PMID- 31597330
OWN - NLM
STAT- PubMed-not-MEDLINE
DCOM- 20191016
LR  - 20210110
IS  - 1424-8220 (Electronic)
IS  - 1424-8220 (Linking)
VI  - 19
IP  - 19
DP  - 2019 Oct 8
TI  - Machine Learning for LTE Energy Detection Performance Improvement.
LID - 10.3390/s19194348 [doi]
LID - 4348
AB  - The growing number of radio communication devices and limited spectrum resources 
      are drivers for the development of new techniques of dynamic spectrum access and 
      spectrum sharing. In order to make use of the spectrum opportunistically, the 
      concept of cognitive radio was proposed, where intelligent decisions on 
      transmission opportunities are based on spectrum sensing. In this paper, two 
      Machine Learning (ML) algorithms, namely k-Nearest Neighbours and Random Forest, 
      have been proposed to increase spectrum sensing performance. These algorithms 
      have been applied to Energy Detection (ED) and Energy Vector-based data (EV) to 
      detect the presence of a Fourth Generation (4G) Long-Term Evolution (LTE) signal 
      for the purpose of utilizing the available resource blocks by a 5G new radio 
      system. The algorithms capitalize on time, frequency and spatial dependencies in 
      daily communication traffic. Research results show that the ML methods used can 
      significantly improve the spectrum sensing performance if the input training data 
      set is carefully chosen. The input data sets with ED decisions and energy values 
      have been examined, and advantages and disadvantages of their real-life 
      application have been analyzed.
FAU - Wasilewska, Malgorzata
AU  - Wasilewska M
AUID- ORCID: 0000-0002-3471-0516
AD  - Department of Wireless Communications, Poznan University of Technology, 61-131 
      Poznan, Poland. Malgorzata.Wasilewska@doctorate.put.poznan.pl.
FAU - Bogucka, Hanna
AU  - Bogucka H
AUID- ORCID: 0000-0002-1709-4862
AD  - Department of Wireless Communications, Poznan University of Technology, 61-131 
      Poznan, Poland. hanna.bogucka@put.poznan.pl.
LA  - eng
GR  - 2017/27/L/ST7/03166/Narodowe Centrum Nauki/
PT  - Journal Article
DEP - 20191008
PL  - Switzerland
TA  - Sensors (Basel)
JT  - Sensors (Basel, Switzerland)
JID - 101204366
SB  - IM
PMC - PMC6806316
OTO - NOTNLM
OT  - cognitive radio
OT  - energy detection
OT  - k-nearest neighbors
OT  - machine learning
OT  - random forest
OT  - spectrum sensing
COIS- The authors declare no conflict of interest.
EDAT- 2019/10/11 06:00
MHDA- 2019/10/11 06:01
PMCR- 2019/10/01
CRDT- 2019/10/11 06:00
PHST- 2019/08/31 00:00 [received]
PHST- 2019/10/04 00:00 [revised]
PHST- 2019/10/06 00:00 [accepted]
PHST- 2019/10/11 06:00 [entrez]
PHST- 2019/10/11 06:00 [pubmed]
PHST- 2019/10/11 06:01 [medline]
PHST- 2019/10/01 00:00 [pmc-release]
AID - s19194348 [pii]
AID - sensors-19-04348 [pii]
AID - 10.3390/s19194348 [doi]
PST - epublish
SO  - Sensors (Basel). 2019 Oct 8;19(19):4348. doi: 10.3390/s19194348.