搜索

x

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于自归一化神经网络的脉冲星候选体选择

康志伟 刘拓 刘劲 马辛 陈晓

引用本文:
Citation:

基于自归一化神经网络的脉冲星候选体选择

康志伟, 刘拓, 刘劲, 马辛, 陈晓

Pulsar candidate selection based on self-normalizing neural networks

Kang Zhi-Wei, Liu Tuo, Liu Jin, Ma Xin, Chen Xiao
PDF
HTML
导出引用
  • 脉冲星候选体选择是脉冲星搜寻任务中的重要步骤. 为了提高脉冲星候选体选择的准确率, 提出了一种基于自归一化神经网络的候选体选择方法. 该方法采用自归一化神经网络、遗传算法、合成少数类过采样这三种技术提升对脉冲星候选体的筛选能力. 利用自归一化神经网络的自归一化性质克服了深层神经网络训练中梯度消失和爆炸的问题, 大大加快了训练速度. 为了消除样本数据的冗余性, 利用遗传算法对脉冲星候选体的样本特征进行选择, 得到了最优特征子集. 针对数据中真实脉冲星样本数极少带来的严重类不平衡性, 采用合成少数类过采样技术生成脉冲星候选体样本, 降低了类不平衡率. 以分类精度为评价指标, 在3个脉冲星候选体数据集上的实验结果表明, 本文提出的方法能有效提升脉冲星候选体选择的性能.
    Pulsar candidate selection is an important step in the search task of pulsars. The traditional candidate selection is heavily dependent on human inspection. However, the human inspection is a subjective, time consuming, and error-prone process. A modern radio telescopes pulsar survey project can produce totally millions of candidates, so the manual selection becomes extremely difficult and inefficient due to a large number of candidates. Therefore, this study focuses on machine learning developed in recent years. In order to improve the efficiency of pulsar candidate selection, we propose a candidate selection method based on self-normalizing neural networks. This method uses three techniques: self-normalizing neural networks, genetic algorithm and synthetic minority over-sampling technique. The self-normalizing neural networks can improve the identification accuracy by applying deep neural networks to pulsar candidate selection. At the same time, it solves the problem of gradient disappearance and explosion in the training process of deep neural networks by using its self-normalizing property, which greatly accelerates the training process. In addition, in order to eliminate the redundancy of the sample data, we use genetic algorithm to choose sample features of pulsar candidates. The genetic algorithm for feature selection can be summarized into three steps: initializing population, assessing population fitness, and generating new populations. Decoding the individual with the largest fitness value in the last generation population, we can obtain the best subset of features. Due to radio frequency interference or noise, there are a large number of non-pulsar signals in candidates, and only a few real pulsar signals exist there. Aiming at solving the severe class imbalance problem, we use the synthetic minority over-sampling technique to increase the pulsar candidates (minority class) and reduce the imbalance degree of data. By using k-nearest neighbor and linear interpolation to insert a new sample between two minority classes of samples that are close to each other according to certain rules, we can prevent the classifier from becoming biased towards the abundant non-pulsar class (majority class). Experimental results on three pulsar candidate datasets show that the self-normalizing neural network has higher accuracy and faster convergence speed than the traditional artificial neural network in the deep structure, By using the genetic algorithm and synthetic minority over-sampling technique, the selection performance of pulsar candidates can be effectively improved.
      通信作者: 康志伟, jt_zwkang@hnu.edu.cn
    • 基金项目: 国家级-面向脉冲星/星光多普勒组合导航的深度融合与智能定位方法(61772187)
      Corresponding author: Kang Zhi-Wei, jt_zwkang@hnu.edu.cn
    [1]

    孙海峰, 谢楷, 李小平, 方海燕, 刘秀平, 傅灵忠, 孙海建, 薛梦凡 2013 物理学报 62 109701Google Scholar

    Sun H F, Xie K, Li X P, Fang H Y, Liu X P, Fu L Z, Sun H J, Xue M F 2013 Acta Phys. Sin. 62 109701Google Scholar

