Machine learning aided noise filtration and signalc lassification for CREDO experiment
@inproceedings{Bibrzycki2021MachineLA, title={Machine learning aided noise filtration and signalc lassification for CREDO experiment}, author={Lukasz Bibrzycki and David E. Alvarez-Castillo and Olaf Bar and Dariusz G{\'o}ra and Piotr Homola and P'eter Kov'acs and Michal Nied'zwiecki and Marcin Piekarczyk and Krzysztof Rzecki and Jaroslaw Stasielak and Sławomir Stuglik and Oleksandr Sushchov and Arman Tursunov}, year={2021} }
The wealth of smartphone data collected by the Cosmic Ray Extremely Distributed Observatory (CREDO) greatly surpasses the capabilities of manual analysis. So, efficient means of rejecting the non-cosmic-ray noise and identification of signals attributable to extensive air showers are necessary. To address these problems we discuss a Convolutional Neural Network-based method of artefact rejection and complementary method of particle identification based on common statistical classifiers as well…
References
SHOWING 1-10 OF 20 REFERENCES
CNN-Based Classifier as an Offline Trigger for the CREDO Experiment
- Computer ScienceSensors
- 2021
To tag the artefacts appearing in the CREDO database with a CNN-based trigger, the method based on machine learning allows eliminating the manual supervision of the competition process.
Removing cosmic-ray hits from CCD images in real-time mode by means of an artificial neural network
- Physics
- 2006
A feed-forward artificial neural network has been implemented to the problem of removing cosmic-ray hits (CRH) from CCD images. The results of a number of tests demonstrate the effectiveness of this…
Muon Trigger for Mobile Phones
- Physics, Computer ScienceArXiv
- 2017
A trigger algorithm based on Convolutional Neural Networks is presented which increases the sensitivity considerably comparable with image thresholding, while the lazy evaluation allows for execution of the trigger under the limited computational power of mobile phones.
Evaluation of wavelet transform preprocessing with deep learning aimed at palm vein recognition application
- Computer ScienceTHE 4TH BIOMEDICAL ENGINEERING’S RECENT PROGRESS IN BIOMATERIALS, DRUGS DEVELOPMENT, HEALTH, AND MEDICAL DEVICES: Proceedings of the International Symposium of Biomedical Engineering (ISBE) 2019
- 2019
The accuracy of the wavelet transforms and enhanced palm vein images are more than 92%.
Towards A Global Cosmic Ray Sensor Network: CREDO Detector as the First Open-Source Mobile Application Enabling Detection of Penetrating Radiation
- PhysicsSymmetry
- 2020
We present the purpose, long-term development vision, basic design, detection algorithm and preliminary results obtained with the Cosmic Ray Extremely Distributed Observatory (CREDO) Detector mobile…
Explainable AI: A Review of Machine Learning Interpretability Methods
- Computer ScienceEntropy
- 2021
This study focuses on machine learning interpretability methods; more specifically, a literature review and taxonomy of these methods are presented, as well as links to their programming implementations, in the hope that this survey would serve as a reference point for both theorists and practitioners.
Cosmic rays and other nonsense in astronomical CCD imagers
- Physics
- 2002
Cosmic-ray muons make recognizable straight tracks in the new-generation CCD's with thick sensitive regions. Wandering tracks (‘worms’), which we identify with multiply-scattered low-energy…
Cosmic-Ray Extremely Distributed Observatory
- PhysicsSymmetry
- 2020
The CREDO Collaboration invites the astroparticle physics community to actively join or to contribute to the research dedicated to CRE, and in particular to share any cosmic ray data useful for the specific CRE detection strategies.
Recognition of facial expressions using locally weighted and adjusted order Pseudo Zernike Moments
- Computer ScienceProceedings of the 21st International Conference on Pattern Recognition (ICPR2012)
- 2012
A novel facial expression recognition approach based on locally weighted and adjusted order Pseudo Zernike Moments (PZM) is proposed, which is one of the best descriptors that are robust to noise and rotation.