed Farkhari, Joseanne Viana, Sarang Kahvazadeh, Pedro Sebastiao, Victor P. Gil Jimenez, Rui Dinis
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10763503/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846128559434760192
author Hamed Farkhari
Joseanne Viana
Sarang Kahvazadeh
Pedro Sebastiao
Victor P. Gil Jimenez
Rui Dinis
author_facet Hamed Farkhari
Joseanne Viana
Sarang Kahvazadeh
Pedro Sebastiao
Victor P. Gil Jimenez
Rui Dinis
author_sort Hamed Farkhari
collection DOAJ
description Deep Neural Networks (DNNs) have gained prominence due to their remarkable accomplishments across various domains, including telecommunications and security. Their integration into decision-making processes within 5G telecommunication systems and UAV security is noteworthy. However, the iterative nature of DNN data processing can introduce uncertainties in classification decisions, impacting their reliability. This paper presents novel combined preprocessing and post-processing techniques designed to enhance the accuracy and reliability of binary classification DNNs by managing uncertainty levels. The study evaluates these methods through calibration error metrics, confidence values, and the Reliability Score (RS), which quantifies the disparity between Mean Accuracy (MA) and Mean Confidence (MC). Additionally, the effectiveness of these methods is demonstrated by applying them to simulated real-world scenarios to improve jamming detection reliability in UAV communications. The proposed algorithms’ impact is compared against baseline DNNs and DNNs augmented with the eXtreme Gradient Boosting (XGB) classifier, as well as the latest research to validate our approach. This paper comprehensively overviews the experimental setup, dataset, deep network architecture, preprocessing and post-processing techniques, evaluation metrics, and results. By addressing uncertainty in XGB and DNN outputs, this study improves the trustworthiness of ML-DNN-based decision-making processes in 5G UAV security scenarios.
format Article
id doaj-art-a95c718f1756462492fa5ff15eeaa169
institution Kabale University
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-a95c718f1756462492fa5ff15eeaa1692024-12-11T00:05:20ZengIEEEIEEE Access2169-35362024-01-011217889817890810.1109/ACCESS.2024.350472910763503A Hybrid Approach to Reliable Jamming Identification in UAV Communications Using Combined DNNs and ML AlgorithmsHamed Farkhari0https://orcid.org/0000-0002-2620-260XJoseanne Viana1https://orcid.org/0000-0002-4191-3127Sarang Kahvazadeh2https://orcid.org/0000-0001-5607-8120Pedro Sebastiao3https://orcid.org/0000-0001-7729-4033Victor P. Gil Jimenez4https://orcid.org/0000-0001-7029-1710Rui Dinis5https://orcid.org/0000-0002-8520-7267ISCTE-Instituto Universitário de Lisboa, Lisbon, PortugalDepartamento de Teoría de la Señal y Comunicaciones, Universidad Carlos III de Madrid (UC3M), Madrid, SpainCentre Tecnològic de Telecomunicacions de Catalunya (CTTC), CERCA, Barcelona, SpainISCTE-Instituto Universitário de Lisboa, Lisbon, PortugalDepartamento de Teoría de la Señal y Comunicaciones, Universidad Carlos III de Madrid (UC3M), Madrid, SpainInstituto de Telecomunicações (IT), Lisbon, PortugalDeep Neural Networks (DNNs) have gained prominence due to their remarkable accomplishments across various domains, including telecommunications and security. Their integration into decision-making processes within 5G telecommunication systems and UAV security is noteworthy. However, the iterative nature of DNN data processing can introduce uncertainties in classification decisions, impacting their reliability. This paper presents novel combined preprocessing and post-processing techniques designed to enhance the accuracy and reliability of binary classification DNNs by managing uncertainty levels. The study evaluates these methods through calibration error metrics, confidence values, and the Reliability Score (RS), which quantifies the disparity between Mean Accuracy (MA) and Mean Confidence (MC). Additionally, the effectiveness of these methods is demonstrated by applying them to simulated real-world scenarios to improve jamming detection reliability in UAV communications. The proposed algorithms’ impact is compared against baseline DNNs and DNNs augmented with the eXtreme Gradient Boosting (XGB) classifier, as well as the latest research to validate our approach. This paper comprehensively overviews the experimental setup, dataset, deep network architecture, preprocessing and post-processing techniques, evaluation metrics, and results. By addressing uncertainty in XGB and DNN outputs, this study improves the trustworthiness of ML-DNN-based decision-making processes in 5G UAV security scenarios.https://ieeexplore.ieee.org/document/10763503/Unmanned aerial vehicledeep neural networksmachine learninguncertaintyreliabilityjamming identification
spellingShingle Hamed Farkhari
Joseanne Viana
Sarang Kahvazadeh
Pedro Sebastiao
Victor P. Gil Jimenez
Rui Dinis
A Hybrid Approach to Reliable Jamming Identification in UAV Communications Using Combined DNNs and ML Algorithms
IEEE Access
Unmanned aerial vehicle
deep neural networks
machine learning
uncertainty
reliability
jamming identification
title A Hybrid Approach to Reliable Jamming Identification in UAV Communications Using Combined DNNs and ML Algorithms
title_full A Hybrid Approach to Reliable Jamming Identification in UAV Communications Using Combined DNNs and ML Algorithms
title_fullStr A Hybrid Approach to Reliable Jamming Identification in UAV Communications Using Combined DNNs and ML Algorithms
title_full_unstemmed A Hybrid Approach to Reliable Jamming Identification in UAV Communications Using Combined DNNs and ML Algorithms
title_short A Hybrid Approach to Reliable Jamming Identification in UAV Communications Using Combined DNNs and ML Algorithms
title_sort hybrid approach to reliable jamming identification in uav communications using combined dnns and ml algorithms
topic Unmanned aerial vehicle
deep neural networks
machine learning
uncertainty
reliability
jamming identification
url https://ieeexplore.ieee.org/document/10763503/
work_keys_str_mv AT hamedfarkhari ahybridapproachtoreliablejammingidentificationinuavcommunicationsusingcombineddnnsandmlalgorithms
AT joseanneviana ahybridapproachtoreliablejammingidentificationinuavcommunicationsusingcombineddnnsandmlalgorithms
AT sarangkahvazadeh ahybridapproachtoreliablejammingidentificationinuavcommunicationsusingcombineddnnsandmlalgorithms
AT pedrosebastiao ahybridapproachtoreliablejammingidentificationinuavcommunicationsusingcombineddnnsandmlalgorithms
AT victorpgiljimenez ahybridapproachtoreliablejammingidentificationinuavcommunicationsusingcombineddnnsandmlalgorithms
AT ruidinis ahybridapproachtoreliablejammingidentificationinuavcommunicationsusingcombineddnnsandmlalgorithms
AT hamedfarkhari hybridapproachtoreliablejammingidentificationinuavcommunicationsusingcombineddnnsandmlalgorithms
AT joseanneviana hybridapproachtoreliablejammingidentificationinuavcommunicationsusingcombineddnnsandmlalgorithms
AT sarangkahvazadeh hybridapproachtoreliablejammingidentificationinuavcommunicationsusingcombineddnnsandmlalgorithms
AT pedrosebastiao hybridapproachtoreliablejammingidentificationinuavcommunicationsusingcombineddnnsandmlalgorithms
AT victorpgiljimenez hybridapproachtoreliablejammingidentificationinuavcommunicationsusingcombineddnnsandmlalgorithms
AT ruidinis hybridapproachtoreliablejammingidentificationinuavcommunicationsusingcombineddnnsandmlalgorithms