CNN-Based Classifier as an Offline Trigger for the CREDO Experiment.
CNN-Based Classifier as an Offline Trigger for the CREDO Experiment.
复制标题
DOI：
10.3390/s21144804
复制
发表时间：
2021-07-14
期刊：
影响因子：
--
通讯作者：
Zamora-Saa J
中科院分区：
文献类型：
--
作者：
Piekarczyk M;Bar O;Bibrzycki Ł;Niedźwiecki M;Rzecki K;Stuglik S;Andersen T;Budnev NM;Alvarez-Castillo DE;Cheminant KA;Góra D;Gupta AC;Hnatyk B;Homola P;Kamiński R;Kasztelan M;Knap M;Kovács P;Łozowski B;Miszczyk J;Mozgova A;Nazari V;Pawlik M;Rosas M;Sushchov O;Smelcerz K;Smolek K;Stasielak J;Wibig T;Woźniak KW;Zamora-Saa J
众所周知，游戏化可以提高用户对遵循公民科学范式的教育和研究项目的参与。宇宙射线极端分布观测台（CREDO）实验旨在大规模研究从空间持续到达地球的各种辐射形式，统称为宇宙射线。CREDO Detector应用程序依赖于相关用户的网络，目前在全球范围内的手机和其他配备CMOS传感器的设备上运行。为了扩大用户群并激活现有用户，CREDO广泛使用游戏化解决方案，如定期的粒子猎人竞赛。然而，游戏化的不利影响是，人工制品的数量，即，与宇宙射线探测无关或公开与欺骗有关的信号显著增加。为了标记出现在CREDO数据库中的人工制品，我们提出了基于机器学习的方法。该方法涉及训练卷积神经网络（CNN）来识别信号和伪影之间的形态差异。因此，我们获得了基于CNN的触发器，该触发器能够尽可能接近地模仿人类注释者的信号与伪影分配。为了增强该方法，输入图像信号自适应阈值，然后使用Daubechies小波变换。在这项探索性的研究中，我们使用小波变换来放大独特的图像特征。其结果是，我们获得了一个非常好的识别率几乎99%的信号和文物。所提出的解决方案允许消除竞争过程的人工监督。
Gamification is known to enhance users’ participation in education and research projects that follow the citizen science paradigm. The Cosmic Ray Extremely Distributed Observatory (CREDO) experiment is designed for the large-scale study of various radiation forms that continuously reach the Earth from space, collectively known as cosmic rays. The CREDO Detector app relies on a network of involved users and is now working worldwide across phones and other CMOS sensor-equipped devices. To broaden the user base and activate current users, CREDO extensively uses the gamification solutions like the periodical Particle Hunters Competition. However, the adverse effect of gamification is that the number of artefacts, i.e., signals unrelated to cosmic ray detection or openly related to cheating, substantially increases. To tag the artefacts appearing in the CREDO database we propose the method based on machine learning. The approach involves training the Convolutional Neural Network (CNN) to recognise the morphological difference between signals and artefacts. As a result we obtain the CNN-based trigger which is able to mimic the signal vs. artefact assignments of human annotators as closely as possible. To enhance the method, the input image signal is adaptively thresholded and then transformed using Daubechies wavelets. In this exploratory study, we use wavelet transforms to amplify distinctive image features. As a result, we obtain a very good recognition ratio of almost 99% for both signal and artefacts. The proposed solution allows eliminating the manual supervision of the competition process.
登录
查看更多内容
DOI：
10.3390/s21061963
发表时间：
2021-03-11
期刊：
Sensors (Basel, Switzerland)
影响因子：
--
作者：
Hachaj T;Bibrzycki Ł;Piekarczyk M
通讯作者：
Piekarczyk M
影响因子：
7.5
作者：
CORTES, C;VAPNIK, V
通讯作者：
VAPNIK, V
影响因子：
2.7
作者：
Bibrzycki, Lukasz;Burakowski, Dariusz;Zamora-Saa, Jilberto
通讯作者：
Zamora-Saa, Jilberto
影响因子：
1.3
作者：
Biau, Gerard;Scornet, Erwan
通讯作者：
Scornet, Erwan
影响因子：
3.9
作者：
Kim, Song-Kyoo;Yeun, Chan Yeob;Lo, Nai-Wei
通讯作者：
Lo, Nai-Wei