Research Article
BibTex RIS Cite

Bağımsız Bileşenler Analizinde Örneklem Frekansının Etkisi ve Tekrarlanabilirlik

Year 2023, Volume: 10 Issue: 2, 377 - 386, 31.08.2023
https://doi.org/10.21020/husbfd.1222083

Abstract

Amaç: BBA (Bağımsız Bileşenler Analizi), derin öğrenme infomax algoritmasını kullanan doğrusal veri ayrıştırma yöntemlerinden biridir. BBA, EEG verilerini yersel ve zamansal özellikleri üzerinden ayrıştırmakta, EEG verileri ve OIP açısından gürültü olarak kabul edilen sinyallerin ayrıştırılmasında sıklıkla kullanılmaktadır.
Gereç ve Yöntem: Lateralize ışık uyaranının kullanıldığı bir deneme sırasında kaydedilen EEG verileri kullanılarak, BBA bileşenlerinin hesaplanmasında örneklem frekansının etkisi incelenmiş, tekrarlanabilirliği ele alınmıştır. EEG örneklem frekansının 250Hz olduğu veri seti için bir, 500Hz’lik EEG veri seti için ise üç kez BBA bileşenleri hesaplanmıştır.
Bulgular: 250Hz ve 500Hz’lik örneklem frekanslarının kullanıldığı EEG verilerine ait BBA bileşenlerinin, topografik ve spektral gösterim ve zamansal değişim açısından farklı olduğu görülmüştür. 500Hz’lik örneklem frekansı ile elde edilen BBA bileşenleri arasında topografi ve polarite açısından farklılıklar gözlendi.
Sonuç: BBA uygulanırken EEG verilerindeki gürültü, kullanılan örneklem frekansı, öğrenme sürecinin durdurulmasında kullanılan değişkenin dikkate alınması büyük önem taşımaktadır. BBA ile elde edilen bileşenler incelenirken tekrarlanabilirliği mutlaka test edilmelidir.

References

  • Barbati, G., Porcaro, C., Zappasodi, F., Rossini, P. M., & Tecchio, F. (2004). Optimization of an independent component analysis approach for artifact identification and removal in magnetoencephalographic signals. Clin Neurophysiol, 115(5), 1220-1232. doi:10.1016/j.clinph.2003.12.015
  • Bell, A. J., & Sejnowski, T. J. (1995). An information-maximization approach to blind separation and blind deconvolution. Neural Comput, 7(6), 1129-1159. doi:10.1162/neco.1995.7.6.1129
  • Delorme, A., & Makeig, S. (2004). EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis. J Neurosci Methods, 134(1), 9-21. doi:10.1016/j.jneumeth.2003.10.009
  • Deprez, H., Gransier, R., Hofmann, M., van Wieringen, A., Wouters, J., & Moonen, M. (2018). Independent component analysis for cochlear implant artifacts attenuation from electrically evoked auditory steady-state response measurements. J Neural Eng, 15(1), 016006. doi:10.1088/1741-2552/aa87ce
  • EEGLAB_WIKI. (2022a). ICA Background. Retrieved from https://eeglab.org/tutorials/ConceptsGuide/ICA_background.html
  • EEGLAB_WIKI. (2022b). Independent Component Analysis for artifact removal Retrieved from https://eeglab.org/tutorials/06_RejectArtifacts/RunICA.html
  • Erbil, N., & Yagcioglu, S. (2016). Connectivity measures in the Poffenberger paradigm indicate hemispheric asymmetries. Funct Neurol, 31(4), 249-256. doi:10.11138/fneur/2016.31.4.249
