Application of Neural Networks to Classification of Data of the TUS Orbital Telescope

Zotov, M. Yu.

doi:10.3390/universe7070221

Cited by 9 publications

(5 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have seen in [33] that an ANN trained on data with clearly pronounced signals is able to identify patterns with low signal-to-noise ratio. Such events are classified as false positives during tests but their closer analysis reveals that their considerable part contains "positive" signals that were not found by the conventional algorithm used to prepare training and testing datasets.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Neural Network Based Approach to Recognition of Meteor Tracks in the Mini-EUSO Telescope Data

Zotov,

Anzhiganov,

Kryazhenkov

et al. 2023

Algorithms

Self Cite

View full text Add to dashboard Cite

Mini-EUSO is a wide-angle fluorescence telescope that registers ultraviolet (UV) radiation in the nocturnal atmosphere of Earth from the International Space Station. Meteors are among multiple phenomena that manifest themselves not only in the visible range but also in the UV. We present two simple artificial neural networks that allow for recognizing meteor signals in the Mini-EUSO data with high accuracy in terms of a binary classification problem. We expect that similar architectures can be effectively used for signal recognition in other fluorescence telescopes, regardless of the nature of the signal. Due to their simplicity, the networks can be implemented in onboard electronics of future orbital or balloon experiments.

show abstract

Section: Discussionmentioning

confidence: 99%

“…In [33], a simple convolutional neural network (CNN) was employed to perform binary classification of two types of signals registered with the TUS telescope. The instrument had a focal surface of 16 × 16 pixels, and data arranged in 16 × 16 × T chunks worked well.…”

Section: Recognition Of Meteor Data Samplesmentioning

confidence: 99%

Neural Network Based Approach to Recognition of Meteor Tracks in the Mini-EUSO Telescope Data

Zotov,

Anzhiganov,

Kryazhenkov

et al. 2023

Algorithms

Self Cite

View full text Add to dashboard Cite

show abstract

“…A totally different approach to the recognition of patterns produced by UV emission of EASs on the focal surface and to the reconstruction of parameters of primary UHECRs can be based on machine learning methods. A high efficiency of neural networks for identifying certain types of signals in the TUS data was demonstrated recently [61,62]. The first applications of neural networks to CR parameter reconstruction are also potentially interesting; see, e.g., [63][64][65].…”

Section: Energy Reconstructionmentioning

confidence: 98%

Status of the K-EUSO Orbital Detector of Ultra-High Energy Cosmic Rays

Климов¹,

Battisti²,

Белов³

et al. 2022

Universe

Self Cite

View full text Add to dashboard Cite

K-EUSO (KLYPVE-EUSO) is a planned orbital mission aimed at studying ultra-high energy cosmic rays (UHECRs) by detecting fluorescence and Cherenkov light emitted by extensive air showers in the nocturnal atmosphere of Earth in the ultraviolet (UV) range. The observatory is being developed within the JEM-EUSO collaboration and is planned to be deployed on the International Space Station after 2025 and operated for at least two years. The telescope, consisting of ∼105 independent pixels, will allow a spatial resolution of ∼0.6 km on the ground, and, from a 400 km altitude, it will achieve a large and full sky exposure to sample the highest energy range of the UHECR spectrum. We provide a comprehensive review of the current status of the development of the K-EUSO experiment, paying special attention to its hardware parts and expected performance. We demonstrate how results of the K-EUSO mission can complement the achievements of the existing ground-based experiments and push forward the intriguing studies of ultra-high energy cosmic rays, as well as bring new knowledge about other phenomena manifesting themselves in the atmosphere in the UV range.

show abstract

“…Two examples of reconstructed profiles of the signal from 100 EeV UHECRs arriving at the zenith angle of 60 • are shown in Figure 15 A totally different approach to the recognition of patterns produced by UV emission of EASs on the focal surface and to the reconstruction of parameters of primary UHECRs can be based on machine learning methods. A high efficiency of neural networks for identifying certain types of signals in the TUS data was demonstrated recently [61,62]. The first applications of neural networks to CR parameter reconstruction are also potentially interesting; see, e.g., [63][64][65].…”

Section: Energy Reconstructionmentioning

confidence: 98%