×
Home Current Archive Editorial board
Instructions for papers
For Authors Aim & Scope Contact
Original scientific article

COMBINING TRANSFORMERS AND FUZZY CLUSTERING BASED ON FUZZY FUNCTIONS FOR OPTIMAL UAV LOCALIZATION IN 5G WIRELESS NETWORKS

By
Sajjad H. Hasan Orcid logo ,
Sajjad H. Hasan

Islamic Azad University, Isfahan , Isfahan , Iran

Mehdi Hamidkhani Orcid logo ,
Mehdi Hamidkhani

Islamic Azad University, Isfahan , Isfahan , Iran

Nasseer K. Bachache Orcid logo ,
Nasseer K. Bachache

Bilad Alrafidain University College , Baqubah , Iraq

Keyvan Mohebbi Orcid logo
Keyvan Mohebbi

Islamic Azad University, Isfahan , Isfahan , Iran

Abstract

This paper introduces a new way to use UAVs in the 5G wireless network, based on Fuzzy C-Means (FCM) clustering and Transformer architecture for improved coverage, less energy consumption, and better Quality of Service (QoS). The new method improves user grouping by incorporating fuzzy distance functions into the FCM algorithm and it further trains Transformer models to interpret the spatial and temporal complexities of the network. This enables UAV replacement, such that now they can be placed more intelligently, especially in congested or unserved regions. Tests with the C2TM dataset demonstrated that the approach outperformed traditional ones by K-Medoid and plain FCM. Energy consumption by the UAV was reduced by 20.100% to 3,597 joules against 4,500 joules using K-Medoid, and the network performed better in terms of Mbps, reaching an average throughput of 180 and with latency at 40 milliseconds and packet loss at 0.8%. This shows a great change in how reliable the network is and what the user experiences. The plan also made the UAV use better by getting more close grouping within and farther apart grouping between, making sure resources are used well. This work points to how much can be done when smart computer models are joined with grouping methods to solve hard issues in the wireless networks of the future. The way suggested here gives a strong answer for changing places, making sure there are scale-able, useful, and trusted communication services. These results make a way for more study in UAV-based communication systems, looking at going deeper with the use of smart learning methods and quick math finding.

References

1.
Bisio I, Garibotto C, Haleem H, Lavagetto F, Sciarrone A. RF/WiFi-based UAV surveillance systems: A systematic literature review. Internet of Things. 2024 Jul 1;26:101201.
2.
Sofiazizi A, Kianfar F. Modeling and Forecasting Exchange Rates Using Econometric Models and Neural Networks. International Academic Journal of Innovative Research. 2015;2(4):11-27.
3.
Khan A, Zhang J, Ahmad S, Memon S, Qureshi HA, Ishfaq M. Dynamic Positioning and Energy-Efficient Path Planning for Disaster Scenarios in 5G-Assisted Multi-UAV Environments. Electronics. 2022 Jul 13;11(14):2197.
4.
Ghazanfari DM, Domirani S, Hamze H. Human resources strategies approach in organizations with network model (supply chain model) “Case study: defense industries organizations.” International Academic Journal of Organizational Behavior and Human Resource Management. 2018;5(1):63-83.
5.
Mei LM, Johal MS, Idris F, Hashim N. Spectrally efficient UAV communications using non-orthogonal multiple access (NOMA). Journal of Advanced Research in Applied Sciences and Engineering Technology. 2025;43:227-42.

Citation

This is an open access article distributed under the  Creative Commons Attribution Non-Commercial License (CC BY-NC) License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. 

Article metrics

Google scholar: See link

The statements, opinions and data contained in the journal are solely those of the individual authors and contributors and not of the publisher and the editor(s). We stay neutral with regard to jurisdictional claims in published maps and institutional affiliations.