Handling Overfitting and Imbalance Data in Modelling Convolutional Neural Networks for Astronomical Transient Discovery

Tossapon Boongoen*, Natthakan Iam-On

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference Proceeding (Non-Journal item)

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.

Original languageEnglish
Title of host publicationContributions Presented at The International Conference on Computing, Communication, Cybersecurity and AI - The C3AI 2024
EditorsNitin Naik, Paul Grace, Paul Jenkins, Shaligram Prajapat
PublisherSpringer Nature
Pages691-698
Number of pages8
ISBN (Print)9783031744426
DOIs
Publication statusPublished - 2024
EventInternational Conference on Computing, Communication, Cybersecurity and AI, C3AI 2024 - London, United Kingdom of Great Britain and Northern Ireland
Duration: 03 Jul 202404 Jul 2024

Publication series

NameLecture Notes in Networks and Systems
Volume884 LNNS
ISSN (Print)2367-3370
ISSN (Electronic)2367-3389

Conference

ConferenceInternational Conference on Computing, Communication, Cybersecurity and AI, C3AI 2024
Country/TerritoryUnited Kingdom of Great Britain and Northern Ireland
CityLondon
Period03 Jul 202404 Jul 2024

Keywords

  • Astronomy
  • Classification
  • CNN
  • Data augmentation
  • Transient event

Fingerprint

Dive into the research topics of 'Handling Overfitting and Imbalance Data in Modelling Convolutional Neural Networks for Astronomical Transient Discovery'. Together they form a unique fingerprint.

Cite this