Cargando…

CNN-Based Classifier as an Offline Trigger for the CREDO Experiment

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 fr...

Descripción completa

Detalles Bibliográficos
Autores principales: Piekarczyk, Marcin, Bar, Olaf, Bibrzycki, Łukasz, Niedźwiecki, Michał, Rzecki, Krzysztof, Stuglik, Sławomir, Andersen, Thomas, Budnev, Nikolay M., Alvarez-Castillo, David E., Cheminant, Kévin Almeida, Góra, Dariusz, Gupta, Alok C., Hnatyk, Bohdan, Homola, Piotr, Kamiński, Robert, Kasztelan, Marcin, Knap, Marek, Kovács, Péter, Łozowski, Bartosz, Miszczyk, Justyna, Mozgova, Alona, Nazari, Vahab, Pawlik, Maciej, Rosas, Matías, Sushchov, Oleksandr, Smelcerz, Katarzyna, Smolek, Karel, Stasielak, Jarosław, Wibig, Tadeusz, Woźniak, Krzysztof W., Zamora-Saa, Jilberto
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8309790/
https://www.ncbi.nlm.nih.gov/pubmed/34300544
http://dx.doi.org/10.3390/s21144804
_version_ 1783728605498441728
author Piekarczyk, Marcin
Bar, Olaf
Bibrzycki, Łukasz
Niedźwiecki, Michał
Rzecki, Krzysztof
Stuglik, Sławomir
Andersen, Thomas
Budnev, Nikolay M.
Alvarez-Castillo, David E.
Cheminant, Kévin Almeida
Góra, Dariusz
Gupta, Alok C.
Hnatyk, Bohdan
Homola, Piotr
Kamiński, Robert
Kasztelan, Marcin
Knap, Marek
Kovács, Péter
Łozowski, Bartosz
Miszczyk, Justyna
Mozgova, Alona
Nazari, Vahab
Pawlik, Maciej
Rosas, Matías
Sushchov, Oleksandr
Smelcerz, Katarzyna
Smolek, Karel
Stasielak, Jarosław
Wibig, Tadeusz
Woźniak, Krzysztof W.
Zamora-Saa, Jilberto
author_facet Piekarczyk, Marcin
Bar, Olaf
Bibrzycki, Łukasz
Niedźwiecki, Michał
Rzecki, Krzysztof
Stuglik, Sławomir
Andersen, Thomas
Budnev, Nikolay M.
Alvarez-Castillo, David E.
Cheminant, Kévin Almeida
Góra, Dariusz
Gupta, Alok C.
Hnatyk, Bohdan
Homola, Piotr
Kamiński, Robert
Kasztelan, Marcin
Knap, Marek
Kovács, Péter
Łozowski, Bartosz
Miszczyk, Justyna
Mozgova, Alona
Nazari, Vahab
Pawlik, Maciej
Rosas, Matías
Sushchov, Oleksandr
Smelcerz, Katarzyna
Smolek, Karel
Stasielak, Jarosław
Wibig, Tadeusz
Woźniak, Krzysztof W.
Zamora-Saa, Jilberto
author_sort Piekarczyk, Marcin
collection PubMed
description 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.
format Online
Article
Text
id pubmed-8309790
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-83097902021-07-25 CNN-Based Classifier as an Offline Trigger for the CREDO Experiment Piekarczyk, Marcin Bar, Olaf Bibrzycki, Łukasz Niedźwiecki, Michał Rzecki, Krzysztof Stuglik, Sławomir Andersen, Thomas Budnev, Nikolay M. Alvarez-Castillo, David E. Cheminant, Kévin Almeida Góra, Dariusz Gupta, Alok C. Hnatyk, Bohdan Homola, Piotr Kamiński, Robert Kasztelan, Marcin Knap, Marek Kovács, Péter Łozowski, Bartosz Miszczyk, Justyna Mozgova, Alona Nazari, Vahab Pawlik, Maciej Rosas, Matías Sushchov, Oleksandr Smelcerz, Katarzyna Smolek, Karel Stasielak, Jarosław Wibig, Tadeusz Woźniak, Krzysztof W. Zamora-Saa, Jilberto Sensors (Basel) Article 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. MDPI 2021-07-14 /pmc/articles/PMC8309790/ /pubmed/34300544 http://dx.doi.org/10.3390/s21144804 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Piekarczyk, Marcin
Bar, Olaf
Bibrzycki, Łukasz
Niedźwiecki, Michał
Rzecki, Krzysztof
Stuglik, Sławomir
Andersen, Thomas
Budnev, Nikolay M.
Alvarez-Castillo, David E.
Cheminant, Kévin Almeida
Góra, Dariusz
Gupta, Alok C.
Hnatyk, Bohdan
Homola, Piotr
