基于特征选择处理脉冲星候选体筛选中数据不平衡问题
Dealing with the data imbalance problem on pulsar candidates sifting based on feature selection
AI总结：
针对脉冲星候选体筛选中的数据不平衡问题，提出KFRG两阶段特征选择算法，通过K折Relief过滤和贪婪搜索选特征，在HTRU数据集上验证了其能提升分类性能。
摘要：
脉冲星探测近来已成为射电天文学中的一个活跃研究课题。脉冲星探测的关键步骤之一是脉冲星候选体筛选（PCS），即从巡天数据中找出潜在脉冲星信号的过程。然而，脉冲星候选体总是存在类别不平衡问题，因为大多数候选体是非脉冲星（如射频干扰），只有极少数来自真实脉冲星。类别不平衡严重损害了机器学习（ML）模型的性能，导致一些真实脉冲星被误判，造成重大损失。为解决该问题，本文聚焦于选择相关特征以区分脉冲星与非脉冲星的技术，即特征选择。特征选择是从特征池中选取最相关特征子集的过程。即使数据高度不平衡，脉冲星与非脉冲星之间的区分特征也能显著提升分类器性能。本工作中，设计了一种名为K折Relief-贪婪算法（KFRG）的特征选择算法。KFRG是一种两阶段算法：第一阶段根据K折Relief得分过滤掉一些不相关特征；第二阶段通过前向贪婪搜索策略去除冗余特征并选择最相关特征。在高时间分辨率宇宙巡天数据集上的实验验证了基于KFRG的机器学习模型能够胜任PCS任务，即使在候选体高度类别不平衡的情况下也能正确区分脉冲星与非脉冲星。
英文摘要：
Pulsar detection has become an active research topic in radio astronomy recently. One of the essential procedures for pulsar detection is pulsar candidate sifting (PCS), a procedure of finding out the potential pulsar signals in a survey. However, pulsar candidates are always class-imbalanced, as most candidates are non-pulsars such as RFI and only a tiny part of them are from real pulsars. Class imbalance has greatly damaged the performance of machine learning (ML) models, resulting in a heavy cost as some real pulsars are misjudged. To deal with the problem, techniques of choosing relevant features to discriminate pulsars from non-pulsars are focused on, which is known as {\itshape feature selection}. Feature selection is a process of selecting a subset of the most relevant features from a feature pool. The distinguishing features between pulsars and non-pulsars can significantly improve the performance of the classifier even if the data are highly imbalanced.In this work, an algorithm of feature selection called {\itshape K-fold Relief-Greedy} algorithm (KFRG) is designed. KFRG is a two-stage algorithm. In the first stage, it filters out some irrelevant features according to their K-fold Relief scores, while in the second stage, it removes the redundant features and selects the most relevant features by a forward greedy search strategy. Experiments on the dataset of the High Time Resolution Universe survey verified that ML models based on KFRG are capable for PCS, correctly separating pulsars from non-pulsars even if the candidates are highly class-imbalanced.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
