Abstract
In this paper we propose and evaluate several deep neural network (DNN) architectures that are capable to generate low-dimensional embedding of cosmic ray images obtained from CMOS cameras. All images have been acquired by the CREDO distributed cosmic ray observatory infrastructure. The embedding we obtained can also be used to classify those images using a threshold schema that models an uncertainty of class assignment. The proposed method has also a potential to be a filtering mechanism in order to search data set for images that satisfy certain criteria. The training and validation of the model has been performed on the labelled subset of the CREDO data set that contains 2350 images. We also performed an embedding and classification for the first time on a large subset of CREDO data containing 3.5 million unlabelled images. To the best of our knowledge, this is the most comprehensive study of this scale, published with CREDO imaging data. Both the CREDO data set and the source codes of our method can be downloaded in order to reproduce the results. We also make available for download the data set embedding and classification results.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Link to CREDO data set https://user.credo.science/user-interface/download/images/.
- 2.
Link to source codes and results https://github.com/browarsoftware/credo_dnn_rays_embedding/.
References
Bibrzycki, Ł, et al.: Towards a global cosmic ray sensor network: CREDO detectoras the first open-source mobile application enabling detection of penetrating radiation. Symmetry 12(11), 1802 (2020). https://doi.org/10.3390/sym121118
Borisyak, M., et al.: Muon trigger for mobile phones. J. Phys. Conf. Seri. 898, 032048. IOP Publishing (2017)
Gao, M., et al.: RGB-D-based object recognition using multimodal convolutional neural networks: a survey. IEEE Access 7, 43110–43136 (2019)
Hachaj, T., et al.: Recognition of cosmic ray images obtained from CMOS sensors used in mobile phones by approximation of uncertain class assignment with deep convolutional neural network. Sensors 21(6) (2021). https://doi.org/10.3390/s21061963
Homola, P., et al.: Cosmic-ray extremely distributed observatory. Symmetry 12(11)(2020). https://doi.org/10.3390/sym12111835
Jiao, L., et al.: A survey of deep learning-based object detection. IEEE Access 7, 128837–128868 (2019)
Krishna, S.T., Kalluri, H.K.: Deep learning and transfer learning approaches for image classification. Int. J. Recent Technol. Eng. (IJRTE) 7(5S4), 427–432 (2019)
Piekarczyk, M., et al.: CNN-based classifier as an offline trigger for the CREDO experiment. Sensors 21(14), 4804 (2021). https://doi.org/10.3390/s21144804
Vandenbroucke, J., et al.: Measurement of cosmic-ray muons with the distributed electronic cosmic-ray observatory, a network of smartphones. J. Instrum. 11(04), P04019 (2016)
Wang, S., et al.: Class-specific reconstruction transfer learning for visual recognition across domains. IEEE Trans. Image Process. 29, 2424–2438 (2019)
Whiteson, D., et al.: Searching for ultra-high energy cosmic rays with smartphones. Astropart. Phys. 79, 1–9 (2016)
Winter, M., et al.: Particle identification in camera image sensors using computer vision. Astropart. Phys. 104, 42–53 (2019). https://doi.org/10.1016/j.astropartphys.2018.08.009
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Hachaj, T., Piekarczyk, M., Bibrzycki, Ł. (2021). Deep Neural Network Architecture for Low-Dimensional Embedding and Classification of Cosmic Ray Images Obtained from CMOS Cameras. In: Mantoro, T., Lee, M., Ayu, M.A., Wong, K.W., Hidayanto, A.N. (eds) Neural Information Processing. ICONIP 2021. Communications in Computer and Information Science, vol 1516. Springer, Cham. https://doi.org/10.1007/978-3-030-92307-5_36
Download citation
DOI: https://doi.org/10.1007/978-3-030-92307-5_36
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-92306-8
Online ISBN: 978-3-030-92307-5
eBook Packages: Computer ScienceComputer Science (R0)