Detection of potentially anomalous cosmic particle tracks acquired with CMOS sensors: Validation of rough k-means clustering with PCA feature extraction

• Autorzy: Hachaj Tomasz , Piekarczyk Marcin , Wąs Jarosław

Identyfikatory

DOI

10.61822/amcs-2025-0001

• Języki publikacji: EN

Abstrakty

EN

We present a method capable of detecting potentially anomalous cosmic particle tracks acquired with complementary metal-oxide-semiconductor (CMOS) sensors. We apply a principal components analysis-based feature extraction method and rough k-means clustering for outlier detection. We evaluated our approach on more than 10⁴ images acquired by the Cosmic Ray Extremely Distributed Observatory (CREDO). The method presented in this work proved to be an effective solution. The analysis of the behavior of the rough k-means clustering-based algorithm presented here and the method of selecting its parameters showed that the algorithm performs as expected and demonstrates efficiency, stability, and repeatability of results for the test data set. The results included in this work are very relevant to the international CREDO project and the broader problem of anomaly analysis in image data sets. We plan to deploy the presented methodology in the image processing pipeline of the large data set we are working on in the CREDO project. The results can be reproduced using our source code, which is published in an open repository.

Słowa kluczowe

EN

cosmic ray particle; rough set; rough K-means; anomalies detection; principal components analysis

PL

zbiór przybliżony; wykrywanie anomalii; analiza składowych głównych

• Wydawca: Oficyna Wydawnicza Uniwersytetu Zielonogórskiego
• Czasopismo: International Journal of Applied Mathematics and Computer Science
• Rocznik: 2025
• Tom: Vol. 35, no. 1
• Strony: 7--18
• Opis fizyczny: Bibliogr. 37 poz., rys., tab.

Twórcy

autor

Hachaj Tomasz

• Faculty of Electrical Engineering, Automatics, Computer Science and Biomedical Engineering, AGH University of Krakow, Al. Mickiewicza 30, 30-059 Krakow, Poland

autor

Piekarczyk Marcin

• Faculty of Electrical Engineering, Automatics, Computer Science and Biomedical Engineering, AGH University of Krakow, Al. Mickiewicza 30, 30-059 Krakow, Poland

autor

Wąs Jarosław

• Faculty of Electrical Engineering, Automatics, Computer Science and Biomedical Engineering, AGH University of Krakow, Al. Mickiewicza 30, 30-059 Krakow, Poland

Bibliografia

• [1] Afridi, M.K., Azam, N., Yao, J. and Alanazi, E. (2018). A three-way clustering approach for handling missing data using GTRS, International Journal of Approximate Reasoning 98: 11-24.
• [2] Albin, E.K. and Whiteson, D. (2023). Feasibility of correlated extensive air shower detection with a distributed cosmic-ray network, Astrophysical Journal 954(1): 106.
• [3] Bar, O., Bibrzycki, Ł., Niedźwiecki, M., Piekarczyk, M., Rzecki, K., Sośnicki, T., Stuglik, S., Frontczak, M., Homola, P., Alvarez-Castillo, D.E., Andersen, T. and Tursunov, A. (2021). Zernike moment based classification of cosmic ray candidate hits from CMOS sensors, Sensors 21(22): 7718.
• [4] Bibrzycki, Ł., Burakowski, D., Homola, P., Piekarczyk, M., Niedźwiecki, M., Rzecki, K., Stuglik, S., Tursunov, A., Hnatyk, B., Castillo, D.E.A., Smelcerz, K., Stasielak, J., Duffy, A. R., Chevalier, L., Ali, E., Lakerink, L., Poole, G. B., Wibig, T. and Zamora-Saa, J. (2020). Towards a global cosmic ray sensor network: Credo detector as the first open-source mobile application enabling detection of penetrating radiation, Symmetry 12(11): 1802.
• [5] Crispim Romão, M., Castro, N.F. and Pedro, R. (2021). Finding new physics without learning about it: Anomaly detection as a tool for searches at colliders, European Physical Journal C 81(1): 27.
• [6] Fan, Z., Li, C., Chen, Y., Wei, J., Loprencipe, G., Chen, X. and Di Mascio, P. (2020). Automatic crack detection on road pavements using encoder-decoder architecture, Materials 13(13): 2960.
• [7] Forgey, E. (1965). Cluster analysis of multivariate data: Efficiency vs. interpretability of classification, Biometrics 21(3): 768-769.
• [8] Hachaj, T., Koptyra, K. and Ogiela, M.R. (2021). Eigenfaces-based steganography, Entropy 23(3): 273.
• [9] Hachaj, T. and Piekarczyk, M. (2023). The practice of detecting potential cosmic rays using CMOS cameras: Hardware and algorithms, Sensors 23(10): 4858.
• [10] Hachaj, T., Piekarczyk, M. and Wąs, J. (2023). Searching of potentially anomalous signals in cosmic-ray particle tracks images using rough k-means clustering combined with eigendecomposition-derived embedding, in A. Campagner et al. (Eds), Rough Sets, Springer Nature Switzerland, Cham, pp. 431-445.
• [11] Homola, P., Beznosko, D., Bhatta, G., Bibrzycki, Ł., Borczyńska, M., Bratek, Ł., Budnev, N., Burakowski, D., Alvarez-Castillo, D.E., Cheminant, K.A., Ćwikła, A., Dam-o, P., Dhital, N., Duffy, A.R., Głownia, P., Gorzkiewicz, K., Góra, D., Gupta, A.C., Hlávková, Z., Homola, M., Jałocha, J., Kamiński, R., Karbowiak, M., Kasztelan, M., Kierepko, R., Knap, M., Kovács, P., Kuliński, S., Łozowski, B., Magryś, M., Medvedev, M.V., Mędrala, J., Mietelski, J.W., Miszczyk, J., Mozgova, A., Napolitano, A., Nazari, V., Ng, Y.J., Niedźwiecki, M., Oancea, C., Ogan, B., Opiła, G., Oziomek, K., Pawlik, M., Piekarczyk, M., Poncyljusz, B., Pryga, J., Rosas, M., Rzecki, K., Zamora-Saa, J., Smelcerz, K., Smolek, K., Stanek, W., Stasielak, J., Stuglik, S., Sulma, J., Sushchov, O., Svanidze, M., Tam, K.M., Tursunov, A., Vaquero, J.M., Wibig, T., and Woźniak, K.W. (2020). Cosmic-ray extremely distributed observatory, Symmetry 12(11): 1835.
• [12] Javan, H. (2002). Characterizing sensitive CMOS radiation detector, Proceedings of IEEE SoutheastCon 2002, Columbia, USA, pp. 28-32.
• [13] Jewell, J.T., Khazaie, V.R. and Mohsenzadeh, Y. (2022). One-class learned encoder-decoder network with adversarial context masking for novelty detection, Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, Waikoloa, USA, pp. 3591-3601.
• [14] Johary, Y.H., Trapp, J., Aamry, A., Aamri, H., Tamam, N. and Sulieman, A. (2021). The suitability of smartphone camera sensors for detecting radiation, Scientific Reports 11(1): 12653.
• [15] Karbowiak, M., Wibig, T., Alvarez Castillo, D., Beznosko, D., Duffy, A.R., Góra, D., Homola, P., Kasztelan, M. and Niedźwiecki, M. (2021). Determination of zenith angle dependence of incoherent cosmic ray muon flux using smartphones of the credo project, Applied Sciences 11(3): 1185.
• [16] Kuusela, M., Vatanen, T., Malmi, E., Raiko, T., Aaltonen, T. and Nagai, Y. (2012). Semi-supervised anomaly detection - Towards model-independent searches of new physics, Journal of Physics: Conference Series 368: 012032.