Kamiński, Robert
Kasztelan, Marcin
Knap, Marek
Kovács, Péter
Łozowski, Bartosz
Miszczyk, Justyna
Mozgova, Alona
Nazari, Vahab
Pawlik, Maciej
Rosas, Matías
Sushchov, Oleksandr
Smelcerz, Katarzyna
Smolek, Karel
Stasielak, Jarosław
Wibig, Tadeusz
Woźniak, Krzysztof W.
Zamora-Saa, Jilberto
CNN-Based Classifier as an Offline Trigger for the CREDO Experiment
title CNN-Based Classifier as an Offline Trigger for the CREDO Experiment
title_full CNN-Based Classifier as an Offline Trigger for the CREDO Experiment
title_fullStr CNN-Based Classifier as an Offline Trigger for the CREDO Experiment
title_full_unstemmed CNN-Based Classifier as an Offline Trigger for the CREDO Experiment
title_short CNN-Based Classifier as an Offline Trigger for the CREDO Experiment
title_sort cnn-based classifier as an offline trigger for the credo experiment
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8309790/
https://www.ncbi.nlm.nih.gov/pubmed/34300544
http://dx.doi.org/10.3390/s21144804
work_keys_str_mv AT piekarczykmarcin cnnbasedclassifierasanofflinetriggerforthecredoexperiment
AT barolaf cnnbasedclassifierasanofflinetriggerforthecredoexperiment
AT bibrzyckiłukasz cnnbasedclassifierasanofflinetriggerforthecredoexperiment
AT niedzwieckimichał cnnbasedclassifierasanofflinetriggerforthecredoexperiment
AT rzeckikrzysztof cnnbasedclassifierasanofflinetriggerforthecredoexperiment
AT stugliksławomir cnnbasedclassifierasanofflinetriggerforthecredoexperiment
AT andersenthomas cnnbasedclassifierasanofflinetriggerforthecredoexperiment
AT budnevnikolaym cnnbasedclassifierasanofflinetriggerforthecredoexperiment
AT alvarezcastillodavide cnnbasedclassifierasanofflinetriggerforthecredoexperiment
AT cheminantkevinalmeida cnnbasedclassifierasanofflinetriggerforthecredoexperiment
AT goradariusz cnnbasedclassifierasanofflinetriggerforthecredoexperiment
AT guptaalokc cnnbasedclassifierasanofflinetriggerforthecredoexperiment
AT hnatykbohdan cnnbasedclassifierasanofflinetriggerforthecredoexperiment
AT homolapiotr cnnbasedclassifierasanofflinetriggerforthecredoexperiment
AT kaminskirobert cnnbasedclassifierasanofflinetriggerforthecredoexperiment
AT kasztelanmarcin cnnbasedclassifierasanofflinetriggerforthecredoexperiment
AT knapmarek cnnbasedclassifierasanofflinetriggerforthecredoexperiment
AT kovacspeter cnnbasedclassifierasanofflinetriggerforthecredoexperiment
AT łozowskibartosz cnnbasedclassifierasanofflinetriggerforthecredoexperiment
AT miszczykjustyna cnnbasedclassifierasanofflinetriggerforthecredoexperiment
AT mozgovaalona cnnbasedclassifierasanofflinetriggerforthecredoexperiment
AT nazarivahab cnnbasedclassifierasanofflinetriggerforthecredoexperiment
AT pawlikmaciej cnnbasedclassifierasanofflinetriggerforthecredoexperiment
AT rosasmatias cnnbasedclassifierasanofflinetriggerforthecredoexperiment
AT sushchovoleksandr cnnbasedclassifierasanofflinetriggerforthecredoexperiment
AT smelcerzkatarzyna cnnbasedclassifierasanofflinetriggerforthecredoexperiment
AT smolekkarel cnnbasedclassifierasanofflinetriggerforthecredoexperiment
AT stasielakjarosław cnnbasedclassifierasanofflinetriggerforthecredoexperiment
AT wibigtadeusz cnnbasedclassifierasanofflinetriggerforthecredoexperiment
AT wozniakkrzysztofw cnnbasedclassifierasanofflinetriggerforthecredoexperiment
AT zamorasaajilberto cnnbasedclassifierasanofflinetriggerforthecredoexperiment