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

Abstract

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.

Zernike Moment Based Classification of Cosmic Ray Candidate Hits from CMOS Sensors

“…The comparison of the total brightness of the samples (Figures 2 and 3), shows that this parameter obviously divides the samples into 3 classes: 1-spots, 2-tracks+worms, 3artefacts, which is demonstrated in Figure 5. The luminosity based separation of artefacts vs. other classes was employed in the discussion of the CNN based trigger in [12]. This qualitative division is also supported by the properties of the Zernike moment spectrum.…”

“…In this study, we use the data set originally introduced in [12]. Recall that this set was annotated so that each image was assigned to one of the four classes: spots, tracks, worms and artefacts.…”

“…Recent analyses of data acquired by the CREDO experiment employed various CNN architectures to detect potentially relevant signals [12] and classify them [32]. Here, rather than CNN based classifiers, we discuss an approach based on the classical statistical learning classifiers implemented in the sci-kit-learn library [31].…”

“…In this paper, 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]. 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.…”

Application of Wigner Distribution Function for THz Propagation Analysis

“…This allows for the acceptance of spatial mapping and visualization of the EM field in 5G technology [ 9 ]. Using the CNN method with wavelet transform into a spectral representation of cosmic rays (composed of high-energy particles) obtained a very good recognition ratio by amplifying distinctive image features [ 10 ].…”