Research Article
BibTex RIS Cite

İğnecik Dalga Biçimlerinin İyileştirilmiş Seyrek Temsillerinin Temel Takip Yaklaşımı Kullanılarak Elde Edilmesi

Year 2021, Issue: 29, 46 - 51, 01.12.2021
https://doi.org/10.31590/ejosat.1009464

Abstract

Hücre dışı sinirsel kayıtlarda, kullanılan elektrodun yakınındaki sinir hücrelerinin oluşturduğu iğnecik dalga biçimlerinin morfolojilerine göre sıralanması gerekmektedir. Bu işleme iğnecik sıralaması adı verilir ve sinirsel kod çözme algoritmalarında kullanılan önemli bir ön koşuldur. Düşük Q-faktörlü dalgacık dönüşümleri, birbirine yakın sinir hücrelerinin aktiviteleri arasındaki ayırt edici örüntüleri tespit etmek için öznitelik çıkarıcılar olarak sıklıkla kullanılmaktadır. Fakat, farklı alt bantlardaki dalgacık katsayıları, kullanılan enstrümantasyon sistemi nedeniyle oluşan gürültü bileşenlerine ve yakındaki sinir hücrelerinin toplam aktivitesi olarak tanımlanan yerel alan potansiyellerine oldukça duyarlıdır. Bununla birlikte, azaltılmış gürültü aktivitesine sahip ğnecik dalga biçimlerinin geliştirilmiş seyrek temsilleri, ayarlanabilir Q faktörü dalgacık dönüşümü tabanlı katsayılara uygulanan temel takip yöntemi kullanılarak elde edilebilir. Ayarlanabilir Q faktörü dalgacık dönüşümünde, dalgacık filtrelerinin Q faktörü, kontrol edilebilir bir fazlalık ile ilgili sinyale göre ayarlanabilir. Önerilen çalışmada, dalgacık katsayılarına uygulanan temel takip yaklaşımı kullanılarak iğneciklerin iyileştirilmiş bir seyrek gösterimi elde edilmiştir. Daha sonra, ayrışmış alt bantların enerji değerleri, iğnecik şekillerindeki morfolojik farklılıkları ayırt edebilen özellikler olarak kullanılmıştır. Son olarak, elde edilen öznitelikler, geliştirilmiş seyreklik ayrıştırmasının etkisini nesnel olarak ölçmek için tarafsız bir çapraz doğrulama şemasında k-en yakın komşular ve karar ağaçları öğrenme modellerine beslenmiştir. Niteliksel ve niceliksel sonuçlar, iyileştirilmiş seyreklik tabanlı enerji özelliklerinin, doğruluk metriği açısından geleneksel düşük Q faktörüne dayalı dalgacık ayrıştırmasından daha üstün olduğunu göstermektedir.

References

  • Rizk, M., Bossetti, C. A., Jochum, T. A., Callender, S. H., Nicolelis, M. A., Turner, D. A., & Wolf, P. D. (2009). A fully implantable 96-channel neural data acquisition system. Journal of neural engineering, 6(2), 026002.
  • Lewicki, M. S. (1998). A review of methods for spike sorting: the detection and classification of neural action potentials. Network: Computation in Neural Systems, 9(4), R53.
  • Buzsáki, G. (2004). Large-scale recording of neuronal ensembles. Nature neuroscience, 7(5), 446-451.
  • Chah, E., Hok, V., Della-Chiesa, A., Miller, J. J. H., O'Mara, S. M., & Reilly, R. B. (2011). Automated spike sorting algorithm based on Laplacian eigenmaps and k-means clustering. Journal of neural engineering, 8(1), 016006.
  • Abeles, M., & Goldstein, M. H. (1977). Multispike train analysis. Proceedings of the IEEE, 65(5), 762-773.
  • Harris, K. D., Henze, D. A., Csicsvari, J., Hirase, H., & Buzsaki, G. (2000). Accuracy of tetrode spike separation as determined by simultaneous intracellular and extracellular measurements. Journal of neurophysiology, 84(1), 401-414.
  • Thakur, P. H., Lu, H., Hsiao, S. S., & Johnson, K. O. (2007). Automated optimal detection and classification of neural action potentials in extra-cellular recordings. Journal of Neuroscience Methods, 162(1-2), 364-376.
  • Hulata, E., Segev, R., & Ben-Jacob, E. (2002). A method for spike sorting and detection based on wavelet packets and Shannon's mutual information. Journal of neuroscience methods, 117(1), 1-12.
  • Quiroga, R. Q., Nadasdy, Z., & Ben-Shaul, Y. (2004). Unsupervised spike detection and sorting with wavelets and superparamagnetic clustering. Neural computation, 16(8), 1661-1687.
  • Takahashi, S., Anzai, Y., & Sakurai, Y. (2003). A new approach to spike sorting for multi-neuronal activities recorded with a tetrode—how ICA can be practical. Neuroscience research, 46(3), 265-272.
  • Geng, X., Hu, G., & Tian, X. (2010). Neural spike sorting using mathematical morphology, multiwavelets transform and hierarchical clustering. Neurocomputing, 73(4-6), 707-715.
  • Geng, X., & Hu, G. (2012). Unsupervised feature selection by kernel density estimation in wavelet-based spike sorting. Biomedical Signal Processing and Control, 7(2), 112-117.
  • Selesnick, I. W. (2011). Wavelet transform with tunable Q-factor. IEEE transactions on signal processing, 59(8), 3560-3575.
  • Ulukaya, S., Serbes, G., & Kahya, Y. P. (2016, August). Resonance based respiratory sound decomposition aiming at localization of crackles in noisy measurements. In 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (pp. 3688-3691). IEEE.
  • Serbes, G., & Aydin, N. (2017, May). Resonance based pre-processing method for eliminating artifacts in Doppler ultrasound signals. In 2017 25th Signal Processing and Communications Applications Conference (SIU) (pp. 1-4). IEEE.
  • Serbes, G., Aydin, N., & Gulcur, H. O. (2013, July). Directional dual-tree complex wavelet packet transform. In 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (pp. 3046-3049). IEEE.
  • Serbes, G., & Aydin, N. (2012, January). Embolic Doppler ultrasound signal detection using modified dual tree complex wavelet transform. In Proceedings of 2012 IEEE-EMBS International Conference on Biomedical and Health Informatics (pp. 945-947). IEEE.
  • Serbes, G., Sakar, C. O., Kahya, Y. P., & Aydin, N. (2011, September). Effect of different window and wavelet types on the performance of a novel crackle detection algorithm. In International Conference on Hybrid Information Technology (pp. 575-581). Springer, Berlin, Heidelberg.
  • Chen, S. S., Donoho, D. L., & Saunders, M. A. (2001). Atomic decomposition by basis pursuit. SIAM review, 43(1), 129-159.

Enhanced Sparse Representations of Spike Waveforms Obtained by using the Basis Pursuit Approach

Year 2021, Issue: 29, 46 - 51, 01.12.2021
https://doi.org/10.31590/ejosat.1009464

Abstract

In the extracellular neural recordings, the spike waveforms formed by the neurons nearby the recording electrode must be sorted according to their morphology. This process is called as spike sorting and it is an important prerequisite in neural decoding algorithms. Low Q-factor wavelet transforms are frequently being used as feature extractors to detect the discriminative patterns between adjacent neurons’ activity. However, the wavelet coefficients are highly sensitive to noise that may occur due to the employed instrumentation system and the local field potentials defined as the total activity of nearby neurons. However, enhanced sparse representations of the spike wave forms, having reduced noise activity, can be attained by using the basis pursuit method that is applied to the tunable Q-factor wavelet transform coefficients. In the tunable Q-factor wavelet transform, the Q-factor of the wavelet filters can be tuned according to the signal of interest with a controllable redundancy. In the proposed study, enhanced sparse representations of the spike waveforms were obtained by using the basis pursuit approach. Later, the energy values of the decomposed subbands were employed as features that can discriminate morphological differences in spike shapes. Finally, the obtained features were fed to k-nearest neighbors and decision trees learning models in an unbiased cross-validation scheme to objectively measure the effect of the enhanced sparsity decomposition. The qualitative and quantitative results show that the enhanced sparsity-based energy features are superior to the traditional low Q-factor based wavelet decomposition in terms of the accuracy metric.

References

  • Rizk, M., Bossetti, C. A., Jochum, T. A., Callender, S. H., Nicolelis, M. A., Turner, D. A., & Wolf, P. D. (2009). A fully implantable 96-channel neural data acquisition system. Journal of neural engineering, 6(2), 026002.
  • Lewicki, M. S. (1998). A review of methods for spike sorting: the detection and classification of neural action potentials. Network: Computation in Neural Systems, 9(4), R53.
  • Buzsáki, G. (2004). Large-scale recording of neuronal ensembles. Nature neuroscience, 7(5), 446-451.
  • Chah, E., Hok, V., Della-Chiesa, A., Miller, J. J. H., O'Mara, S. M., & Reilly, R. B. (2011). Automated spike sorting algorithm based on Laplacian eigenmaps and k-means clustering. Journal of neural engineering, 8(1), 016006.
  • Abeles, M., & Goldstein, M. H. (1977). Multispike train analysis. Proceedings of the IEEE, 65(5), 762-773.
  • Harris, K. D., Henze, D. A., Csicsvari, J., Hirase, H., & Buzsaki, G. (2000). Accuracy of tetrode spike separation as determined by simultaneous intracellular and extracellular measurements. Journal of neurophysiology, 84(1), 401-414.
  • Thakur, P. H., Lu, H., Hsiao, S. S., & Johnson, K. O. (2007). Automated optimal detection and classification of neural action potentials in extra-cellular recordings. Journal of Neuroscience Methods, 162(1-2), 364-376.
  • Hulata, E., Segev, R., & Ben-Jacob, E. (2002). A method for spike sorting and detection based on wavelet packets and Shannon's mutual information. Journal of neuroscience methods, 117(1), 1-12.
  • Quiroga, R. Q., Nadasdy, Z., & Ben-Shaul, Y. (2004). Unsupervised spike detection and sorting with wavelets and superparamagnetic clustering. Neural computation, 16(8), 1661-1687.
  • Takahashi, S., Anzai, Y., & Sakurai, Y. (2003). A new approach to spike sorting for multi-neuronal activities recorded with a tetrode—how ICA can be practical. Neuroscience research, 46(3), 265-272.
  • Geng, X., Hu, G., & Tian, X. (2010). Neural spike sorting using mathematical morphology, multiwavelets transform and hierarchical clustering. Neurocomputing, 73(4-6), 707-715.
  • Geng, X., & Hu, G. (2012). Unsupervised feature selection by kernel density estimation in wavelet-based spike sorting. Biomedical Signal Processing and Control, 7(2), 112-117.
  • Selesnick, I. W. (2011). Wavelet transform with tunable Q-factor. IEEE transactions on signal processing, 59(8), 3560-3575.
  • Ulukaya, S., Serbes, G., & Kahya, Y. P. (2016, August). Resonance based respiratory sound decomposition aiming at localization of crackles in noisy measurements. In 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (pp. 3688-3691). IEEE.
  • Serbes, G., & Aydin, N. (2017, May). Resonance based pre-processing method for eliminating artifacts in Doppler ultrasound signals. In 2017 25th Signal Processing and Communications Applications Conference (SIU) (pp. 1-4). IEEE.
  • Serbes, G., Aydin, N., & Gulcur, H. O. (2013, July). Directional dual-tree complex wavelet packet transform. In 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (pp. 3046-3049). IEEE.
  • Serbes, G., & Aydin, N. (2012, January). Embolic Doppler ultrasound signal detection using modified dual tree complex wavelet transform. In Proceedings of 2012 IEEE-EMBS International Conference on Biomedical and Health Informatics (pp. 945-947). IEEE.
  • Serbes, G., Sakar, C. O., Kahya, Y. P., & Aydin, N. (2011, September). Effect of different window and wavelet types on the performance of a novel crackle detection algorithm. In International Conference on Hybrid Information Technology (pp. 575-581). Springer, Berlin, Heidelberg.
  • Chen, S. S., Donoho, D. L., & Saunders, M. A. (2001). Atomic decomposition by basis pursuit. SIAM review, 43(1), 129-159.
There are 19 citations in total.

Details

Primary Language English
Subjects Engineering
Journal Section Articles
Authors

Görkem Serbes 0000-0003-4591-7368

Early Pub Date December 15, 2021
Publication Date December 1, 2021
Published in Issue Year 2021 Issue: 29

Cite

APA Serbes, G. (2021). Enhanced Sparse Representations of Spike Waveforms Obtained by using the Basis Pursuit Approach. Avrupa Bilim Ve Teknoloji Dergisi(29), 46-51. https://doi.org/10.31590/ejosat.1009464