    [2]

    Heiles C, Li D, Mcclure-Griffiths N, Qian L, Liu S 2019 Res. Astron. Astrophys. 19 5Google Scholar

    [3]

    Yi S X, Zhang S N 2016 Sci. China, Phys. Mech. Astron. 59 689511Google Scholar

    [4]

    Liu J, Ning X L, Ma X, Fang J C 2019 IEEE Trans. Aerosp. Electron. Syst. 55 2556Google Scholar

    [5]

    康志伟, 吴春艳, 刘劲, 马辛, 桂明臻 2018 物理学报 67 099701Google Scholar

    Kang Z W, Wu C Y, Liu J, Ma X, Gui M Z 2018 Acta Phys. Sin. 67 099701Google Scholar

    [6]

    房建成, 宁晓琳, 刘劲 2017 航天器自主天文导航原理与技术 (第二版) (北京: 国防工业出版社) 第8页

    Fang J C, Ning X L, Liu J 2017 Principles and Methods of Spacecraft Celestial Navigation (2nd Ed.) (Beijing: National Defense Industry Press) p8 (in Chinese)

    [7]

    Hewish A, Bell S J, Pilkington J D H, Scott P F, Collins R A 1968 Nature 217 709Google Scholar

    [8]

    Thornton D 2013 Ph. D. Dissertation (Manchester: University of Manchester)

    [9]

    Stovall K, Lynch R S, Ransom S M, et al. 2014 Astrophys. J. 791 67Google Scholar

    [10]

    Manchester R N, Lyne A G, Camilo F, Bell J F, Kaspi V M, D'Amico N, McKay N P F, Crawford F, Stairs I H, Possenti A, Kramer M, Sheppard D C 2001 Mon. Not. R. Astron. Soc. 328 17Google Scholar

    [11]

    Keith M, Jameson A, Van Straten W, Bailes M, Johnston S, Kramer M, Possenti A, Bates S, Bhat N, Burgay M 2010 Mon. Not. R. Astron. Soc. 409 619Google Scholar

    [12]

    van Leeuwen J, Stappers B W 2010 Astron. Astrophys. 509 A7Google Scholar

    [13]

    许余云, 李菂, 刘志杰, 王晨, 王培, 张蕾, 潘之辰 2017 天文学进展 35 304Google Scholar

    Xu Y Y, Li D, Liu Z J, Wang C, Wang P, Zhang L, Pan Z C 2017 Prog. Astron. 35 304Google Scholar

    [14]

    王元超, 郑建华, 潘之辰, 李明涛 2018 深空探测学报 5 203

    Wang Y C, Zheng J H, Pan Z C, Li M T 2018 J. Deep Space Explor. 5 203

    [15]

    Lee K J, Stovall K, Jenet F A, Martinez J, Dartez L P, Mata A, Lunsford G, Cohen S, Biwer C M, Rohr M D 2013 Mon. Not. R. Astron. Soc. 433 688Google Scholar

    [16]

    Mohamed T M 2018 Futur. Comput. Inf. J. 3 1

    [17]

    Eatough R P, Molkenthin N, Kramer M, Noutsos A, Keith M J, Stappers B W, Lyne A G 2010 Mon. Not. R. Astron. Soc. 407 2443Google Scholar

    [18]

    Bates S D, Bailes M, Barsdell B R, Bhat N D R, Burgay M, Burke-Spolaor S, Champion D J, Coster P, D'Amico N, Jameson A, Johnston S, Keith M J, Kramer M, Levin L, Lyne A, Milia S, Ng C, Nietner C, Possenti A, Stappers B, Thornton D, van Straten W 2012 Mon. Not. R. Astron. Soc. 427 1052Google Scholar

    [19]

