Machine Learning for Radio Frequency Interference Flagging
| dc.contributor.advisor | Mishra, Amit | |
| dc.contributor.advisor | Taylor, Russ | |
| dc.contributor.author | Harrison, Kyle | |
| dc.date.accessioned | 2021-08-17T09:23:43Z | |
| dc.date.available | 2021-08-17T09:23:43Z | |
| dc.date.issued | 2021 | |
| dc.date.updated | 2021-08-17T09:18:48Z | |
| dc.description.abstract | The field of radio frequency interference (RFI) flagging involves the identification of corrupted data within radio astronomy measurements. This work explores the application of supervised machine learning algorithms for RFI flagging, trained on real measurement data and simulated data with simulated RFI. The goal of this work is to investigate the prediction of RFI using specific machine learning algorithms; Naive Bayes Classifier, K-Nearest Neighbours Classifier, Random Forest Classifier, the U-Net convolution neural network and the Multilayer Perceptron. These algorithms are trained on real data, in which the ground truth includes inherent false positives, and simulated data where the ground truth positions of RFI are absolute. This is done through the use of time/frequency spectrogram data, relating to radio astronomy measurements, using the magnitudes and phases of each available polarization. Predictions for unseen test data are compared between algorithms, different implementations of those algorithms and each dataset. A specific implementation for data pre-processing is designed and implemented, utilizing a two dimensional filtering technique for feature construction. The goal of this method is intended to implement a means of injecting a form of spatial information of nearby time/frequency samples for each sample in a spectrogram. The inclusion of this spacial information, which is relevant to broadband bursts and narrowband persistent RFI, is hypothesised to increase the level of information present in the processed dataset. The use of feature construction using filtering techniques, demonstrates a noticeable improvement in the machine learning methods where each sample is treated individually during training and inference. | |
| dc.identifier.apacitation | Harrison, K. (2021). <i>Machine Learning for Radio Frequency Interference Flagging</i>. (). ,Faculty of Engineering and the Built Environment ,Department of Electrical Engineering. Retrieved from http://hdl.handle.net/11427/33777 | en_ZA |
| dc.identifier.chicagocitation | Harrison, Kyle. <i>"Machine Learning for Radio Frequency Interference Flagging."</i> ., ,Faculty of Engineering and the Built Environment ,Department of Electrical Engineering, 2021. http://hdl.handle.net/11427/33777 | en_ZA |
| dc.identifier.citation | Harrison, K. 2021. Machine Learning for Radio Frequency Interference Flagging. . ,Faculty of Engineering and the Built Environment ,Department of Electrical Engineering. http://hdl.handle.net/11427/33777 | en_ZA |
| dc.identifier.ris | TY - Master Thesis AU - Harrison, Kyle AB - The field of radio frequency interference (RFI) flagging involves the identification of corrupted data within radio astronomy measurements. This work explores the application of supervised machine learning algorithms for RFI flagging, trained on real measurement data and simulated data with simulated RFI. The goal of this work is to investigate the prediction of RFI using specific machine learning algorithms; Naive Bayes Classifier, K-Nearest Neighbours Classifier, Random Forest Classifier, the U-Net convolution neural network and the Multilayer Perceptron. These algorithms are trained on real data, in which the ground truth includes inherent false positives, and simulated data where the ground truth positions of RFI are absolute. This is done through the use of time/frequency spectrogram data, relating to radio astronomy measurements, using the magnitudes and phases of each available polarization. Predictions for unseen test data are compared between algorithms, different implementations of those algorithms and each dataset. A specific implementation for data pre-processing is designed and implemented, utilizing a two dimensional filtering technique for feature construction. The goal of this method is intended to implement a means of injecting a form of spatial information of nearby time/frequency samples for each sample in a spectrogram. The inclusion of this spacial information, which is relevant to broadband bursts and narrowband persistent RFI, is hypothesised to increase the level of information present in the processed dataset. The use of feature construction using filtering techniques, demonstrates a noticeable improvement in the machine learning methods where each sample is treated individually during training and inference. DA - 2021_ DB - OpenUCT DP - University of Cape Town KW - Electrical Engineering LK - https://open.uct.ac.za PY - 2021 T1 - Machine Learning for Radio Frequency Interference Flagging TI - Machine Learning for Radio Frequency Interference Flagging UR - http://hdl.handle.net/11427/33777 ER - | en_ZA |
| dc.identifier.uri | http://hdl.handle.net/11427/33777 | |
| dc.identifier.vancouvercitation | Harrison K. Machine Learning for Radio Frequency Interference Flagging. []. ,Faculty of Engineering and the Built Environment ,Department of Electrical Engineering, 2021 [cited yyyy month dd]. Available from: http://hdl.handle.net/11427/33777 | en_ZA |
| dc.language.rfc3066 | eng | |
| dc.publisher.department | Department of Electrical Engineering | |
| dc.publisher.faculty | Faculty of Engineering and the Built Environment | |
| dc.subject | Electrical Engineering | |
| dc.title | Machine Learning for Radio Frequency Interference Flagging | |
| dc.type | Master Thesis | |
| dc.type.qualificationlevel | Masters | |
| dc.type.qualificationlevel | MSc |