Cooperation of CUDA and Intel multi-core architecture in the independent component analysis algorithm for EEG data

• Autorzy: Gajos-Balińska Anna , Wójcik Grzegorz M. , Stpiczyński Przemysław

Identyfikatory

DOI

10.1515/bams-2020-0044

• Języki publikacji: EN

Abstrakty

EN

Objectives: The electroencephalographic signal is largely exposed to external disturbances. Therefore, an important element of its processing is its thorough cleaning. Methods: One of the common methods of signal improvement is the independent component analysis (ICA). However, it is a computationally expensive algorithm, hence methods are needed to decrease its execution time. One of the ICA algorithms (fastICA) and parallel computing on the CPU and GPU was used to reduce the algorithm execution time. Results: This paper presents the results of study on the implementation of fastICA, which uses some multi-core architecture and the GPU computation capabilities. Conclusions: The use of such a hybrid approach shortens the execution time of the algorithm.

Słowa kluczowe

EN

CUDA; electroencephalography; independent component analysis; parallel programming

• Wydawca: Uniwersytet Jagielloński - Collegium Medicum ; Index Copernicus Sp. z o.o.
• Czasopismo: Bio-Algorithms and Med-Systems
• Rocznik: 2020
• Tom: Vol. 16, no. 3
• Strony: art. no. 20200044
• Opis fizyczny: Bibliogr. 24 poz., rys., tab.

Twórcy

autor

Gajos-Balińska Anna

• Neuroinformatics and Biomedical Engineering, Institute of Computer Science, Maria Curie-Sklodowska University, Akademicka 9, 20-033 Lublin, Poland

autor

Wójcik Grzegorz M.

• Neuroinformatics and Biomedical Engineering, Institute of Computer Science, Maria Curie-Sklodowska University, Akademicka 9, 20-033 Lublin, Poland

autor

Stpiczyński Przemysław

• Software and Information Systems, Institute of Computer Science, Maria Curie-Sklodowska University, Lublin, Poland

Bibliografia

• 1. Tadeusiewicz R, Śmiałowska M, Hess G, Błaszczyk J, Kamiński WA, Lazarewicz MT, et al. Neurocybernetyka teoretyczna. Warsaw: Wydawnictwa Uniwersytetu Warszawskiego; 2009.
• 2. Dickter CL, Kieffaber PD. EEG methods for the psychological sciences. Los Angeles: SAGE Publications Ltd; 2014.
• 3. Albajes-Eizagirre A, Dubreuil Vall L, David IS, Riera A, Soria-Frisch A, Dunne S, et al. EEG/ERP analysis: methods and applications. CRC Press; 2014.
• 4. Kawala-Janik A, Bauer W, Al-Bakri A, Haddix C, Yuvaraj R, Cichon K, et al. Implementation of low-pass fractional filtering for the purpose of analysis of electroencephalographic signals. In: Conference on non-integer order calculus and its applications. Springer, Berlin; 2017. p. 63-73.
• 5. Brown GD, Yamada S, Sejnowski TJ. Independent component analysis at the neural cocktail party. Trends Neurosci 2001;24:54-63.
• 6. Delorme A, Sejnowski T, Makeig S. Enhanced detection of artifacts in EEG data using higher-order statistics and independent component analysis. Neuroimage 2007;34:1443-9.
• 7. Hyvarinen A. Fast and robust fixed-point algorithms for independent component analysis. IEEE Trans Neural Network 1999;10:626-34.
• 8. Ungureanu M, Bigan C, Strungaru R, Lazarescu V. Independent component analysis applied in biomedical signal processing. Meas Sci Rev 2004;4:18.
• 9. The MathWorks Inc. Documentation, Matlab; 2005.
• 10. NetStation acquisition technical manual. Documentation, EGI; 2011.
• 11. NetStation viewer technical manual. Documentation, EGI; 2011.
• 12. GeoSource 2.0 technical manual. Documentation, EGI; 2011.
• 13. Wojcik GM, Masiak J, Kawiak A, Kwasniewicz L, Schneider P, Polak N, et al. Mapping the human brain in frequency band analysis of brain cortex electroencephalographic activity for selected psychiatric disorders. Front Neuroinf 2018;12. https://doi.org/10.3389/fninf.2018.00073.
• 14. Wojcik GM, Masiak J, Kawiak A, Schneider P, Kwasniewicz L, Polak N, et al. New protocol for quantitative analysis of brain cortex electroencephalographic activity in patients with psychiatric disorders. Front Neuroinf 2018;12. https://doi.org/10.3389/fninf.2018.00027.
• 15. Gajos A, Wójcik GM. Independent component analysis of EEG data for EGI system. Bio Algorithm Med Syst 2016;12: 67-72.
• 16. Gajos-Balińska A, Wójcik GM, Stpiczyński P. High performance optimization of independent component analysis algorithm for EEG data. Lect Notes Comput Sci 2018;10777:495-504.
• 17. Gajos-Balińska A, Wójcik GM, Stpiczyński P. Concept of independent component analysis algorithm parallelisation. In: Proceedings of cracow grid workshop. Cracow: CGW’15; 2015.
• 18. Gajos-Balińska A, Wójcik GM, Stpiczyński P. Parallel independent component analysis algorithm - performance comparison for EEG signal. In: Proceedings of cracow grid workshop. Cracow: CGW’17; 2017.
• 19. Hyvärinen A, Oja E. Independent component analysis: algorithms and applications. Neural Network 2000;13:411-30.
• 20. it++ documentation. Available from: https://itpp.sourceforge. net/4.3.1 [Accessed 3 Aug 2020].
• 21. Rahman R. Intel Xeon Phi coprocessor architecture and tools: the guide for application developers. Berkely, CA, USA: Apress; 2013.
• 22. Szałkowski D, Stpiczyński P. Using distributed memory parallel computers and GPU clusters for multidimensional Monte Carlo integration. Concurrency Comput Pract Ex 2015;27:923-36.
• 23. Mikołajewska E, Mikołajewski D. The prospects of brain-computer interface applications in children. Open Med 2014;9:74-9.
• 24. Mikołajewska E, Mikołajewski D. Integrated IT environment for people with disabilities: a new concept. Open Med 2014;9: 177-82.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).