https://www.mdu.se/

mdh.sePublikasjoner
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Blind Symbol Rate Estimation Using Wavelet Transform and Deep Learning for FSK Modulated Signals
Mälardalens universitet, Akademin för innovation, design och teknik, Inbyggda system.
Research and Development, Wireless P2P Technologies, Falun, Sweden.
Mälardalens universitet, Akademin för innovation, design och teknik, Inbyggda system.ORCID-id: 0000-0002-2419-2735
Mälardalens universitet, Akademin för innovation, design och teknik, Inbyggda system.ORCID-id: 0000-0002-7159-7508
Vise andre og tillknytning
2022 (engelsk)Inngår i: 2022 International Conference on Advanced Technologies for Communications (ATC), 2022Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

This paper is focused on the blind symbol rate estimation for the digital FSK modulated signals, based on the classification between three symbol rate classes: 10, 100, and 1000 KSymbol/second using the scalogram images obtained from continuous wavelet transform with Morse wavelet. Pretrained deep learning AlexNet has been transfer learned to classify between symbol rate classes. Training, testing, and validation data sets have been composed of the artificial data generated using Bernoulli binary random signal generator modulated into FSK signal corrupted by additive white Gaussian noise (AWGN) noise with SNR ranging from 1 to 30 dB. Training and validation data sets have been augmented to obtain twice more extensive data set i.e 1800 scalogram images, compared to the original size of 900 samples. The average classification accuracy during validation has reached 99.7 % and during testing 100 % and 96.3 % for the data sets with SNR 25–30 dB and 20–25 dB respectively. The proposed algorithm has been compared with cyclostationary and has shown improved classification accuracy, especially in conditions of low SNR.

sted, utgiver, år, opplag, sider
2022.
HSV kategori
Identifikatorer
URN: urn:nbn:se:mdh:diva-61136DOI: 10.1109/atc55345.2022.9943051Scopus ID: 2-s2.0-85142741268OAI: oai:DiVA.org:mdh-61136DiVA, id: diva2:1716918
Konferanse
2022 International Conference on Advanced Technologies for Communications (ATC), 20-22 October 2022
Tilgjengelig fra: 2022-12-07 Laget: 2022-12-07 Sist oppdatert: 2023-03-10bibliografisk kontrollert
Inngår i avhandling
1. Spectrum Sensing for Cognitive Radio
Åpne denne publikasjonen i ny fane eller vindu >>Spectrum Sensing for Cognitive Radio
2023 (engelsk)Doktoravhandling, med artikler (Annet vitenskapelig)
Abstract [en]

This work focuses on the improvement of spectrum utilization by evaluating and proposing a subset of radio scene analysis algorithms for opportunistic spectrum access deployment in a cognitive radio network. The proposed algorithms aim to solve two problems: detecting vacant frequency channels and estimating the waveform, including modulation type, symbol rate, and central frequency. To test and prove the hypothesis three research questions related to radio scene observation, classification, and estimation have been formulated, studied, and answered. A two-step spectrum sensing algorithm has been proposed. The first step covers the coarse classification of the observed band into three broad categories: white, gray, or black space, commonly used in the literature to describe spectrum occupancy. Various machine learning algorithms were applied and tested for the coarse classification step. Fine decision trees demonstrated the highest classification accuracy and speed. The second step covers the detailed gray space analysis performed to detect vacant channels and waveforms of the signals present in the observed band. Algorithms such as cyclostationary, energy detection, and wavelet transform were employed for solving the vacant channel detection. The hypothesis has been proven by demonstrating the possibility of blind real-time vacant frequency channel detection using discrete wavelet transform and energy detection within the time compatible with real-time operation and 5G latency requirements on the test hardware.

sted, utgiver, år, opplag, sider
Västerås: Mälardalens universitet, 2023
Serie
Mälardalen University Press Dissertations, ISSN 1651-4238 ; 373
HSV kategori
Forskningsprogram
elektronik
Identifikatorer
urn:nbn:se:mdh:diva-61898 (URN)978-91-7485-583-8 (ISBN)
Disputas
2023-04-12, Gamma, Mälardalens universitet, Västerås, 09:15 (engelsk)
Opponent
Tilgjengelig fra: 2023-02-14 Laget: 2023-02-13 Sist oppdatert: 2023-03-22bibliografisk kontrollert

Open Access i DiVA

Fulltekst mangler i DiVA

Andre lenker

Forlagets fulltekstScopus

Person

Valieva, InnaBjörkman, MatsÅkerberg, JohanEkström, Mikael

Søk i DiVA

Av forfatter/redaktør
Valieva, InnaBjörkman, MatsÅkerberg, JohanEkström, Mikael
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric

doi
urn-nbn
Totalt: 39 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf