Journals / Yüzüncü Yıl Üniversitesi Fen Bilimleri Enstitüsü Dergisi / 2022 / Cilt: 27 - Sayı: 1

Creating an Online Subject Independent P300-Based Brain-Computer Interface Classification Model

Kişiden Bağımsız Çevrimiçi P300-Tabanlı Beyin-Bilgisayar Arayüzü Sınıflandırma Modeli Oluşturulması

Pages
73–85
Publication Date
2022-11-06
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

This model's online character detection success, subject independent, was 95.41%

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Brain-computer interfaces convert electroencephalography signals into computer commands to communicate between the human brain and computer or external devices.
📊
Key Findings & Data:However, one of the most significant limitations of these systems is that it takes a long time to develop a subject-independent model, so patients cannot benefit from the plug-and-play comfort.
💡
Conclusion & Impact:This model's online character detection success, subject independent, was 95.41%
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Beyin-bilgisayar arayüzü · Çevrimiçi · Kişiden bağımsız model

Abstract

Brain-computer interfaces convert electroencephalography signals into computer commands to communicate between the human brain and computer or external devices. However, one of the most significant limitations of these systems is that it takes a long time to develop a subject-independent model, so patients cannot benefit from the plug-and-play comfort. With this study, we created our data set with the data we collected from 10 people in the offline session using new paradigm we developed. A brain-computer interface classification model that works subject-independent was created with this data set. First of all, in the binary classification problem in which event-related potential and non-event-related potential detection were performed, 99.40% ± 0.21 test accuracy was obtained due to the classification process being repeated 50 times, and this model was saved. This developed model was tested by printing the words that 30 different participants determined themselves. This model's online character detection success, subject independent, was 95.41%

Özet

Beyin-bilgisayar arayüzleri, elektroensefalografi sinyallerini bilgisayar komutlarına çevirerek insan beyni ile bilgisayar veya harici cihazlar arasında iletişim kurmaya yarayan sistemlerdir. Bu sistemlerin en büyük sınırlamalarından biri, kişiye özgü modelin geliştirilmesinin uzun sürmesi, böylelikle de hasta bireylerin tak-çalıştır konforundan yararlanamamasıdır. Yapılan bu çalışma ile geliştirilen yeni paradigma kullanılarak çevrimdışı oturumda 10 katılımcıdan toplanılan verilerle kişiden bağımsız çalışan sınıflandırma modeli geliştirildi. Öncelikle olay ilişkili potansiyel ve olay ilişkili olmayan potansiyel tespitinin gerçekleştirildiği bu ikili sınıflandırma probleminde 50 kez tekrarlanan sınıflandırma işlemi sonucunda %99.40 ± 0.21 test doğruluğu elde edilmiş ve kişiden bağımsız model olarak kaydedilmiştir. Geliştirilen bu model farklı 30 katılımcının kendilerinin belirlediği kelimelerin yazdırılması şeklinde test edilmiştir. Önerilen kişiden bağımsız bu modelin çevrimiçi karakter tespit etme başarısı ise %95.41 olarak hesaplanmıştır.

🔖

Cite This Article

KORKMAZ, O. E., AYDEMİR, Ö., ORAL, E. A., ÖZBEK, İ. Y. (2022). Creating an Online Subject Independent P300-Based Brain-Computer Interface Classification Model. Yüzüncü Yıl Üniversitesi Fen Bilimleri Enstitüsü Dergisi, Cilt: 27 - Sayı: 1, 73–85. https://ajindex.com/articles/647765

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (2)

  1. Adobe. (2017). Adobe Inc. Adobe Photoshop for Windows. Ahmad, M. M., & Ahuja, K. (2022). Role of 5G Communication Along with Blockchain Security in Brain-Computer Interfacing: A Review. Futuristic Design and Intelligent Computational Techniques in Neuroscience and Neuroengineering. doi: 10.4018/978-1-7998-7433-1.ch004 Brysbaert, M. (2019). How many words do we read per minute? A review and meta-analysis of reading rate. Journal of Memory and Language, 109, 104047. doi: 10.1016/j.jml.2019.104047 Devlaminck, D., Wyns, B., Grosse-Wentrup, M., Otte, G., & Santens, P. (2011). Multisubject learning for common spatial patterns in motor-imagery BCI. Computational intelligence and neuroscience, 2011. doi: 10.1155/2011/217987 Ergün, E., & Aydemir, Ö. (2020). A hybrid BCI using singular value decomposition values of the fast walsh hadamard transform coefficients. IEEE Transactions on Cognitive and Developmental Systems. doi: 10.1109/TCDS.2020.3028785 Jalilpour, S., Sardouie, S. H., & Mijani, A. (2020). A novel hybrid BCI speller based on RSVP and SSVEP paradigm. Computer methods and programs in biomedicine, 187, 105326. doi: 10.1016/j.cmpb.2020.105326 Kevric, J., & Subasi, A. (2017). Comparison of signal decomposition methods in classification of EEG signals for motor-imagery BCI system. Biomedical Signal Processing and Control, 31, 398-406. doi: 10.1016/j.bspc.2016.09.007 Kirasirova, L., Bulanov, V., Ossadtchi, A., Kolsanov, A., Pyatin, V., & Lebedev, M. (2020). A P300 brain-computer interface with a reduced visual field. Frontiers in neuroscience, 14, 1246. doi: 10.3389/fnins.2020.604629 Kleih, S. C., & Kübler, A. (2013). Empathy, motivation, and P300 BCI performance. Frontiers in human neuroscience, 7, 642. doi: 10.3389/fnhum.2013.00642 Loizidou, P., Rios, E., Marttini, A., Keluo-Udeke, O., Soetedjo, J., Belay, J., & Speier, W. (2022). Extending brain-computer interface access with a multilingual language model in the P300 speller. Brain-Computer Interfaces, 9(1), doi: 10.1080/2326263X.2021.1993426 Lu, Z., Li, Q., Gao, N., & Yang, J. (2020). The self-face paradigm improves the performance of the P300-speller system. Frontiers in computational neuroscience, 13, 93. doi: 10.3389/fncom.2019.00093 Matlab. (2018).
  2. MathWorks for Windows. Muller-Putz, G. R., & Pfurtscheller, G. (2007). Control of an electrical prosthesis with an SSVEP-based BCI. IEEE Transactions on Biomedical Engineering, 55(1), 361-364. doi: 10.1109/TBME.2007.897815 Mussabayeva, A., Jamwal, P. K., & Ak