Neural Network Optimization for Classification Signals with Linear Frequency Modulation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F60162694%3AG43__%2F26%3A00564730" target="_blank" >RIV/60162694:G43__/26:00564730 - isvavai.cz</a>

Výsledek na webu

<a href="http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=11061248" target="_blank" >http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=11061248</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICMT65201.2025.11060897" target="_blank" >10.1109/ICMT65201.2025.11060897</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Neural Network Optimization for Classification Signals with Linear Frequency Modulation

Popis výsledku v původním jazyce

This paper presents the design, implementation and training of a signal classifier based on Wigner-Ville spectral analysis using an artificial neural network composed of fully connected layers. The classifier is developed to discriminate between linear frequency modulation and carrier signals under different signal-to-noise ratio conditions. Deterministic linear frequency modulation signals are generated with random frequency ranges and durations, combined with noise, and analyzed using the Wigner-Ville transform to extract signal features from the spectrogram. The neural network architecture is optimized using multiple fully connected layers, regularization of the outage and normalization of the z-score. The system achieves a high signal classification rate in a challenging noise environment, demonstrating the effectiveness of the proposed method for time-frequency signal analysis.

Název v anglickém jazyce

Neural Network Optimization for Classification Signals with Linear Frequency Modulation

Popis výsledku anglicky

This paper presents the design, implementation and training of a signal classifier based on Wigner-Ville spectral analysis using an artificial neural network composed of fully connected layers. The classifier is developed to discriminate between linear frequency modulation and carrier signals under different signal-to-noise ratio conditions. Deterministic linear frequency modulation signals are generated with random frequency ranges and durations, combined with noise, and analyzed using the Wigner-Ville transform to extract signal features from the spectrogram. The neural network architecture is optimized using multiple fully connected layers, regularization of the outage and normalization of the z-score. The system achieves a high signal classification rate in a challenging noise environment, demonstrating the effectiveness of the proposed method for time-frequency signal analysis.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20200 - Electrical engineering, Electronic engineering, Information engineering

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

2025 10th International Conference on Military Technologies, ICMT 2025 - Proceedings

ISBN

979-8-3315-2338-1

ISSN

—

e-ISSN

—

Počet stran výsledku

5

Strana od-do

24-28

Název nakladatele

Institute of Electrical and Electronics Engineers Inc.

Místo vydání

Brno

Místo konání akce

Brno, Czech Republic

Datum konání akce

27. 5. 2025

Typ akce podle státní příslušnosti

EUR - Evropská akce

Kód UT WoS článku

001545807300001