PMID- 36991727
OWN - NLM
STAT- PubMed-not-MEDLINE
DCOM- 20230330
LR  - 20230401
IS  - 1424-8220 (Electronic)
IS  - 1424-8220 (Linking)
VI  - 23
IP  - 6
DP  - 2023 Mar 10
TI  - Machine Learning-Based Methods for Enhancement of UAV-NOMA and D2D Cooperative 
      Networks.
LID - 10.3390/s23063014 [doi]
LID - 3014
AB  - The cooperative aerial and device-to-device (D2D) networks employing 
      non-orthogonal multiple access (NOMA) are expected to play an essential role in 
      next-generation wireless networks. Moreover, machine learning (ML) techniques, 
      such as artificial neural networks (ANN), can significantly enhance network 
      performance and efficiency in fifth-generation (5G) wireless networks and beyond. 
      This paper studies an ANN-based unmanned aerial vehicle (UAV) placement scheme to 
      enhance an integrated UAV-D2D NOMA cooperative network.The proposed placement 
      scheme selection (PSS) method for integrating the UAV into the cooperative 
      network combines supervised and unsupervised ML techniques. Specifically, a 
      supervised classification approach is employed utilizing a two-hidden layered ANN 
      with 63 neurons evenly distributed among the layers. The output class of the ANN 
      is utilized to determine the appropriate unsupervised learning method-either 
      k-means or k-medoids-to be employed. This specific ANN layout has been observed 
      to exhibit an accuracy of 94.12%, the highest accuracy among the ANN models 
      evaluated, making it highly recommended for accurate PSS predictions in urban 
      locations. Furthermore, the proposed cooperative scheme allows pairs of users to 
      be simultaneously served through NOMA from the UAV, which acts as an aerial base 
      station. At the same time, the D2D cooperative transmission for each NOMA pair is 
      activated to improve the overall communication quality. Comparisons with 
      conventional orthogonal multiple access (OMA) and alternative unsupervised 
      machine-learning based-UAV-D2D NOMA cooperative networks show that significant 
      sum rate and spectral efficiency gains can be harvested through the proposed 
      method under varying D2D bandwidth allocations.
FAU - Tsipi, Lefteris
AU  - Tsipi L
AUID- ORCID: 0000-0002-2591-9289
AD  - Department of Information and Communication Systems Engineering, School of 
      Engineering, University of the Aegean, 83200 Samos, Greece.
FAU - Karavolos, Michail
AU  - Karavolos M
AUID- ORCID: 0000-0002-3707-3313
AD  - Department of Information and Communication Systems Engineering, School of 
      Engineering, University of the Aegean, 83200 Samos, Greece.
FAU - Bithas, Petros S
AU  - Bithas PS
AUID- ORCID: 0000-0002-6858-3674
AD  - Department of Digital Industry Technologies, National and Kapodistrian University 
      of Athens, Thesi Skliro, 34400 Evia, Greece.
FAU - Vouyioukas, Demosthenes
AU  - Vouyioukas D
AUID- ORCID: 0000-0002-6649-6577
AD  - Department of Information and Communication Systems Engineering, School of 
      Engineering, University of the Aegean, 83200 Samos, Greece.
LA  - eng
PT  - Journal Article
DEP - 20230310
PL  - Switzerland
TA  - Sensors (Basel)
JT  - Sensors (Basel, Switzerland)
JID - 101204366
SB  - IM
PMC - PMC10055871
OTO - NOTNLM
OT  - D2D
OT  - NOMA
OT  - UAV placement
OT  - artificial neural network (ANN)
OT  - cooperative communications
OT  - deep neural network (DNN)
OT  - machine learning
COIS- The authors declare no conflict of interest.
EDAT- 2023/03/31 06:00
MHDA- 2023/03/31 06:01
PMCR- 2023/03/10
CRDT- 2023/03/30 01:02
PHST- 2022/12/20 00:00 [received]
PHST- 2023/03/06 00:00 [revised]
PHST- 2023/03/07 00:00 [accepted]
PHST- 2023/03/31 06:01 [medline]
PHST- 2023/03/30 01:02 [entrez]
PHST- 2023/03/31 06:00 [pubmed]
PHST- 2023/03/10 00:00 [pmc-release]
AID - s23063014 [pii]
AID - sensors-23-03014 [pii]
AID - 10.3390/s23063014 [doi]
PST - epublish
SO  - Sensors (Basel). 2023 Mar 10;23(6):3014. doi: 10.3390/s23063014.