[论文解读] Pulsar Candidate Identification with Artificial Intelligence Techniques

Ping Guo, Fuqing Duan+4 more|arXiv (Cornell University)|Nov 27, 2017

Seismic Imaging and Inversion Techniques参考文献 17被引用 12

一句话总结

本文提出一种DCGAN+L2-SVM框架，以解决脉冲星候选体识别中的类别不平衡问题并提升特征学习能力。通过使用深度卷积生成对抗网络生成逼真的正样本并提取层次化特征，再结合L2-SVM分类器，该方法在两个脉冲星数据集上均优于传统CNN和SVM，展现出在有限真实脉冲星数据下处理此类问题的有效性。

ABSTRACT

Discovering pulsars is a significant and meaningful research topic in the field of radio astronomy. With the advent of astronomical instruments such as he Five-hundred-meter Aperture Spherical Telescope (FAST) in China, data volumes and data rates are exponentially growing. This fact necessitates a focus on artificial intelligence (AI) technologies that can perform the automatic pulsar candidate identification to mine large astronomical data sets. Automatic pulsar candidate identification can be considered as a task of determining potential candidates for further investigation and eliminating noises of radio frequency interferences or other non-pulsar signals. It is very hard to raise the performance of DCNN-based pulsar identification because the limited training samples restrict network structure to be designed deep enough for learning good features as well as the crucial class imbalance problem due to very limited number of real pulsar samples. To address these problems, we proposed a framework which combines deep convolution generative adversarial network (DCGAN) with support vector machine (SVM) to deal with imbalance class problem and to improve pulsar identification accuracy. DCGAN is used as sample generation and feature learning model, and SVM is adopted as the classifier for predicting candidate's labels in the inference stage. The proposed framework is a novel technique which not only can solve imbalance class problem but also can learn discriminative feature representations of pulsar candidates instead of computing hand-crafted features in preprocessing steps too, which makes it more accurate for automatic pulsar candidate selection. Experiments on two pulsar datasets verify the effectiveness and efficiency of our proposed method.

研究动机与目标

• 为解决由于真实脉冲星样本稀缺导致的脉冲星候选体识别中严重的类别不平衡问题。
• 开发一种端到端的AI框架，自动学习判别性特征，避免人工特征工程。
• 通过深度生成模型与监督学习相结合，提升脉冲星候选体分类的准确率与鲁棒性。
• 评估生成的正样本与深层特征在提升分类器性能方面的有效性。
• 为下一代射电望远镜（如FAST）实现高效、可扩展且自动化的脉冲星发现流水线。

提出的方法

• 在平衡标注的脉冲星候选体数据上训练深度卷积生成对抗网络（DCGAN），以学习层次化特征表示。
• 从判别器中间层提取最大池化后的激活图作为深层特征，替代手工设计的特征。
• 将这些深层特征用于监督学习阶段，训练L2-SVM分类器以完成最终分类。
• 进一步探索一种条件DCGAN变体，用于生成逼真的脉冲星候选体正样本。
• 在两个数据集上评估该框架：HTRU Medlat和自收集的PMPS-26k数据集（包含真实脉冲星与RFI候选体）。
• 该方法结合了通过DCGAN进行的无监督预训练与通过L2-SVM进行的监督微调，以实现最优性能。

实验结果

研究问题

• RQ1 基于DCGAN的框架能否有效缓解脉冲星候选体识别中的类别不平衡问题？
• RQ2 使用预训练DCGAN判别器提取的深层特征是否相比手工设计特征能显著提升分类准确率？
• RQ3 通过条件DCGAN生成的逼真正样本能否增强下游分类器的性能？
• RQ4 DCGAN+L2-SVM框架在真实脉冲星数据集上与标准CNN和SVM基线相比表现如何？
• RQ5 该框架能否在不同数据质量与复杂度的脉冲星巡天数据集之间实现良好泛化？

主要发现

• 在HTRU Medlat数据集上，DCGAN+L2-SVM框架的分类准确率高于标准CNN和RBF-SVM基线。
• 在PMPS-26k数据集上，DCGAN+L2-SVM优于PCA+SVM方法，表明其在不同数据集间具有强大的泛化能力。
• 使用DCGAN判别器提取的深层特征相比传统手工设计特征显著提升了分类性能。
• 基于条件DCGAN生成逼真正样本进一步增强了分类器区分真实脉冲星与噪声的能力。
• 该框架在处理有限真实脉冲星数据时表现出鲁棒性与有效性，适用于大规模、实时脉冲星巡天。
• 结果表明，将生成建模与监督学习相结合是脉冲星候选体识别的一种有前景方法。