Signal Detection with a Digital Antenna Array using Machine Learning - Image Recognition Methods Applied for Joint Detection and Signal Parameter Estimation

Aug 4, 2026

Upload by Miles

Radars and radar warning receiver systems operate in a continuous contest for superior detection performance, motivating new approaches. This master’s thesis designs a “You Only Look Once”-style neural network to detect pulsed radar signals and estimate angle of arrival, frequency, time of arrival, and pulse width. A digital uniform linear antenna array provides multi-channel outputs, processed with short-time Fourier transforms and beamforming across angles to form a 3D spectrogram image for recognition. Simulated results demonstrate detection of two sinusoidal signals in noisy environments.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages56

Reading Time2 h 21 min

AccessFree to download

Abstract

Keywords

Acknowledgements

List of Acronyms

Signal Detection with a Digital Antenna Array using Machine Learning Image Recognition Methods Applied for Joint Detection and Signal Parameter Estimation Master’s thesis in Physics Elin Ohlman DEPARTMENT OF ELECTRICAL ENGINEERING CHALMERS UNIVERSITY OF TECHNOLOGY Gothenburg, Sweden 2023 [www.chalmers.se](www.chalmers.se) Master’s thesis 2023 Signal Detection with a Digital Antenna Array using Machine Learning Image Recognition Methods Applied for Joint Detection and Signal Parameter Estimation ELIN OHLMAN Department of Electrical Engineering Division of Communications, Antennas, and Optical Networks Chalmers University of Technology Gothenburg, Sweden 2023 Signal Detection with a Digital Antenna Array using Machine Learning Image Recognition Methods Applied for Joint Detection and Signal Parameter Estimation ELIN OHLMAN © ELIN OHLMAN, 2023 . Supervisor: Eric Norgren, SAAB Supervisor: Alexander Karlsson, SAAB Examiner: Rob Maaskant, Department of Electrical Engineering, Chalmers Master’s Thesis 2023 Department of Electrical Engineering Division of Communications, Antennas, and Optical Networks Chalmers University of Technology SE-412 96 Gothenburg Telephone +46 31 772 1000 Cover: Predictions and targets for a 3D image with the angle of arrival, frequency, and time as the three axes. The predictions are made by the network developed in the thesis. Typeset in LATEX Gothenburg, Sweden 2023 Signal Detection with a Digital Antenna Array using Machine Learning Image Recognition Methods Applied for Joint Detection and Signal Parameter Estimation ELIN OHLMAN Department of Electrical Engineering Chalmers University of Technology Abstract Radars and radar warning receiver systems engage in a perpetual battle for superiority. This constant struggle demands the development of new methods, and recent advancements in machine learning and image recognition may serve as sources of inspiration. In this thesis, a “You Only Look Once”-style neural network is designed to detect pulsed radar signals and estimate their angle of arrival, frequency, time of arrival, and pulse width. Employing a digital multi-channel uniform linear antenna array, a short-time Fourier transform is applied to the output from each antenna element. Afterward, beamforming is performed for various angles combining the spectrograms, producing a 3D image upon which image recognition is applied. We find that using simulated data this method works for detecting two sinusoidal signals, even in noisy environments. Keywords: Angle of Arrival (AOA), Beamforming, Convolutional Neural Network (CNN), Digital Antenna, Signal Detection, Spectrogram, Uniform Linear Array (ULA), You Only Look Once (YOLO) Acknowledgements First I would like to thank my supervisors at Saab, Eric Norgren, and Alexander Karlsson for the opportunity to do this thesis work. This project would never have been possible without your support, patience, and guidance. To my academic supervisor at Chalmers, Rob Maaskant, thank you for your support and understanding. To my partner Lukas Falk, thank you for your love and unwavering faith in me, even when I myself lacked it. Lastly, I thank my family, Börje, Hanna, Elsa, and Erik Ohlman for your everlasting support and encouragement. Elin Ohlman, Stockholm, May 2023 List of Acronyms Below is the list of acronyms that have been used throughout this thesis listed in alphabetical order. AOA Angle of Arrival CNN Convolutional Neural Network FFT Fast Fourier Transform IoU Intersection over Union IQ In-phase and Quadrature ML Machine Learning NN Neural Network PW Pulse Width ResNet Residual Neural Network RF Radio Frequency RMSE Root Mean Square Error SNR Signal to Noise Ratio STFT Short Time Fourier Transform TOA Time Of Arrival ULA Uniform Linear Array YOLO You Only Look Once

FAQs

What signals and parameters does the thesis focus on detecting and estimating?

It targets pulsed radar signals and estimates angle of arrival, frequency, time of arrival, and pulse width.

How is the antenna array data processed before neural network-based recognition?

Each antenna element output is transformed using a short-time Fourier transform, followed by beamforming across angles to create a 3D image used for recognition.

What neural network approach is used, and what does the thesis report about its performance?

A “You Only Look Once”-style neural network is used; with simulated data it can detect two sinusoidal signals even in noisy conditions.

Aug 4, 2026

Upload by Miles