Araştırma Makalesi
BibTex RIS Kaynak Göster

DHGUP TABANLI BEYİN-BİLGİSAYAR ARAYÜZLERİ İÇİN ALT UZAY KEŞFİ

Yıl 2023, , 86 - 97, 15.03.2023
https://doi.org/10.17780/ksujes.1175402

Öz

Bu makalede, günümüz modern uygulamalarında hızla artan veri miktar ve boyutlarının sebep olduğu algoritma eğitme sorunlarının çözümüne yönelik, kompakt veri özniteliklerinin öğrenilmesi amacıyla bir boyut indirgeme metodu önerilmiştir. Verinin boyutu yüksek olsa da, genellikle taşıdığı bilgi daha düşük boyutlu alt uzaylarda yaşar. Çalışmamızda, böyle alt uzayların bir kümesel birleşimi burada geliştirdiğimiz yenilikçi bir ileri beslemeli sinir ağı ile algoritmik öğrenilmiştir. İlaveten, bu bağlamdaki sınıflandırma problemleri üzerinde durduk. Metodumuzun performansı öncelikle kendi oluşturduğumuz bir yapay veri seti üzerinde incelenmiştir. Sonrasında ise, durağan hal görsel uyarılmış potansiyel (DHGUP) tabanlı beyin-bilgisayar arayüzü (BBA) heceletici sistemleri için sıkça kullanılan genel kullanıma açık bir veri seti üzerinde metodumuz test edilmiştir. Sonuçlar, metodumuzun alt uzayları başarıyla bulabildiğini ve diğer DHGUP BBA heceletici hedef karakter tanıma metotlarından makul zaman aralıklarında daha iyi bir performans (0,8 saniye sinyal uzunluğunda 156 bit/dk’lık veri aktarım hızı) verdiğini göstermiştir.

Destekleyen Kurum

Türkiye Bilimsel ve Teknolojik Araştırma Kurumu (TÜBİTAK)

Proje Numarası

118E268

Teşekkür

Bu çalışma, Türkiye Bilimsel ve Teknolojik Araştırma Kurumu (TÜBİTAK) tarafından 118E268 numaralı proje kapsamında desteklenmiş, ve birinci yazar Abdullah Kutay Cankı’nın yüksek lisans tezi kapsamında yapılmıştır. Yazım ve deney aşamalarındaki yardımlarından dolayı Osman Berke Güney’e teşekkür ederiz.

