Addressing Distribution Discrepancies in Pulsar Candidate Identification via Bayesian-neural-network-based Multimodal Incremental Learning
With the advancement of astronomical observation technology and the substantial increase in data volume, traditional methods for pulsar identification are increasingly challenged by the dynamic nature of data distributions. To address this, our study introduces a multimodal incremental learning appr...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2025-01-01
|
| Series: | The Astrophysical Journal Supplement Series |
| Subjects: | |
| Online Access: | https://doi.org/10.3847/1538-4365/ad9dec |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841527656175108096 |
|---|---|
| author | Yi Liu Jing Jin Hongyang Zhao Zhenyi Wang Yi Shen |
| author_facet | Yi Liu Jing Jin Hongyang Zhao Zhenyi Wang Yi Shen |
| author_sort | Yi Liu |
| collection | DOAJ |
| description | With the advancement of astronomical observation technology and the substantial increase in data volume, traditional methods for pulsar identification are increasingly challenged by the dynamic nature of data distributions. To address this, our study introduces a multimodal incremental learning approach utilizing Bayesian neural networks. This method enables the model to adapt to new data distributions while preserving the knowledge of previous data. In our experiments, we utilized pulsar data sets from two telescopes and compared our new method with traditional techniques. The research results demonstrate that our method performs comparably to traditional methods across all evaluation metrics, while showing a significant improvement in handling data distribution discrepancy, with the F1-score increasing from approximately 70% to over 95%. Specifically, our model achieved an accuracy of 97.93%, a recall of 96.13%, and an F1-score of 97.02% under conditions of distributional disparities. These findings not only confirm the model's capability to adapt to dynamic data environments but also effectively address the challenges of data distribution discrepancy, significantly enhancing the predictive accuracy of pulsar identification in the context of evolving and variable radio frequency interference environments. |
| format | Article |
| id | doaj-art-0e1e675df2c948f781aa4f8b79fac13c |
| institution | Kabale University |
| issn | 0067-0049 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | The Astrophysical Journal Supplement Series |
| spelling | doaj-art-0e1e675df2c948f781aa4f8b79fac13c2025-01-15T08:37:13ZengIOP PublishingThe Astrophysical Journal Supplement Series0067-00492025-01-0127623910.3847/1538-4365/ad9decAddressing Distribution Discrepancies in Pulsar Candidate Identification via Bayesian-neural-network-based Multimodal Incremental LearningYi Liu0https://orcid.org/0000-0002-0261-3172Jing Jin1Hongyang Zhao2https://orcid.org/0000-0003-0755-990XZhenyi Wang3Yi Shen4Department of Control Science and Engineering, Harbin Institute of Technology , People’s Republic of ChinaDepartment of Control Science and Engineering, Harbin Institute of Technology , People’s Republic of ChinaCollege of Mechanical and Electrical Engineering, Northeast Forestry University , People’s Republic of ChinaDepartment of Control Science and Engineering, Harbin Institute of Technology , People’s Republic of ChinaDepartment of Control Science and Engineering, Harbin Institute of Technology , People’s Republic of ChinaWith the advancement of astronomical observation technology and the substantial increase in data volume, traditional methods for pulsar identification are increasingly challenged by the dynamic nature of data distributions. To address this, our study introduces a multimodal incremental learning approach utilizing Bayesian neural networks. This method enables the model to adapt to new data distributions while preserving the knowledge of previous data. In our experiments, we utilized pulsar data sets from two telescopes and compared our new method with traditional techniques. The research results demonstrate that our method performs comparably to traditional methods across all evaluation metrics, while showing a significant improvement in handling data distribution discrepancy, with the F1-score increasing from approximately 70% to over 95%. Specifically, our model achieved an accuracy of 97.93%, a recall of 96.13%, and an F1-score of 97.02% under conditions of distributional disparities. These findings not only confirm the model's capability to adapt to dynamic data environments but also effectively address the challenges of data distribution discrepancy, significantly enhancing the predictive accuracy of pulsar identification in the context of evolving and variable radio frequency interference environments.https://doi.org/10.3847/1538-4365/ad9decPulsarsConvolutional neural networksRadio pulsarsAstronomy data analysisAstronomy data modelingAstronomical object identification |
| spellingShingle | Yi Liu Jing Jin Hongyang Zhao Zhenyi Wang Yi Shen Addressing Distribution Discrepancies in Pulsar Candidate Identification via Bayesian-neural-network-based Multimodal Incremental Learning The Astrophysical Journal Supplement Series Pulsars Convolutional neural networks Radio pulsars Astronomy data analysis Astronomy data modeling Astronomical object identification |
| title | Addressing Distribution Discrepancies in Pulsar Candidate Identification via Bayesian-neural-network-based Multimodal Incremental Learning |
| title_full | Addressing Distribution Discrepancies in Pulsar Candidate Identification via Bayesian-neural-network-based Multimodal Incremental Learning |
| title_fullStr | Addressing Distribution Discrepancies in Pulsar Candidate Identification via Bayesian-neural-network-based Multimodal Incremental Learning |
| title_full_unstemmed | Addressing Distribution Discrepancies in Pulsar Candidate Identification via Bayesian-neural-network-based Multimodal Incremental Learning |
| title_short | Addressing Distribution Discrepancies in Pulsar Candidate Identification via Bayesian-neural-network-based Multimodal Incremental Learning |
| title_sort | addressing distribution discrepancies in pulsar candidate identification via bayesian neural network based multimodal incremental learning |
| topic | Pulsars Convolutional neural networks Radio pulsars Astronomy data analysis Astronomy data modeling Astronomical object identification |
| url | https://doi.org/10.3847/1538-4365/ad9dec |
| work_keys_str_mv | AT yiliu addressingdistributiondiscrepanciesinpulsarcandidateidentificationviabayesianneuralnetworkbasedmultimodalincrementallearning AT jingjin addressingdistributiondiscrepanciesinpulsarcandidateidentificationviabayesianneuralnetworkbasedmultimodalincrementallearning AT hongyangzhao addressingdistributiondiscrepanciesinpulsarcandidateidentificationviabayesianneuralnetworkbasedmultimodalincrementallearning AT zhenyiwang addressingdistributiondiscrepanciesinpulsarcandidateidentificationviabayesianneuralnetworkbasedmultimodalincrementallearning AT yishen addressingdistributiondiscrepanciesinpulsarcandidateidentificationviabayesianneuralnetworkbasedmultimodalincrementallearning |