• [17] Lingras, P. and Peters, G. (2012). Applying rough set concepts to clustering, in G. Peters et al. (Eds), Rough Sets: Selected Methods and Applications in Management and Engineering, Springer, Berlin/Heidelberg, pp. 23-37.
• [18] Lloyd, S. (1982). Least squares quantization in PCM, IEEE Transactions on Information Theory 28(2): 129-137.
• [19] Pang, G., Shen, C., Cao, L. and Hengel, A.V.D. (2021). Deep learning for anomaly detection: A review, ACM Computing Surveys 54(2): 1-38.
• [20] Pawlak, Z. (1982). Rough sets, International Journal of Computer & Information Sciences 11: 341-356.
• [21] Peters, J.F., Skowron, A., Suraj, Z., Rzasa, W. and Borkowski, M. (2002). Clustering: A rough set approach to constructing information granules, Proceedings of the 6th International Conference on Soft Computing and Distributed Processing, SCDP, Rzeszów, Poland, pp. 57-61.
• [22] Piekarczyk, M., Bar, O., Bibrzycki, Ł., Niedźwiecki, M., Rzecki, K., Stuglik, S., Andersen, T., Budnev, N.M., Alvarez-Castillo, D.E., Cheminant, K.A., Góra, D., Gupta, A.C., Hnatyk, B., Homola, P., Kamiński, R., Kasztelan, M., Knap, M., Kovács, P., Łozowski, B., Miszczyk, J., Mozgova, A., Nazari, V., Pawlik, M., Rosas, M., Sushchov, O., Smelcerz, K., Smolek, K., Stasielak, J., Wibig, T., Woźniak, K.W. and Zamora-Saa, J. (2021). CNN-based classifier as an offline trigger for the credo experiment, Sensors 21(14): 4804.
• [23] Pięta, P. and Szmuc, T. (2021). Applications of rough sets in big data analysis: An overview, International Journal of Applied Mathematics and Computer Science 31(4): 659-683, DOI: 10.34768/amcs-2021-0046.
• [24] Riza, L. S., Janusz, A., Bergmeir, C., Cornelis, C., Herrera, F., Ślęzak, D. and Benítez, J.M. (2014). Implementing algorithms of rough set theory and fuzzy rough set theory in the R package “RoughSets”, Information Sciences 287: 68-89.
• [25] Skowron, A. and Dutta, S. (2018). Rough sets: Past, present, and future, Natural Computing 17: 855-876.
• [26] Skowron, A. and Ślęzak, D. (2022). Rough sets turn 40: From information systems to intelligent systems, 17th Conference on Computer Science and Intelligence Systems (Fed-CSIS), Sofia, Bulgaria, pp. 23-34.
• [27] Stein, G., Seljak, U. and Dai, B. (2020). Unsupervised in-distribution anomaly detection of new physics through conditional density estimation, arXiv: 2012.11638.
• [28] Turk, M. and Pentland, A. (1991). Face recognition using eigenfaces, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Maui, USA, pp. 586-591.
• [29] Vandenbroucke, J., BenZvi, S., Bravo, S., Jensen, K., Karn, P., Meehan, M., Peacock, J., Plewa, M., Ruggles, T., Santander, M., Schultz, D., Simons, A.L. and Tosi, D. (2016). Measurement of cosmic-ray muons with the distributed electronic cosmic-ray observatory, a network of smartphones, Journal of Instrumentation 11(04): P04019.
• [30] Vandenbroucke, J., Bravo, S., Karn, P., Meehan, M., Plewa, M., Ruggles, T., Schultz, D., Peacock, J. and Simons, A.L. (2015). Detecting particles with cell phones: The distributed electronic cosmic-ray observatory, arXiv: 1510.07665.
• [31] Wang, P., Yang, X., Ding, W., Zhan, J. and Yao, Y. (2024). Three-way clustering: Foundations, survey and challenges, Applied Soft Computing 151: 111131.
• [32] Wang, P. and Yao, Y. (2018). CE3: A three-way clustering method based on mathematical morphology, Knowledge-Based Systems 155(1): 54-65.
• [33] Wei, R. and Mahmood, A. (2021). Recent advances in variational autoencoders with representation learning for biomedical informatics: A survey, IEEE Access 9: 4939-4956.
• [34] Whiteson, D.,Mulhearn, M., Shimmin, C., Cranmer, K., Brodie, K. and Burns, D. (2016). Searching for ultra-high energy cosmic rays with smartphones, Astroparticle Physics 79: 1-9.
• [35] Yao, Y. (2010). Three-way decisions with probabilistic rough sets, Information Sciences 180(3): 341-353.
• [36] Yu, H. (2017). A framework of three-way cluster analysis, in L. Polkowski et al. (Eds), Rough Sets: International Joint Conference, IJCRS 2017, Springer, Cham, pp. 300-312.
• [37] Yu, H. (2018). Three-way decisions and three-way clustering, in H.S. Nguyen et al. (Eds), Rough Sets: International Joint Conference, IJCRS 2018, Springer, Cham, pp. 13-28.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).