| |
 |
| Paper: |
Detection of GWAC Abnormal Light Transform Based on
Sparse Autoencoder |
| Volume: |
527, Astronomical Data Analysis Software and Systems XXIX |
| Page: |
563 |
| Authors: |
Zhu, M.; Liu, W.; Yu, X. C.; Duan, F. Q.; Zhang, Y. G. |
| Abstract: |
The Geographic Wide Angle Camera Array (GWAC) is an important ground–based observation device for the Sino–French astronomical satellite project. It can get millions of light curves in just 15 seconds every night. This gives GWAC the advantages of observation and research in gravitational microlenses (important probe observations of exoplanets), flare stars, unknown transient objects (Gravitational Wave Bursts). These transient sources have anomalous characteristics in light and appear infrequently. It is a challenging task to detect the celestial bodies with abnormal light from the observed light curve. In order to improve the unfavorable conditions of artificial interpretation of a light curve, such as low efficiency and unavoidable errors or omissions, this paper proposes a light curve anomaly detection method based on Sparse AutoEncoder (SAE). To prove the effectiveness of the proposed algorithm, we performed some experiments on the algorithm and compared it with K–means in terms of false positive rate and time consumption. We identified 3 types of unknown mutations and some individual outliers, which will be tracked for deeper analysis. Experimental results show that the method has better performance in anomaly detection. |
|
|
|
|
|
