arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2304.11604astro-ph.IM
收藏

使用结合卷积与注意力的计算机视觉方法进行脉冲星候选体分类

Pulsar Candidate Classification Using A Computer Vision Method Combining with Convolution and Attention

NanNan Cai, JinLin Han, WeiCong Jing, ZeKai Zhang, DeJiang Zhou, Xue Chen

AI总结:

提出融合 CoAtNet、多层感知机与逻辑回归的脉冲星识别系统,分别处理二维和一维融合特征,在 GPPS 测试集上实现高召回率、低假阳性率与高准确率。

摘要:

人工智能方法对于从大量候选体中识别脉冲星不可或缺。我们开发了一种新的脉冲星识别系统,该系统利用 CoAtNet 对候选体的二维特征进行评分,使用多层感知机对一维特征进行评分,并采用逻辑回归对上述评分作出判断。在数据预处理阶段,我们分别进行了两次特征融合,一次针对一维特征,另一次针对二维特征,分别用作多层感知机和 CoAtNet 的输入。新开发的系统在我们的 GPPS 测试集上取得了 98.77% 的召回率、1.07% 的假阳性率和 98.85% 的准确率。

英文摘要:

Artificial intelligence methods are indispensable to identifying pulsars from large amounts of candidates. We develop a new pulsar identification system that utilizes the CoAtNet to score two-dimensional features of candidates, uses a multilayer perceptron to score one-dimensional features, and uses logistic regression to judge the scores above. In the data preprocessing stage, we performed two feature fusions separately, one for one-dimensional features and the other for two-dimensional features, which are used as inputs for the multilayer perceptron and the CoAtNet respectively. The newly developed system achieves 98.77\% recall, 1.07\% false positive rate and 98.85\% accuracy in our GPPS test set.

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。

↑