Kaynakça

  • Abdi, H. & Williams, L.J. (2010). Principal component analysis. Wiley Interdisciplinary Reviews: Computational Statistics, 2(4), 433-459. https://doi.org/10.1002/wics.101
  • Dietterich, T. G. & Bakiri, G. (1994). Solving multiclass learning problems via error-correcting output codes. Journal of Artificial Intelligence Research, 2(1), 263-286. https://dl.acm.org/doi/10.5555/1622826.1622834
  • Ghodsi, A. (2006). Dimensionality reduction a short tutorial. Department of Statistics and Actuarial Science at Univ. of Waterloo, Ontario, Canada, 37(38). https://www.math.uwaterloo.ca/~aghodsib/courses/f06stat890/readings/tutorial_stat890.pdf
  • Guney, O. B., Oblokulov, M. & Ozkan, H. (2022). A deep neural network for ssvep-based brain-computer interfaces. IEEE Transactions on Biomedical Engineering, 69(2), 932-944. https://doi.org/10.1109/TBME.2021.3110440
  • Kim, C. & Klabjan, D. (2019). A simple and fast algorithm for L1-norm kernel PCA. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(8), pp.1842-1855. https://doi.org/10.1109/TPAMI.2019.2903505
  • Kingma, D.P. & Welling, M. (2019). An introduction to variational autoencoders. Foundations and Trends in Machine Learning, 12(4), 307-392. http://dx.doi.org/10.1561/2200000056
  • Kolda, T. G. & Bader, B. W. (2009). Tensor decompositions and applications. SIAM review, 51(3), 455-500. https://doi.org/10.1137/07070111X
  • Krauledat, M., Tangermann, M., Blankertz, B. & Müller, K. R. (2008). Towards zero training for brain-computer interfacing. PloS one, 3(8), e2967. https://doi.org/10.1371/journal.pone.0002967
  • Lao, K. F., Wong, C. M., Wang, Z. & Wan, F. (2018, Ekim). Learning prototype spatial filters for subject-independent SSVEP-based brain-computer interface. IEEE International Conference on Systems, Man, and Cybernetics (SMC), Japonya, 485-490.
  • Lebedev, M. A. & Nicolelis, M. A. (2006). Brain–machine interfaces: past, present and future. Trends in Neurosciences, 29(9), 536-546. https://doi.org/10.1016/j.tins.2006.07.004
  • Lin, Z., Zhang, C., Wu, W. & Gao, X. (2006). Frequency recognition based on canonical correlation analysis for SSVEP-based BCIs. IEEE Transactions on Biomedical Engineering, 53(12), 2610-2614. https://doi.org/10.1109/TBME.2006.886577
  • Liu, F., Zhang, W. & Gu, S. (2016). Local linear Laplacian eigenmaps: A direct extension of LLE. Pattern Recognition Letters, 75, 30-35. https://doi.org/10.1016/j.patrec.2016.03.003
  • Lu, H., Plataniotis, K. N. & Venetsanopoulos, A. (2013). Multilinear subspace learning: dimensionality reduction of multidimensional data. CRC press, Florida ABD, 296.
  • Rezeika, A., Benda, M., Stawicki, P., Gembler, F., Saboor, A. & Volosyak, I. (2018). Brain–computer interface spellers: A review. Brain Sciences, 8(4), 57. https://doi.org/10.3390/brainsci8040057
  • Saeed, N., Nam, H., Haq, M.I.U. & Muhammad Saqib, D.B. (2018). A survey on multidimensional scaling. ACM Computing Surveys (CSUR), 51(3), 1-25. https://doi.org/10.1145/3178155
  • Srinivasan, R., Bibi, F. A. & Nunez, P. L. (2006). Steady-state visual evoked potentials: distributed local sources and wave-like dynamics are sensitive to flicker frequency. Brain Topography, 18(3), 167-187. https://doi.org/10.1007/s10548-006-0267-4
  • Wang, Y., Nakanishi, M., Wang, Y.-T. & Jung, T.-P. (2014, Ağustos). Enhancing detection of steady-state visual evoked potentials using individual training data. Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IL ABD, 3037–3040.
  • Wang, Y., Chen, X., Gao, X. & Gao, S. (2016). A benchmark dataset for SSVEP-based brain–computer interfaces. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 25(10), 1746-1752. https://doi.org/10.1109/TNSRE.2016.2627556
  • Wolpaw, J. R., Birbaumer, N., McFarland, D. J., Pfurtscheller, G. & Vaughan, T. M. (2002). Brain–computer interfaces for communication and control. Clinical Neurophysiology, 113(6), 767-791. https://doi.org/10.1016/S1388-2457(02)00057-3
  • Yuan, P., Chen, X., Wang, Y., Gao, X. & Gao, S. (2015). Enhancing performances of SSVEP-based brain–computer interfaces via exploiting inter-subject information. Journal of Neural Engineering, 12(4), 46006. https://doi.org/10.1088/1741-2560/12/4/046006
  • Zerafa, R., Camilleri, T., Falzon, O. & Camilleri, K. P. (2018). To train or not to train? A survey on training of feature extraction methods for SSVEP-based BCIs. Journal of Neural Engineering, 15(5), 51001. https://doi.org/10.1088/1741-2552/aaca6e
  • Zhai, J., Zhang, S., Chen, J. & He, Q. (2018, Ekim). Autoencoder and its various variants. IEEE International Conference on Systems, Man, and Cybernetics (SMC), Japonya, 415-419.
  • Zhang, Y., Zhang, Z., Qin, J., Zhang, L., Li, B. & Li, F. (2018a). Semi-supervised local multi-manifold isomap by linear embedding for feature extraction. Pattern Recognition, 76, 662-678. https://doi.org/10.1016/j.patcog.2017.09.043
  • Zhang, Y., Yin, E., Li, F., Zhang, Y., Tanaka, T., Zhao, Q., Cui, Y., Xu, P., Yao, D. & Guo, D. (2018b). Two- Stage Frequency Recognition Method Based on Correlated Component Analysis for SSVEP-Based BCI. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 26(7), 1314–1323. https://doi.org/10.1109/TNSRE.2018.2848222
  • Zhang, Z. (2018, Haziran). Improved adam optimizer for deep neural networks. IEEE/ACM 26th International Symposium on Quality of Service (IWQoS), Banff, Alberta, Kanada

