Research on Pulsar Candidate Identification Method Based on Deep Residual Neural Network |
| |
| Institution: | 1. Shanghai Astronomical Observatory, Chinese Academy of Sciences, Shanghai 200030;2. University of Chinese Academy of Sciences, Beijing 100049;1. Beijing Institute of Spacecraft Environment Engineering, Beijing 100094;2. National Key Laboratory of Science and Technology on Reliability and Environmental Engineering, Beijing 100094;3. Department of Engineering Physics, Tsinghua University, Beijing 100084;4. Key Laboratory of Particle & Radiation Imaging (Tsinghua University), Ministry of Education, Beijing 100084;1. National Time Service Center, Chinese Academy of Sciences, Xi’an 710600;2. Key Laboratory of Time and Frequency Primary Standards, Chinese Academy of Sciences, Xi’an 710600;3. School of Astronomy and Space Science, University of Chinese Academy of Sciences, Beijing 100049;1. Yunnan Observatories, Chinese Academy of Sciences, Kunming 650216;2. Center for Astronomical Mega-Science, Chinese Academy of Sciences, Beijing 100012;3. University of Chinese Academy of Sciences, Beijing 100049;4. Kunming University of Science and Technology, Kunming 650031;5. National Space Science Center, Chinese Academy of Sciences, Beijing 100190;6. Beijing Key Laboratory of Space Environment Exploration, Beijing 100190;7. Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094;8. Purple Mountain Observatories, Chinese Academy of Sciences, Nanjing 210008;9. School of Earth and Space Sciences, Peking University, Beijing 100871;10. Key Laboratory of Solar Activity, Chinese Academy of Sciences, Beijing 100012;11. Institute of Space Sciences, Shandong University (Weihai), Shandong 264209;12. National Astronomical Observatories, Chinese Academy of Sciences, Beijing 100012;13. Innovation Academy for Microsatellites, Chinese Academy of Sciences, Shanghai 201203;14. School of Space and Environment, Beihang University, Beijing 100191;15. School of Astronomy and Space Science, Nanjing University, Nanjing 210093 |
| |
| Abstract: | As the next-generation radio astronomical telescopes continuously improve and develop, the pulsar survey will produce millions of pulsar candidates, which pose considerable challenges for pulsar identification and classification. The rapidly evolving artificial intelligence (AI) techniques are being used for pulsar identification and discovery of new pulsars. Using the pulsar data set observed with the Parkes telescope, namely the High Time Resolution Universe Survey (HTRUS), a 14-layer deep residual network has been designed (called the Residual Network, ResNet) for pulsar candidate classifications. In the HTRUS sample data, the number of non-pulsar candidates (i.e., negative samples) is much larger than that of pulsar candidates (i.e., positive samples). The imbalance between the positive and negative samples is prone to result in model misjudgement. By using the over-sampling technique to enhance the data of positive samples in the training set and adjusting the ratio of positive and negative samples, we have solved this imbalance problem. In the training process, the hyperparameters are adjusted by means of 5-fold cross validation to build the model. The test results indicate that the model can achieve a high precision (98%) and recall (100%), the F1-score can reach 99%, and that the implementation of each sample test needs only 7 ms, it has provided a feasible approach for the future big-data analysis of pulsars. |
| |
| Keywords: | Pulsar: general Data set: HTRUS methods: ResNet methods: classification |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