    Zhu W W, Berndsen A, Madsen E C, et al. 2014 Astrophys. J. 781 117Google Scholar

    [20]

    Lyon R J, Stappers B W, Cooper S, Brooke J M, Knowles J D 2016 Mon. Not. R. Astron. Soc. 459 1104Google Scholar

    [21]

    Wang H F, Zhu W W, Guo P, Li D, Feng S B, Yin Q, Miao C C, Tao Z Z, Pan Z C, Wang P, Zheng X, Deng X D, Liu Z J, Xie X Y, Yu X H, You S P, Zhang H 2019 Sci. China, Phys. Mech. Astron. 62 959507Google Scholar

    [22]

    Klambauer G, Unterthiner T, Mayr A, Hochreiter S 2017 Advances in Neural Information Processing Systems, Long Beach, USA, December 4–9, 2017 p971

    [23]

    Oh I S, Lee J S, Moon B R 2004 IEEE Trans. Pattern Anal. Mach. Intell. 26 1424Google Scholar

    [24]

    Chawla N V, Bowyer K W, Hall L O, Kegelmeyer W P 2002 J. Artif. Intell. Res. 16 321Google Scholar

    [25]

    Morello V, Barr E D, Bailes M, Flynn C M, Keane E F, van Straten W 2014 Mon. Not. R. Astron. Soc. 443 1651Google Scholar

    [26]

    Yao Y, Xin X, Guo P 2016 12th International Conference on Computational Intelligence and Security, Wuxi, China, December 16–19, 2016 p120

    [27]

    Nan R D, Li D, Jin C J, Wang Q M, Zhu L C, Zhu W B, Zhang H Y, Yue Y L, Qian L 2011 Int. J. Mod. Phys. D. 20 989Google Scholar

  • 图 1  SELU激活函数

    Fig. 1.  SELU activation function.

    图 2  GMO_SNN候选体选择算法流程图

    Fig. 2.  GMO_SNN candidate selection algorithm.

    图 3  SNN与ANN损失函数的对比

    Fig. 3.  Comparison of the loss function between SNN and ANN.

    表 1  脉冲星候选体数据集

    Table 1.  Pulsar candidate datasets.

    数据集非脉冲星数脉冲星数总样本数
    HTRU 189996119691192
    HTRU 216259163917898
    LOTAAS 14987665053
    下载: 导出CSV

    表 2  特征描述

    Table 2.  Feature description.

    编号特征编号特征
    1P12轮廓直方图最大值/高斯拟合的最大值
    2DM13对轮廓求导后的直方图与轮廓直方图的偏移量
    3S/N14$S/N/\sqrt {\left( {P - W} \right)/W} $
    4W15拟合$S/N/\sqrt {\left( {P - W} \right)/W} $
    5用sin曲线拟合脉冲轮廓的卡方值16DM拟合值与DM最优值取余
    6用sin2曲线拟合脉冲轮廓的卡方值17DM曲线拟合的卡方值
    7高斯拟合脉冲轮廓的卡方值18峰值处对应的所有频段值的均方根
    8高斯拟合脉冲轮廓的半高宽19任意两个频段线性相关度的均值
    9双高斯拟合脉冲轮廓的卡方值20线性相关度的和
    10双高斯拟合脉冲轮廓的平均半高宽21脉冲轮廓的波峰数
    11脉冲轮廓直方图对0的偏移量22脉冲轮廓减去均值后的面积
    下载: 导出CSV

    表 3  不同隐藏层数下的分类效果

    Table 3.  Classification results with the different hidden layers.

    隐藏层数F1-score/%
    282.48
    489.58
    894.56
    994.20
    下载: 导出CSV

    表 4  不同批次大小下的分类效果

    Table 4.  Classification results with the different batch size.

    批次大小F1-score/%运行时间/s
    1694.8774
    3294.5643
    6493.9023
    12891.0511
    下载: 导出CSV

    表 5  不同学习速率的分类效果

    Table 5.  Classification results with the different learning rates.

