@inproceedings{710e97d36b694654aea4b0b08f7b6ab3,
title = "Handling Overfitting and Imbalance Data in Modelling Convolutional Neural Networks for Astronomical Transient Discovery",
abstract = "Given development in telescope and image acquisition technology, efficient processing and timely discovery of events have become challenges for astronomers and data scientists around the globe. Among modern sky survey projects, GOTO (Gravitational-wave Optical Transient Observer) is searching for transient events with new breed of optical survey telescopes, which allow a faster and deeper assessment. As compared to conventional machine learning techniques that have been sup-optimal to identify new sources from a large pool of candidates, this works presents the application of convolutional neural networks, with different data augmentation methods being explored to handle issues of overfitting and imbalance data.",
keywords = "Astronomy, Classification, CNN, Data augmentation, Transient event",
author = "Tossapon Boongoen and Natthakan Iam-On",
note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.; International Conference on Computing, Communication, Cybersecurity and AI, C3AI 2024 ; Conference date: 03-07-2024 Through 04-07-2024",
year = "2024",
doi = "10.1007/978-3-031-74443-3_40",
language = "English",
isbn = "978-3-031-74442-6; 978-3-031-74443-3",
volume = "884",
series = "Lecture Notes in Networks and Systems",
publisher = "Springer Nature",
pages = "691--698",
editor = "Nitin Naik and Paul Grace and Paul Jenkins and Shaligram Prajapat",
booktitle = "Contributions Presented at The International Conference on Computing, Communication, Cybersecurity and AI - The C3AI 2024",
address = "Switzerland",
}