SUBSPACE DISCOVERY FOR SSVEP BASED BRAIN-COMPUTER INTERFACES

Yıl 2023, , 86 - 97, 15.03.2023
https://doi.org/10.17780/ksujes.1175402

Öz

In this paper, a dimensionality reduction method is proposed for the learning of compact data features in order to mitigate the algorithm training issues caused by the increasing data size and dimensionalities in today’s modern applications. Although the dimension of data is high, most of the information typically lives in lower dimensional subspaces. In our study, a set combination of such subspaces is algorithmically learned by a novel feed forward neural network that we develop here. Additionally, we consider classification problems in this context. The performance of our method is first evaluated on a synthetic dataset that we generated. Afterwards, our method is tested on a publicly open and widely used steady state visually evoked potentials (SSVEP)-based brain-computer interface (BCI) speller system dataset. The results reveal that our method successfully finds the subspaces and delivers a superior performance (156 bit/min information transfer rate at 0,8 seconds of signal length) than other SSVEP BCI speller target character recognition methods in reasonable time intervals.

Proje Numarası

118E268

Kaynakça

  • Abdi, H. & Williams, L.J. (2010). Principal component analysis. Wiley Interdisciplinary Reviews: Computational Statistics, 2(4), 433-459. https://doi.org/10.1002/wics.101
  • Dietterich, T. G. & Bakiri, G. (1994). Solving multiclass learning problems via error-correcting output codes. Journal of Artificial Intelligence Research, 2(1), 263-286. https://dl.acm.org/doi/10.5555/1622826.1622834
  • Ghodsi, A. (2006). Dimensionality reduction a short tutorial. Department of Statistics and Actuarial Science at Univ. of Waterloo, Ontario, Canada, 37(38). https://www.math.uwaterloo.ca/~aghodsib/courses/f06stat890/readings/tutorial_stat890.pdf
  • Guney, O. B., Oblokulov, M. & Ozkan, H. (2022). A deep neural network for ssvep-based brain-computer interfaces. IEEE Transactions on Biomedical Engineering, 69(2), 932-944. https://doi.org/10.1109/TBME.2021.3110440
  • Kim, C. & Klabjan, D. (2019). A simple and fast algorithm for L1-norm kernel PCA. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(8), pp.1842-1855. https://doi.org/10.1109/TPAMI.2019.2903505
  • Kingma, D.P. & Welling, M. (2019). An introduction to variational autoencoders. Foundations and Trends in Machine Learning, 12(4), 307-392. http://dx.doi.org/10.1561/2200000056
  • Kolda, T. G. & Bader, B. W. (2009). Tensor decompositions and applications. SIAM review, 51(3), 455-500. https://doi.org/10.1137/07070111X
  • Krauledat, M., Tangermann, M., Blankertz, B. & Müller, K. R. (2008). Towards zero training for brain-computer interfacing. PloS one, 3(8), e2967. https://doi.org/10.1371/journal.pone.0002967
  • Lao, K. F., Wong, C. M., Wang, Z. & Wan, F. (2018, Ekim). Learning prototype spatial filters for subject-independent SSVEP-based brain-computer interface. IEEE International Conference on Systems, Man, and Cybernetics (SMC), Japonya, 485-490.
  • Lebedev, M. A. & Nicolelis, M. A. (2006). Brain–machine interfaces: past, present and future. Trends in Neurosciences, 29(9), 536-546. https://doi.org/10.1016/j.tins.2006.07.004
  • Lin, Z., Zhang, C., Wu, W. & Gao, X. (2006). Frequency recognition based on canonical correlation analysis for SSVEP-based BCIs. IEEE Transactions on Biomedical Engineering, 53(12), 2610-2614. https://doi.org/10.1109/TBME.2006.886577