  • Iriarte, J., Urrestarazu, E., Valencia, M., Alegre, M., Malanda, A., Viteri, C., & Artieda, J. (2003). Independent component analysis as a tool to eliminate artifacts in EEG: a quantitative study. J Clin Neurophysiol, 20(4), 249-257. doi:10.1097/00004691-200307000-00004
  • James, C. J., & Gibson, O. J. (2003). Temporally constrained ICA: an application to artifact rejection in electromagnetic brain signal analysis. IEEE Trans Biomed Eng, 50(9), 1108-1116. doi:10.1109/tbme.2003.816076
  • Joyce, C. A., Gorodnitsky, I. F., & Kutas, M. (2004). Automatic removal of eye movement and blink artifacts from EEG data using blind component separation. Psychophysiology, 41(2), 313-325. doi:10.1111/j.1469-8986.2003.00141.x
  • Jung, T. P., Makeig, S., McKeown, M. J., Bell, A. J., Lee, T. W., & Sejnowski, T. J. (2001). Imaging Brain Dynamics Using Independent Component Analysis. Proc IEEE Inst Electr Electron Eng, 89(7), 1107-1122. doi:10.1109/5.939827
  • Kim, K., Punte, A. K., Mertens, G., Van de Heyning, P., Park, K. J., Choi, H., . . . Song, J. J. (2015). A novel method for device-related electroencephalography artifact suppression to explore cochlear implant-related cortical changes in single-sided deafness. J Neurosci Methods, 255, 22-28. doi:10.1016/j.jneumeth.2015.07.020
  • Lee, T.-W., Girolami, M., Bell, A. J., & Sejnowski, T. J. (2000). A unifying information-theoretic framework for independent component analysis. Computers & Mathematics with Applications, 39(11), 1-21. doi:https://doi.org/10.1016/S0898-1221(00)00101-2
  • Makeig, S., Debener, S., Onton, J., & Delorme, A. (2004). Mining event-related brain dynamics. Trends Cogn Sci, 8(5), 204-210. doi:10.1016/j.tics.2004.03.008
  • Makeig, S., Jung, T. P., Bell, A. J., Ghahremani, D., & Sejnowski, T. J. (1997). Blind separation of auditory event-related brain responses into independent components. Proc Natl Acad Sci U S A, 94(20), 10979-10984. doi:10.1073/pnas.94.20.10979
  • Makeig, S., Westerfield, M., Jung, T. P., Enghoff, S., Townsend, J., Courchesne, E., & Sejnowski, T. J. (2002). Dynamic brain sources of visual evoked responses. Science, 295(5555), 690-694. doi:10.1126/science.1066168
  • Miller, S., & Zhang, Y. (2014). Validation of the cochlear implant artifact correction tool for auditory electrophysiology. Neurosci Lett, 577, 51-55. doi:10.1016/j.neulet.2014.06.007
  • Tran, Y., Craig, A., Boord, P., & Craig, D. (2004). Using independent component analysis to remove artifact from electroencephalographic measured during stuttered speech. Med Biol Eng Comput, 42(5), 627-633. doi:10.1007/bf02347544
  • Urrestarazu, E., Iriarte, J., Alegre, M., Valencia, M., Viteri, C., & Artieda, J. (2004). Independent component analysis removing artifacts in ictal recordings. Epilepsia, 45(9), 1071-1078. doi:10.1111/j.0013-9580.2004.12104.x
  • Zhukov, L., Weinstein, D., & Johnson, C. (2000). Independent component analysis for EEG source localization. IEEE Eng Med Biol Mag, 19(3), 87-96. doi:10.1109/51.844386

