Cross-Frequency Pulsar Noise Prediction Via LSTM With GAN-Based Data Augmentation

This work proposes a novel solution for the prediction of pulsar noise while addressing the critical challenge of data scarcity in specific spin frequencies. The prediction backbone is a bi-directional LSTM network, trained with mixed-frequency data or in the transfer learning strategy, where high-f...

Full description

Saved in:
Bibliographic Details
Published in2025 IEEE 2nd International Conference on Deep Learning and Computer Vision (DLCV) pp. 1 - 5
Main Authors Tang, Qingye, An, Dechao, Ouyang, Yuqi
Format Conference Proceeding
LanguageEnglish
Published IEEE 06.06.2025
Subjects
Adversarial Training
Bidirectional long short term memory
Computer vision
Data augmentation
Deep learning
GAN
Generative adversarial networks
LSTM
Memory management
Noise
Noise Prediction
Predictive models
Pulsar
Training
Transfer learning
Online AccessGet full text
DOI10.1109/DLCV65218.2025.11088530

Cover

More Information
Summary:This work proposes a novel solution for the prediction of pulsar noise while addressing the critical challenge of data scarcity in specific spin frequencies. The prediction backbone is a bi-directional LSTM network, trained with mixed-frequency data or in the transfer learning strategy, where high-frequency noises are generated via adversarial training. Evaluated on the IPTA dataset, our solution produces accurate predictions in different high-frequency domains, requiring only 10 % real high-frequency noise in the adversarial training process. Such robust generalization makes our solution suitable for real-world scenarios where pulsar observations are limited.
DOI:10.1109/DLCV65218.2025.11088530