Detection of Gravitational-Wave Signals from Time- Frequency Distributions Using Deep Learning (CROSBI ID 448485)
Ocjenski rad | doktorska disertacija
Podaci o odgovornosti
Lopac, Nikola
Lerga, Jonatan
engleski
Detection of Gravitational-Wave Signals from Time- Frequency Distributions Using Deep Learning
This thesis proposes a method for classifying noisy, non-stationary signals based on deep learning algorithms and Cohen's class of time- frequency distributions (TFDs). The proposed approach is demonstrated on the challenging task of detecting gravitational-wave (GW) signals in intensive real-life, non-stationary, non-Gaussian, and non-white noise. By retrieving real-life measurements from Laser Interferometer Gravitational-Wave Observatory detectors and performing extensive GW waveform simulations, a diverse time-series dataset of 100 000 examples was obtained with the signal-to-noise ratio (SNR) in the range from -123.46 to -2.27 dB. Next, 12 TFDs were calculated from the preprocessed time series, resulting in 1.2 million TFD images, then used as input to the deep learning classification algorithms utilizing three state-of-the-art two- dimensional convolutional neural network (CNN) architectures (ResNet-101, Xception, and EfficientNet). The results obtained by evaluating each of 36 TFD-CNN models show excellent classification performance of the proposed approach, with classification accuracy, area under the receiver operating characteristic curve (ROC AUC), recall, precision, F1 score, and area under the precision-recall curve (PR AUC) up to 97.100%, 0.98854, 95.867%, 99.507%, 97.029%, and 0.99195, respectively. Moreover, the proposed approach significantly outperforms the baseline deep learning model trained on the time-series data in terms of all considered metrics, with the statistical significance confirmed by McNemar's test. The obtained results indicate that the proposed technique can improve the classification of non-stationary GW signals at very low SNRs with the potentials to be extended to other practical applications.
non-stationary signals ; noisy signals ; time-frequency signal analysis ; Cohen’s class of time-frequency distributions ; deep learning ; convolutional neural networks ; gravitational waves
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o izdanju
184
11.03.2022.
obranjeno
Podaci o ustanovi koja je dodijelila akademski stupanj
Tehnički fakultet, Rijeka
Rijeka