Abstract
Reliable tools for artefact rejection and signal classification are a must for cosmic ray detection experiments based on CMOS technology. In this paper, we analyse the fitness of several feature-based statistical classifiers for the classification of particle candidate hits in four categories: spots, tracks, worms and artefacts. We use Zernike moments of the image function as feature carriers and propose a preprocessing and denoising scheme to make the feature extraction more efficient. As opposed to convolution neural network classifiers, the feature-based classifiers allow for establishing a connection between features and geometrical properties of candidate hits. Apart from basic classifiers we also consider their ensemble extensions and find these extensions generally better performing than basic versions, with an average recognition accuracy of 88%.
Highlights
Cosmic rays are actively studied by astrophysicists, due to their as-yet-unknown unknown origin and enormous peak energies
We describe a method of signal classification for cosmic ray images, called hits, obtained from CMOS sensors mounted in smartphones equipped with the specialized CREDO Detector application [10]
We present the classification results and optimal hyperparameters obtained in the optimization phase as well as their mean accuracies and standard deviations from the evaluation phase for both basic classifiers and ensemble models
Summary
Cosmic rays are actively studied by astrophysicists, due to their as-yet-unknown unknown origin and enormous peak energies. Studying cosmic rays by using a worldwide network of mobile devices as an extremely distributed radiation detector was proposed by several research groups [7,8,9] and can be treated as an example of the citizen science paradigm. Practical application of this paradigm requires overcoming several obstacles like the identification and rejection of artefacts: i.e., images that cannot be attributed to a particle’s passage through the sensor. Unlike other solutions discussed in the literature [11,12,13] where Convolutional Neural Networks were used for the online or offline trigger and offline signal classification, respectively, we instead use a feature-based solution
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
