杨阳, 文中略, 夏俊卿. 基于残差神经网络的恒星-星系分类器[J]. 北京师范大学学报(自然科学版), 2021, 57(4): 450-457. DOI: 10.12202/j.0476-0301.2021106
引用本文: 杨阳, 文中略, 夏俊卿. 基于残差神经网络的恒星-星系分类器[J]. 北京师范大学学报(自然科学版), 2021, 57(4): 450-457. DOI: 10.12202/j.0476-0301.2021106
YANG Yang, WEN Zhonglue, XIA Junqing. Star-galaxy separation by the residual neural network algorithm[J]. Journal of Beijing Normal University(Natural Science), 2021, 57(4): 450-457. DOI: 10.12202/j.0476-0301.2021106
Citation: YANG Yang, WEN Zhonglue, XIA Junqing. Star-galaxy separation by the residual neural network algorithm[J]. Journal of Beijing Normal University(Natural Science), 2021, 57(4): 450-457. DOI: 10.12202/j.0476-0301.2021106

基于残差神经网络的恒星-星系分类器

Star-galaxy separation by the residual neural network algorithm

  • 摘要: 使用残差神经网络(residual neural network,RNN)算法对斯隆数字巡天(Sloan digital sky survey,SDSS)提供的天体伪彩色图片进行分类,直接从图像中获得特征.使用带有光谱信息的星系与恒星图片作为训练集和测试集.经过训练,在测试集上的准确率达到98.23%,召回率达到98.80%。这表明:RNN可以实现对星系和恒星图像的精确分类,分类器给出的恒星-星系概率是有效的,可用于分类可靠度评估;还可以尝试将此分类器应用到未来巡天中,进一步测试其性能.

     

    Abstract: In this paper, the residual neural network (RNN) algorithm was used to classify pseudo-color images of stars and galaxies from Sloan  digital  sky  survey (SDSS), with features obtained directly from images.Images of galaxies and stars with spectral information were used as training and test sets.After training, accuracy rate on the test set can reach 98.23%, and recall rate 98.80%, indicating that the RNN algorithm can accurately classify images of galaxies and stars.The probability of being a star or galaxy given by the classifier is verified, and the probability can be used to evaluate the reliability of classification.This classifier can be applied to future sky surveys to further test its performance.

     

/

返回文章
返回