  • Liu, F., Zhang, W. & Gu, S. (2016). Local linear Laplacian eigenmaps: A direct extension of LLE. Pattern Recognition Letters, 75, 30-35. https://doi.org/10.1016/j.patrec.2016.03.003
  • Lu, H., Plataniotis, K. N. & Venetsanopoulos, A. (2013). Multilinear subspace learning: dimensionality reduction of multidimensional data. CRC press, Florida ABD, 296.
  • Rezeika, A., Benda, M., Stawicki, P., Gembler, F., Saboor, A. & Volosyak, I. (2018). Brain–computer interface spellers: A review. Brain Sciences, 8(4), 57. https://doi.org/10.3390/brainsci8040057
  • Saeed, N., Nam, H., Haq, M.I.U. & Muhammad Saqib, D.B. (2018). A survey on multidimensional scaling. ACM Computing Surveys (CSUR), 51(3), 1-25. https://doi.org/10.1145/3178155
  • Srinivasan, R., Bibi, F. A. & Nunez, P. L. (2006). Steady-state visual evoked potentials: distributed local sources and wave-like dynamics are sensitive to flicker frequency. Brain Topography, 18(3), 167-187. https://doi.org/10.1007/s10548-006-0267-4
  • Wang, Y., Nakanishi, M., Wang, Y.-T. & Jung, T.-P. (2014, Ağustos). Enhancing detection of steady-state visual evoked potentials using individual training data. Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IL ABD, 3037–3040.
  • Wang, Y., Chen, X., Gao, X. & Gao, S. (2016). A benchmark dataset for SSVEP-based brain–computer interfaces. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 25(10), 1746-1752. https://doi.org/10.1109/TNSRE.2016.2627556
  • Wolpaw, J. R., Birbaumer, N., McFarland, D. J., Pfurtscheller, G. & Vaughan, T. M. (2002). Brain–computer interfaces for communication and control. Clinical Neurophysiology, 113(6), 767-791. https://doi.org/10.1016/S1388-2457(02)00057-3
  • Yuan, P., Chen, X., Wang, Y., Gao, X. & Gao, S. (2015). Enhancing performances of SSVEP-based brain–computer interfaces via exploiting inter-subject information. Journal of Neural Engineering, 12(4), 46006. https://doi.org/10.1088/1741-2560/12/4/046006
  • Zerafa, R., Camilleri, T., Falzon, O. & Camilleri, K. P. (2018). To train or not to train? A survey on training of feature extraction methods for SSVEP-based BCIs. Journal of Neural Engineering, 15(5), 51001. https://doi.org/10.1088/1741-2552/aaca6e
  • Zhai, J., Zhang, S., Chen, J. & He, Q. (2018, Ekim). Autoencoder and its various variants. IEEE International Conference on Systems, Man, and Cybernetics (SMC), Japonya, 415-419.
  • Zhang, Y., Zhang, Z., Qin, J., Zhang, L., Li, B. & Li, F. (2018a). Semi-supervised local multi-manifold isomap by linear embedding for feature extraction. Pattern Recognition, 76, 662-678. https://doi.org/10.1016/j.patcog.2017.09.043
  • Zhang, Y., Yin, E., Li, F., Zhang, Y., Tanaka, T., Zhao, Q., Cui, Y., Xu, P., Yao, D. & Guo, D. (2018b). Two- Stage Frequency Recognition Method Based on Correlated Component Analysis for SSVEP-Based BCI. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 26(7), 1314–1323. https://doi.org/10.1109/TNSRE.2018.2848222
  • Zhang, Z. (2018, Haziran). Improved adam optimizer for deep neural networks. IEEE/ACM 26th International Symposium on Quality of Service (IWQoS), Banff, Alberta, Kanada
Toplam 25 adet kaynakça vardır.

Ayrıntılar

Birincil Dil Türkçe
Konular Bilgisayar Yazılımı, Elektrik Mühendisliği
Bölüm Elektrik Elektronik Mühendisliği
Yazarlar

Abdullah Kutay Cankı 0000-0002-4485-6826

Hüseyin Özkan 0000-0002-5539-9085

Proje Numarası 118E268
Yayımlanma Tarihi 15 Mart 2023
Gönderilme Tarihi 14 Eylül 2022
Yayımlandığı Sayı Yıl 2023

Kaynak Göster

APA Cankı, A. K., & Özkan, H. (2023). DHGUP TABANLI BEYİN-BİLGİSAYAR ARAYÜZLERİ İÇİN ALT UZAY KEŞFİ. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 26(1), 86-97. https://doi.org/10.17780/ksujes.1175402