Journal of the Institute of Convergence Signal Processing (융합신호처리학회논문지)

The Korea Institute of Convergence Signal Processing (한국융합신호처리학회)
권호 표지
DOI QR코드

DOI QR Code

Impact of Data Continuity in EEG Signal-based BCI Research

뇌파 신호 기반 BCI 연구에서 데이터 연속성의 영향

  • Youn-Sang Kim (Department of Medical Engineering, Konyang University) ;
  • Ju-Hyuck Han (Department of Medical Engineering, Konyang University) ;
  • Woong-Sik Kim (Department of Medical Artificial Intelligence, Konyang University)
  • 김윤상 (건양대학교 의료공학과) ;
  • 한주혁 (건양대학교 의료공학과) ;
  • 김웅식 (건양대학교 의료인공지능학과)
  • Received : 2023.12.19
  • Accepted : 2024.03.30
  • Published : 2024.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

This study conducted a comparative experiment on the continuity of time series data and the classification performance of artificial intelligence models. In BCI research using EEG signals, the performance of behavior and thought classification improved as the continuity of the data decreased. In particular, LSTM achieved a high performance of 0.8728 on data with low continuity, and DNN showed a performance of 0.9178 when continuity was not considered. This suggests that data without continuity may perform better. Additionally, data without continuity showed better performance in task classification. These results suggest that BCI research based on EEG signals can perform better by showing various data characteristics through shuffling rather than considering data continuity.

본 연구는 시계열 데이터의 연속성과 인공지능 모델의 분류 성능에 대한 비교 실험을 수행하였다. EEG 신호를 이용한 BCI 연구에서는 데이터 연속성이 감소할수록 행동과 사고 분류의 성능이 향상되었다. 특히, LSTM은 연속성이 낮은 데이터에서 0.8728이라는 높은 성능을 달성하였고, 연속성을 고려하지 않은 경우 DNN이 0.9178의 성능을 보였다. 연속성을 고려하지 않는 데이터가 더 우수한 성능을 보일 수 있음을 시사하였다. 또한, 연속성을 고려하지 않은 데이터는 작업 분류에서도 더 높은 성능을 보였다. 이러한 결과는 뇌파 신호를 기반으로 한 BCI 연구에서는 데이터 연속성을 고려하기보다는 셔플링을 통해 다양한 데이터 특성을 보여줌으로써 우수한 성능을 발휘할 수 있음을 시사한다.

Keywords

Acknowledgement

이 논문은 2023년도 정부(산업통상자원부)의 재원으로 한국산업기술진흥원의 '바이오융복합기술 전문인력 양성사업'의 지원을 받아 수행된 연구임(No. P0017805).

References

  1. C. G. Langton, "Artificial Life: The Proceedings of an Interdisciplinary Workshop on the Synthesis and Simulation of Living Systems, Held September, 1987, in Los Alamos, New Mexico," in Artificial Life, xth ed., Addison-Wesley Pub. Co., Advanced Book Program, 1989. 
  2. G. Macauda, "Artifacts removal and application of cross-frequency coupling to EEG signals of epileptic patients," Webthesis, 2020. 
  3. W.-S. Choi and H.-G. Yeom, "Studies to overcome brain-computer interface challenges," MDPI, Vol.12(5), pp.2598, 2022. 
  4. M. Lo Giudice et al., "1D convolutional neural netw ork approach to classify voluntary eye blinks in EEG signals for BCI applications," in Proceedings of the 2020 International Joint Conference on Neural Networ ks (IJCNN), 2020, doi:10.1109/ijcnn48605.2020.9207195. 
  5. S. Cheng, J. Wang, L. Zhang, and Q. Wei, "Motion imagery-BCI based on EEG and eye movement data fusion," IEEE Trans. Neural Syst. Rehabil. Eng., vol. 28, no. 12, pp. 2783-2793, 2020, doi:10.1109/tnsre.2020.3048422. 
  6. H. S. Lee et al., "Individual finger movement decoding using a novel ultra-high-density electroencephalography-based brain-computer interface system," Front. Neurosci, vol.16, 2022. 
  7. J. Shin, J. Kwon, and C.-H. Im, "A ternary hybrid EEG-NIRS brain-computer interface for the classificat ion of brain activation patterns during mental arithm etic, motor imagery, and Idle State," Front. Neuroinf ormatics, vol.12, 2018, doi:10.3389/fninf.2018.00005. 
  8. R. Chai et al., "Selecting optimal EEG channels for mental tasks classification: An approach using ICA," in Proceedings of the 2016 IEEE Congress on Evolutionary Computation (CEC), 2016, doi:10.1109/cec.2016.7743942. 
  9. R. Darmakusuma et al., "Analysis of arm movement prediction by using the Electroencephalography signal," Makara Journal of Technology, vol. 20, no. 1, pp.38, 2016, doi:10.7454/mst.v20i1.3054. 
  10. C. Huang, Y. Xiao, and G. Xu, "Predicting human intention-behavior through EEG signal analysis using multi-scale CNN," IEEE/ACM Trans. Comput. Biol. Bioinformatics, vol.18, no.5, pp.1722-1729, 2021, doi:10.1109/tcbb.2020.3039834. 
  11. J.-H. Cho, J.-R. Jeong, D.-J. Kim, and S.-W. Lee, "A novel approach to classify natural grasp actions by estimating muscle activity patterns from EEG signals," in Proceedings of the 2020 8th International Winter Conference on Brain-Computer Interface (BCI), 2020, doi:10.1109/bci48061.2020.9061627.