    隐藏层数F1-score/%
    0.1无法收敛
    0.0194.29
    0.00194.55
    0.000184.10
    下载: 导出CSV

    表 6  不同方法在3个数据集上的分类效果

    Table 6.  Classification results with different methods on three datasets.

    数据集模型Accuracy/%Recall/%Precison/%F1-score/%FPR/%G-mean/%
    HTRU 1SNN99.8292.4493.4592.940.0896.11
    GA_SNN99.8592.4595.1993.800.0696.12
    MO_SNN99.8194.2397.9496.050.0597.05
    GMO_SNNNNNNNNN99.8595.3298.5196.890.0497.61
    HTRU 2SNN98.3087.7393.9390.730.5993.38
    GA_SNN98.3088.9192.8690.840.7193.96
    MO_SNN97.8992.1795.0893.600.9595.54
    GMO_SNNNNNNNNN98.0392.5395.5894.030.0895.78
    LOTAAS 1SNN99.9293.75100.0096.770.0896.79
    GA_SNN99.92100.0093.3396.550100.00
    MO_SNN99.69100.0087.1093.100.3199.84
    GMO_SNN100.00100.00100.00100.000100.00
    下载: 导出CSV
  • [1]

    孙海峰, 谢楷, 李小平, 方海燕, 刘秀平, 傅灵忠, 孙海建, 薛梦凡 2013 物理学报 62 109701Google Scholar

    Sun H F, Xie K, Li X P, Fang H Y, Liu X P, Fu L Z, Sun H J, Xue M F 2013 Acta Phys. Sin. 62 109701Google Scholar

    [2]

    Heiles C, Li D, Mcclure-Griffiths N, Qian L, Liu S 2019 Res. Astron. Astrophys. 19 5Google Scholar

    [3]

    Yi S X, Zhang S N 2016 Sci. China, Phys. Mech. Astron. 59 689511Google Scholar

    [4]

    Liu J, Ning X L, Ma X, Fang J C 2019 IEEE Trans. Aerosp. Electron. Syst. 55 2556Google Scholar

    [5]

    康志伟, 吴春艳, 刘劲, 马辛, 桂明臻 2018 物理学报 67 099701Google Scholar

    Kang Z W, Wu C Y, Liu J, Ma X, Gui M Z 2018 Acta Phys. Sin. 67 099701Google Scholar

    [6]

    房建成, 宁晓琳, 刘劲 2017 航天器自主天文导航原理与技术 (第二版) (北京: 国防工业出版社) 第8页

    Fang J C, Ning X L, Liu J 2017 Principles and Methods of Spacecraft Celestial Navigation (2nd Ed.) (Beijing: National Defense Industry Press) p8 (in Chinese)

    [7]

    Hewish A, Bell S J, Pilkington J D H, Scott P F, Collins R A 1968 Nature 217 709Google Scholar

    [8]

    Thornton D 2013 Ph. D. Dissertation (Manchester: University of Manchester)

    [9]

    Stovall K, Lynch R S, Ransom S M, et al. 2014 Astrophys. J. 791 67Google Scholar

    [10]

    Manchester R N, Lyne A G, Camilo F, Bell J F, Kaspi V M, D'Amico N, McKay N P F, Crawford F, Stairs I H, Possenti A, Kramer M, Sheppard D C 2001 Mon. Not. R. Astron. Soc. 328 17Google Scholar

    [11]

    Keith M, Jameson A, Van Straten W, Bailes M, Johnston S, Kramer M, Possenti A, Bates S, Bhat N, Burgay M 2010 Mon. Not. R. Astron. Soc. 409 619Google Scholar

    [12]

    van Leeuwen J, Stappers B W 2010 Astron. Astrophys. 509 A7Google Scholar

    [13]

