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

一种基于轻量化CNN的天文暂现源智能识别方法

李晓斌 薛长斌 戴育岐 周莉

李晓斌, 薛长斌, 戴育岐, 周莉. 一种基于轻量化CNN的天文暂现源智能识别方法[J]. 空间科学学报, 2023, 43(1): 112-118. doi: 10.11728/cjss2023.01.211224133
引用本文: 李晓斌, 薛长斌, 戴育岐, 周莉. 一种基于轻量化CNN的天文暂现源智能识别方法[J]. 空间科学学报, 2023, 43(1): 112-118. doi: 10.11728/cjss2023.01.211224133
LI Xiaobin, XUE Changbin, DAI Yuqi, ZHOU Li. An Intelligent Detection Method of Astronomical Transients Based on Lightweight CNN Model (in Chinese). Chinese Journal of Space Science, 2023, 43(1): 112-118 doi: 10.11728/cjss2023.01.211224133
Citation: LI Xiaobin, XUE Changbin, DAI Yuqi, ZHOU Li. An Intelligent Detection Method of Astronomical Transients Based on Lightweight CNN Model (in Chinese). Chinese Journal of Space Science, 2023, 43(1): 112-118 doi: 10.11728/cjss2023.01.211224133

一种基于轻量化CNN的天文暂现源智能识别方法

doi: 10.11728/cjss2023.01.211224133
基金项目: 中国科学院GF科技重点实验室基金项目资助(CXJJ-20 S017)
详细信息
    作者简介:

    李晓斌:E-mail:lixiaobinwf@126.com

  • 中图分类号: P152,TP391

An Intelligent Detection Method of Astronomical Transients Based on Lightweight CNN Model

  • 摘要: 天文暂现源携带了关于天体本质及演化过程的丰富信息,对暂现源进行探测与研究具有极为重要的科学价值。天文暂现源的辐射峰值大多在X射线或伽马射线,天基望远镜对这些高能波段的观测优势是地基望远镜无法比拟的,更适合于暂现源观测。但由于星载计算机的性能约束,很难实现依托于地面强大算力的复杂检测算法。针对以上问题,提出了基于轻量化卷积神经网络(CNN)模型的天基暂现源检测算法,并在嵌入式ARM平台上实现了模型部署。实验结果表明,本文提出的轻量化CNN暂现源检测算法的模型复杂度和计算量不及Deep Hits算法的1/4,准确率达到96.52%,可应用于星载有限算力平台,实现未来的天基暂现源实时检测。

     

  • 图  1  星地协同在轨暂现源智能检测系统

    Figure  1.  Satellite-ground coordinated on-orbit transients intelligent detection system

    图  2  预处理后的图像数据。每一组图像从左到右依次为模板图像、科学图像、差分图像、信噪比图像。label=1.0代表真实暂现源,label=0.0代表伪暂现源

    Figure  2.  Preprocessed image data. Each group of images from left to right are template image, scientific image, differential image, signal-to-noise ratio image. label=1.0 represents the real transients, label=0.0 represents the pseudo transients

    图  3  轻量化CNN网络模型架构(C代表卷积层、P代表池化层、FC代表全连接层,池化层采用最大池化策略,激活函数采用RELU函数)

    Figure  3.  Lightweight CNN network model architecture (C represents the convolutional layer, P represents the pooling layer, FC represents the fully connected layer, the pooling layer adopts the maximum pooling strategy, and the activation function adopts the RELU function)

    图  4  轻量化CNN网络模型训练流程(损失函数采用交叉熵损失函数,优化函数采用Adam优化函数)

    Figure  4.  Lightweight CNN network model training process (Loss function adopts the cross-entropy loss function, and the optimization function adopts the Adam optimization function)

    图  5  模型部署流程

    Figure  5.  Model deployment process

    图  6  训练损失率

    Figure  6.  Training loss rate

    图  7  测试准确率

    Figure  7.  Test accuracy rate

    表  1  预测结果混淆矩阵

    Table  1.   Confusion matrix of prediction results

    实际情况预测结果
    正例反例
    正例6901(PT)299(NF)
    反例151(PF)6956(NT)
    下载: 导出CSV

    表  2  模型复杂度对比

    Table  2.   Comparison of model complexity

    模型名称参数量/kByte模型大小/MByte计算量/MFlops准确率/(%)
    Deep-Hits[4] 1705.67 6.86 97.36 99.45
    轻量化CNN 407.10 1.57 20.13 96.52
    R-DIA[7] 90.89
    下载: 导出CSV
  • [1] YU Hai. Applications of Transients and Other Observations in Cosmology[D]. Nanjing: Nanjing University, 2019
    [2] ZHAO Yifei. Astronomical Transient Source Recognition Based on Deep Learning and Raspberry Pi[D]. Taiyuan: Taiyuan University of Technology, 2019
    [3] PENG Bin, LI Zheng, LIU Yong, et al. Automatic code comments generation method based on convolutional neural network[J]. Computer Science, 2021, 48(12): 117-124 doi: 10.11896/jsjkx.201100090
    [4] CABRERA-VIVES G, REYES I, FÖRSTER F, et al. Deep-HiTS: rotation invariant convolutional neural network for transient detection[J]. The Astrophysical Journal, 2017, 836(1): 97 doi: 10.3847/1538-4357/836/1/97
    [5] SEDAGHAT N, MAHABAL A. Effective image differencing with convolutional neural networks for real-time transient hunting[J]. Monthly Notices of the Royal Astronomical Society, 2018, 476(4): 5365-5376 doi: 10.1093/mnras/sty613
    [6] CONNOR L, VAN LEEUWEN J. Applying deep learning to fast radio burst classification[J]. The Astronomical Journal, 2018, 156(6): 256 doi: 10.3847/1538-3881/aae649
    [7] HUANG Tianjun. Research on Detecting Transients and Variable Sources in AST3-2 Survey[D]. Hefei: University of Science and Technology of China, 2019
    [8] CHEN Xiaotong. Research on aviation sheet metal parts missing detection technology based on VGG technology[J]. Modern Industrial Economy and Informationization, 2021, 11(9): 219-220
    [9] XU L Y, GAJIC Z. Improved network for face recognition based on feature super resolution method[J]. International Journal of Automation and Computing, 2021, 18(6): 915-925 doi: 10.1007/s11633-021-1309-9
    [10] RAN H H, WEN S P, SHI K B, et al. Stable and compact design of memristive GoogLeNet neural network[J]. Neurocomputing, 2021, 441: 52-63 doi: 10.1016/j.neucom.2021.01.122
    [11] TAN Y H, JING X J. Cooperative spectrum sensing based on convolutional neural networks[J]. Applied Sciences, 2021, 11(10): 4440 doi: 10.3390/app11104440
  • 加载中
图(7) / 表(2)
计量
  • 文章访问数:  207
  • HTML全文浏览量:  78
  • PDF下载量:  39
  • 被引次数: 0
出版历程
  • 收稿日期:  2021-12-16
  • 录用日期:  2022-04-11
  • 修回日期:  2022-07-28
  • 网络出版日期:  2022-11-19

目录

    /

    返回文章
    返回