Recognition of Cosmic Ray Images Obtained from CMOS Sensors Used in Mobile Phones by Approximation of Uncertain Class Assignment with Deep Convolutional Neural Network.
Recognition of Cosmic Ray Images Obtained from CMOS Sensors Used in Mobile Phones by Approximation of Uncertain Class Assignment with Deep Convolutional Neural Network.
复制标题
DOI：
10.3390/s21061963
复制
发表时间：
2021-03-11
期刊：
影响因子：
--
通讯作者：
Piekarczyk M
中科院分区：
文献类型：
--
作者：
Hachaj T;Bibrzycki Ł;Piekarczyk M
在本文中，我们描述了卷积神经网络（CNN）为基础的方法的分类和伪影减少宇宙射线图像中使用的CMOS传感器在移动的手机的问题。作为伪影，我们理解不能归因于颗粒通过传感器而是由配准过程的缺陷引起的所有图像。所提出的深度神经网络由预训练的CNN和基于神经网络的近似器组成，该近似器对图像类别分配的不确定性进行建模。该网络使用具有均方误差损失函数的迁移学习方法进行训练。我们在包含由五位评委标记的2350张图像的数据集上评估了我们的方法。使用VGG 16 CNN架构获得了最准确的结果;识别率（RR）为85.79% ± 2.24%，均方误差（MSE）为0.03 ± 0.00。在应用所提出的阈值方案来消除不太可能的类别分配之后，我们获得了阈值为0.9的RR为96.95% ± 1.38%，这使得总体数据的约62.60% ± 2.88%。重要的是，本文中提出的研究和结果是公民科学在宇宙射线识别中应用的开创性领域的一部分，据我们所知，这种分析是在最大的免费宇宙射线命中数据集上进行的。
In this paper, we describe the convolutional neural network (CNN)-based approach to the problems of categorization and artefact reduction of cosmic ray images obtained from CMOS sensors used in mobile phones. As artefacts, we understand all images that cannot be attributed to particles’ passage through sensor but rather result from the deficiencies of the registration procedure. The proposed deep neural network is composed of a pretrained CNN and neural-network-based approximator, which models the uncertainty of image class assignment. The network was trained using a transfer learning approach with a mean squared error loss function. We evaluated our approach on a data set containing 2350 images labelled by five judges. The most accurate results were obtained using the VGG16 CNN architecture; the recognition rate (RR) was 85.79% ± 2.24% with a mean squared error (MSE) of 0.03 ± 0.00. After applying the proposed threshold scheme to eliminate less probable class assignments, we obtained a RR of 96.95% ± 1.38% for a threshold of 0.9, which left about 62.60% ± 2.88% of the overall data. Importantly, the research and results presented in this paper are part of the pioneering field of the application of citizen science in the recognition of cosmic rays and, to the best of our knowledge, this analysis is performed on the largest freely available cosmic ray hit dataset.
登录
查看更多内容
影响因子：
3.1
作者：
Kim, Jungsik;Lee, Jeong-Soo;Meyyappan, M.
通讯作者：
Meyyappan, M.
影响因子：
4.6
作者：
Bressem, Keno K.;Adams, Lisa C.;Vahldiek, Janis L.
通讯作者：
Vahldiek, Janis L.
影响因子：
2.7
作者：
Bibrzycki, Lukasz;Burakowski, Dariusz;Zamora-Saa, Jilberto
通讯作者：
Zamora-Saa, Jilberto
使用多模态卷积神经网络进行基于 RGB-D 的物体识别：一项调查
影响因子：
3.9
作者：
Gao, Mingliang;Jiang, Jun;Liu, Zheng
通讯作者：
Liu, Zheng
影响因子：
3.9
作者：
Jiao, Licheng;Zhang, Fan;Qu, Rong
通讯作者：
Qu, Rong