    许余云, 李菂, 刘志杰, 王晨, 王培, 张蕾, 潘之辰 2017 天文学进展 35 304Google Scholar

    Xu Y Y, Li D, Liu Z J, Wang C, Wang P, Zhang L, Pan Z C 2017 Prog. Astron. 35 304Google Scholar

    [14]

    王元超, 郑建华, 潘之辰, 李明涛 2018 深空探测学报 5 203

    Wang Y C, Zheng J H, Pan Z C, Li M T 2018 J. Deep Space Explor. 5 203

    [15]

    Lee K J, Stovall K, Jenet F A, Martinez J, Dartez L P, Mata A, Lunsford G, Cohen S, Biwer C M, Rohr M D 2013 Mon. Not. R. Astron. Soc. 433 688Google Scholar

    [16]

    Mohamed T M 2018 Futur. Comput. Inf. J. 3 1

    [17]

    Eatough R P, Molkenthin N, Kramer M, Noutsos A, Keith M J, Stappers B W, Lyne A G 2010 Mon. Not. R. Astron. Soc. 407 2443Google Scholar

    [18]

    Bates S D, Bailes M, Barsdell B R, Bhat N D R, Burgay M, Burke-Spolaor S, Champion D J, Coster P, D'Amico N, Jameson A, Johnston S, Keith M J, Kramer M, Levin L, Lyne A, Milia S, Ng C, Nietner C, Possenti A, Stappers B, Thornton D, van Straten W 2012 Mon. Not. R. Astron. Soc. 427 1052Google Scholar

    [19]

    Zhu W W, Berndsen A, Madsen E C, et al. 2014 Astrophys. J. 781 117Google Scholar

    [20]

    Lyon R J, Stappers B W, Cooper S, Brooke J M, Knowles J D 2016 Mon. Not. R. Astron. Soc. 459 1104Google Scholar

    [21]

    Wang H F, Zhu W W, Guo P, Li D, Feng S B, Yin Q, Miao C C, Tao Z Z, Pan Z C, Wang P, Zheng X, Deng X D, Liu Z J, Xie X Y, Yu X H, You S P, Zhang H 2019 Sci. China, Phys. Mech. Astron. 62 959507Google Scholar

    [22]

    Klambauer G, Unterthiner T, Mayr A, Hochreiter S 2017 Advances in Neural Information Processing Systems, Long Beach, USA, December 4–9, 2017 p971

    [23]

    Oh I S, Lee J S, Moon B R 2004 IEEE Trans. Pattern Anal. Mach. Intell. 26 1424Google Scholar

    [24]

    Chawla N V, Bowyer K W, Hall L O, Kegelmeyer W P 2002 J. Artif. Intell. Res. 16 321Google Scholar

    [25]

    Morello V, Barr E D, Bailes M, Flynn C M, Keane E F, van Straten W 2014 Mon. Not. R. Astron. Soc. 443 1651Google Scholar

    [26]

    Yao Y, Xin X, Guo P 2016 12th International Conference on Computational Intelligence and Security, Wuxi, China, December 16–19, 2016 p120

    [27]

    Nan R D, Li D, Jin C J, Wang Q M, Zhu L C, Zhu W B, Zhang H Y, Yue Y L, Qian L 2011 Int. J. Mod. Phys. D. 20 989Google Scholar

