CS MSc Thesis Presentation 31 May 2023
Plats: Online via: https://lu-se.zoom.us/j/62627647113?pwd=MG5NcUN6c29pdHdzWkxJeTNVczE4UT09
Kontakt: birger [dot] swahn [at] cs [dot] lth [dot] se
Spara händelsen till din kalender
One Computer Science MSc thesis to be presented on 31 May
Wednesday, 31 May there will be a master thesis presentation in Computer Science at Lund University, Faculty of Engineering.
The presentation will take place online in Zoom: https://lu-se.zoom.us/j/62627647113?pwd=MG5NcUN6c29pdHdzWkxJeTNVczE4UT09
Note to potential opponents: (Register as an opponent to the presentation of your choice by sending an email to the examiner for that presentation (firstname.lastname@example.org). Do not forget to specify the presentation you register for! Note that the number of opponents may be limited (often to two), so you might be forced to choose another presentation if you register too late. Registrations are individual, just as the oppositions are! More instructions are found on this page.)
Presenter: Alex Evander
Title: Predictive Maintenance for Large Antennas used in Radio Astronomy
Examiner: Jacek Malec
Supervisor: Flavius Gruian (LTH)
This report investigates the possibility of using machine learning for predicting failures of servo-components in large antennas used for radio astronomy in the Square Kilometer Array project. Data is provided from MeerKAT antennas located in the Karoo-region in South Africa. Different machine learning models are compared, where performance is measured in rates of true positives and false negatives. Models used are LSTM and GRU networks with AutoEncoders. Data used is from sensors placed on MeerKAT-antennas in the Karoo desert, South Africa. The results show that such a complex problem needs further analysis of the failure types as well as additional hyperparameter model tuning. To conclude, the report provides a deeper insight into what is required and how hard it can be to accurately pre-process large amounts of real world data and apply deep learning models to it.
Link to popular science summary: To be uploaded
Link to Zoom presentation: https://lu-se.zoom.us/j/62627647113?pwd=MG5NcUN6c29pdHdzWkxJeTNVczE4UT09