Theoretical and Natural Science
- The Open Access Proceedings Series for Conferences
Series Vol. 12 , 17 November 2023
* Author to whom correspondence should be addressed.
The search for potential pulsars is a difficult job because of the complex nature of the signals and the vast amounts of data involved. In the last few years, a lot of researchers have tried to use machine learning to deal with complex data. This essay examines how machine learning could help to identify potential pulsars, exploring the various types of algorithms and the challenges and limitations associated with this approach. The essay mainly explored three themes: the training of 5 algorithms for the identification of pulsars, the improvement of 2 algorithms by adjusting parameters, and the simplification of the data to improve the processing speed and performance of the algorithms on prediction. All 5 algorithms reached great accuracy after adjustment and the simplification of the input data can help to boost the prediction time and accuracy for future research about pulsars. The essay highlights the need for further research in this area, as machine learning has demonstrated strong potential for pulsar prediction. By analyzing the results of several previous studies, this essay underscores the importance of machine learning as an approach for predicting potential pulsars and made improvements to the performance of current algorithms by adjusting parameters and simplifying the data.
pulsars, machine learning, interdisciplinary astronomy (804)
1. Allison, P. D. Logistic Regression Using the SAS System: Theory and Application. SAS Publishing (2001).
2. Yu, X., X. Yu. The Research on an Adaptive k-Nearest Neighbors Classifier. IEEE International Conference on Cognitive Informatics IEEE, 2007.
3. Ping, L., et al. Decision Tree Network Traffic Classifier Via Adaptive Hierarchical Clustering for Imperfect Training Dataset. International Conference on Wireless Communications IEEE, 2009.
4. Burke-Spolaor, S., et al. The High Time Resolution Universe Survey - III. Single-pulse searches and preliminary analysis. Monthly Notices of the Royal Astronomical Society 4 (2011): 2465-2476.
5. Rustam, F., et al. Predicting pulsar stars using a random tree-boosting voting classifier (RTB-VC). Astronomy and Computing 32 (2020):100404.
6. Wang, Y. C., et al. Pulsar candidate classification with deep convolutional neural networks. Research in Astronomy and Astrophysics (2019).
7. Chawla, N. V., et al. SMOTE: Synthetic Minority Over-sampling Technique. Journal of Artificial Intelligence Research 16.1(2002):321-357.Raschka, Sebastian et al. Python machine learning: machine learning and deep learning with Python, scikit-learn, and TensorFlow. (2017).
8. Alom, Md Zahangir, et al. The History Began from AlexNet: A Comprehensive Survey on Deep Learning Approaches. (2018).
9. Tomonori, Totani. "Cosmological Fast Radio Bursts from Binary Neutron Star Mergers." Publications of the Astronomical Society of Japan 5 (2013):201-201.
10. Buda, Mateusz, A. Maki, and M. A. Mazurowski. A systematic study of the class imbalance problem in convolutional neural networks. arXiv e-prints (2017).
The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. Authors who publish this series agree to the following terms:
1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this series.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this series.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See Open Access Instruction).