The Effect of Sampling Frequency and Repeatability in Independent Component Analysis

Year 2023, Volume: 10 Issue: 2, 377 - 386, 31.08.2023
https://doi.org/10.21020/husbfd.1222083

Abstract

Objectives: ICA (Independent Components Analysis) is one of the linear data decomposing methods using infomax algorithm. ICA decomposes EEG data based on spatial and temporal characteristics and is frequently used to removal of artifacts from EEG and ERP.
Materials and Methods: By using the EEG data recorded during an experiment using lateralized light stimulus, the effect of sampling frequency and reproducibility of ICA components was examined. ICA components were calculated once for the EEG data set with sampled with of 250Hz and three times for the one sampled with 500Hz.
Results: It has been observed that the ICA components of the EEG data sampled with 250Hz and 500Hz are different in terms of topographic and spectral representations and temporal variation. Differences in topography and polarity were observed between ICA components obtained with a sampling frequency of 500Hz.
Conclusion: While applying ICA, it is important to consider the presence of artifacts in EEG data, sampling frequency, and the variable used to stop the learning process. While examining the components obtained with ICA, its reproducibility should be tested.

References

  • Barbati, G., Porcaro, C., Zappasodi, F., Rossini, P. M., & Tecchio, F. (2004). Optimization of an independent component analysis approach for artifact identification and removal in magnetoencephalographic signals. Clin Neurophysiol, 115(5), 1220-1232. doi:10.1016/j.clinph.2003.12.015
  • Bell, A. J., & Sejnowski, T. J. (1995). An information-maximization approach to blind separation and blind deconvolution. Neural Comput, 7(6), 1129-1159. doi:10.1162/neco.1995.7.6.1129
  • Delorme, A., & Makeig, S. (2004). EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis. J Neurosci Methods, 134(1), 9-21. doi:10.1016/j.jneumeth.2003.10.009
  • Deprez, H., Gransier, R., Hofmann, M., van Wieringen, A., Wouters, J., & Moonen, M. (2018). Independent component analysis for cochlear implant artifacts attenuation from electrically evoked auditory steady-state response measurements. J Neural Eng, 15(1), 016006. doi:10.1088/1741-2552/aa87ce
  • EEGLAB_WIKI. (2022a). ICA Background. Retrieved from https://eeglab.org/tutorials/ConceptsGuide/ICA_background.html
  • EEGLAB_WIKI. (2022b). Independent Component Analysis for artifact removal Retrieved from https://eeglab.org/tutorials/06_RejectArtifacts/RunICA.html
  • Erbil, N., & Yagcioglu, S. (2016). Connectivity measures in the Poffenberger paradigm indicate hemispheric asymmetries. Funct Neurol, 31(4), 249-256. doi:10.11138/fneur/2016.31.4.249
  • Iriarte, J., Urrestarazu, E., Valencia, M., Alegre, M., Malanda, A., Viteri, C., & Artieda, J. (2003). Independent component analysis as a tool to eliminate artifacts in EEG: a quantitative study. J Clin Neurophysiol, 20(4), 249-257. doi:10.1097/00004691-200307000-00004
  • James, C. J., & Gibson, O. J. (2003). Temporally constrained ICA: an application to artifact rejection in electromagnetic brain signal analysis. IEEE Trans Biomed Eng, 50(9), 1108-1116. doi:10.1109/tbme.2003.816076
  • Joyce, C. A., Gorodnitsky, I. F., & Kutas, M. (2004). Automatic removal of eye movement and blink artifacts from EEG data using blind component separation. Psychophysiology, 41(2), 313-325. doi:10.1111/j.1469-8986.2003.00141.x
  • Jung, T. P., Makeig, S., McKeown, M. J., Bell, A. J., Lee, T. W., & Sejnowski, T. J. (2001). Imaging Brain Dynamics Using Independent Component Analysis. Proc IEEE Inst Electr Electron Eng, 89(7), 1107-1122. doi:10.1109/5.939827
  • Kim, K., Punte, A. K., Mertens, G., Van de Heyning, P., Park, K. J., Choi, H., . . . Song, J. J. (2015). A novel method for device-related electroencephalography artifact suppression to explore cochlear implant-related cortical changes in single-sided deafness. J Neurosci Methods, 255, 22-28. doi:10.1016/j.jneumeth.2015.07.020
  • Lee, T.-W., Girolami, M., Bell, A. J., & Sejnowski, T. J. (2000). A unifying information-theoretic framework for independent component analysis. Computers & Mathematics with Applications, 39(11), 1-21. doi:https://doi.org/10.1016/S0898-1221(00)00101-2
  • Makeig, S., Debener, S., Onton, J., & Delorme, A. (2004). Mining event-related brain dynamics. Trends Cogn Sci, 8(5), 204-210. doi:10.1016/j.tics.2004.03.008
  • Makeig, S., Jung, T. P., Bell, A. J., Ghahremani, D., & Sejnowski, T. J. (1997). Blind separation of auditory event-related brain responses into independent components. Proc Natl Acad Sci U S A, 94(20), 10979-10984. doi:10.1073/pnas.94.20.10979
  • Makeig, S., Westerfield, M., Jung, T. P., Enghoff, S., Townsend, J., Courchesne, E., & Sejnowski, T. J. (2002). Dynamic brain sources of visual evoked responses. Science, 295(5555), 690-694. doi:10.1126/science.1066168
  • Miller, S., & Zhang, Y. (2014). Validation of the cochlear implant artifact correction tool for auditory electrophysiology. Neurosci Lett, 577, 51-55. doi:10.1016/j.neulet.2014.06.007
  • Tran, Y., Craig, A., Boord, P., & Craig, D. (2004). Using independent component analysis to remove artifact from electroencephalographic measured during stuttered speech. Med Biol Eng Comput, 42(5), 627-633. doi:10.1007/bf02347544
  • Urrestarazu, E., Iriarte, J., Alegre, M., Valencia, M., Viteri, C., & Artieda, J. (2004). Independent component analysis removing artifacts in ictal recordings. Epilepsia, 45(9), 1071-1078. doi:10.1111/j.0013-9580.2004.12104.x
  • Zhukov, L., Weinstein, D., & Johnson, C. (2000). Independent component analysis for EEG source localization. IEEE Eng Med Biol Mag, 19(3), 87-96. doi:10.1109/51.844386
There are 20 citations in total.

Details

Primary Language Turkish
Subjects Health Care Administration
Journal Section Articles
Authors

Nurhan Erbil 0000-0003-1478-5905

Early Pub Date July 18, 2023
Publication Date August 31, 2023
Submission Date December 20, 2022
Published in Issue Year 2023 Volume: 10 Issue: 2

Cite

APA Erbil, N. (2023). Bağımsız Bileşenler Analizinde Örneklem Frekansının Etkisi ve Tekrarlanabilirlik. Hacettepe University Faculty of Health Sciences Journal, 10(2), 377-386. https://doi.org/10.21020/husbfd.1222083