  • [1] 武长春, 周莆钧, 王俊杰, 李国, 胡绍刚, 于奇, 刘洋. 基于忆阻器的脉冲神经网络硬件加速器架构设计. 物理学报, 2022, 71(14): 148401. doi: 10.7498/aps.71.20220098
    [2] 王朝辉, 李勇祥, 朱帅. 基于超表面的旋向选择吸波体. 物理学报, 2020, 69(23): 234103. doi: 10.7498/aps.69.20200511
    [3] 方海燕, 刘兵, 李小平, 孙海峰, 薛梦凡, 沈利荣, 朱金鹏. 一种基于最优频段的X射线脉冲星累积轮廓时延估计方法. 物理学报, 2016, 65(11): 119701. doi: 10.7498/aps.65.119701
    [4] 郭业才, 周林锋. 基于脉冲耦合神经网络和图像熵的各向异性扩散模型研究. 物理学报, 2015, 64(19): 194204. doi: 10.7498/aps.64.194204
    [5] 薛梦凡, 李小平, 孙海峰, 刘兵, 方海燕, 沈利荣. 一种新的X射线脉冲星信号模拟方法. 物理学报, 2015, 64(21): 219701. doi: 10.7498/aps.64.219701
    [6] 贝晓敏, 帅平, 黄良伟, 孙海峰, 吴耀军, 张倩. 一种脉冲星信号模拟新方法. 物理学报, 2014, 63(21): 219701. doi: 10.7498/aps.63.219701
    [7] 李欢, 王友国. 一类非线性神经网络中噪声改善信息传输. 物理学报, 2014, 63(12): 120506. doi: 10.7498/aps.63.120506
    [8] 孟广慧, 林鑫. 二元层片共晶凝固过程的特征尺度选择. 物理学报, 2014, 63(6): 068104. doi: 10.7498/aps.63.068104
    [9] 李勇军, 刘尊, 于会. 基于最大熵模型的导师-学生关系推测. 物理学报, 2013, 62(16): 168902. doi: 10.7498/aps.62.168902
    [10] 李建勋, 柯熙政, 赵宝升. 一种脉冲星周期的时域估计新方法. 物理学报, 2012, 61(6): 069701. doi: 10.7498/aps.61.069701
    [11] 郭永峰, 谭建国. 一类非线性神经网络系统的超阈值随机共振现象. 物理学报, 2012, 61(17): 170502. doi: 10.7498/aps.61.170502
    [12] null. 初始位置布局不平衡的疏散行人流仿真研究. 物理学报, 2012, 61(13): 130509. doi: 10.7498/aps.61.130509
    [13] 徐念喜, 冯晓国, 王岩松, 陈新, 高劲松. 微型化频率选择表面的设计研究. 物理学报, 2011, 60(11): 114102. doi: 10.7498/aps.60.114102
    [14] 刘朝华, 章兢, 张英杰, 李小花, 吴建辉. 一类不确定离散混沌系统的自抗扰控制器与小脑神经网络并行优化控制. 物理学报, 2011, 60(3): 030701. doi: 10.7498/aps.60.030701
    [15] 赵洪涌, 陈凌, 于小红. 一类惯性神经网络的分岔与控制. 物理学报, 2011, 60(7): 070202. doi: 10.7498/aps.60.070202
    [16] 王兴元, 赵 群. 一类不确定延迟神经网络的自适应投影同步. 物理学报, 2008, 57(5): 2812-2818. doi: 10.7498/aps.57.2812
    [17] 张军峰, 胡寿松. 基于一种新型聚类算法的RBF神经网络混沌时间序列预测. 物理学报, 2007, 56(2): 713-719. doi: 10.7498/aps.56.713
    [18] 王占山, 张化光, 王智良. 一类混沌神经网络的全局同步. 物理学报, 2006, 55(6): 2687-2693. doi: 10.7498/aps.55.2687
    [19] 郭旗, 田野, 刘承宜. 自散焦介质中光束聚焦的最佳参数选择. 物理学报, 2002, 51(5): 1057-1062. doi: 10.7498/aps.51.1057
    [20] 王宏霞, 虞厥邦. 细胞神经网络平衡态的稳定性分析. 物理学报, 2001, 50(12): 2303-2306. doi: 10.7498/aps.50.2303
计量
  • 文章访问数:  5880
  • PDF下载量:  98
  • 被引次数: 0
出版历程
  • 收稿日期:  2019-10-17
  • 修回日期:  2019-12-19
  • 刊出日期:  2020-03-20

/

返回文章
返回