loading page

A Deep Transfer Learning Approach on Identifying Glitch Wave-form in Gravitational Wave Data
  • Reymond Mesuga ,
  • Brian James Bayanay
Reymond Mesuga
Polytechnic University of the Philippines, Polytechnic University of the Philippines

Corresponding Author:[email protected]

Author Profile
Brian James Bayanay
Author Profile

Abstract

LIGO is considered the most sensitive and complicated gravitational experiment ever built. Its main objective is to detect the gravitational wave from the strongest events in the universe by observing if the length of its 4-kilometer arms change by a distance 10,000 times smaller than the diameter of a proton. Due to its sensitivity, LIGO is prone to the disturbance of external noises which affects the data being collected to detect the gravitational wave. These noises are commonly called by the LIGO community as glitches. This study focuses on identifying those glicthes using different deep transfer learning algorithms. The extensive experiment shows that algorithm with architecture VGG19 recorded the highest AUC-ROC among other experimented architectures with 0.9898. On the other hand, ResNet152 recorded the lowest AUC-ROC of 0.93954 which performs poorly in identifying almost half of the classes in the Gravity Spy dataset. It was also observed that less complex algorithm like VGG19, DenseNet169 and VGG16 performs better than most of the more complex algorithms featured in this study which could possibly indicate that less complex models might be preferred when identifying glitch wave-forms.