Journal of IKEEE (전기전자학회논문지)

Institute of Korean Electrical and Electronics Engineers (한국전기전자학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on EEG Artifact Removal Method using Eye tracking Sensor Data

시선 추적 센서 데이터를 활용한 뇌파 잡파 제거 방법에 관한 연구

  • Yun, Jong-Seob (Dept. of Computer Engineering, Seokyeong University) ;
  • Kim, Jin-Heon (Dept. of Computer Engineering, Seokyeong University)
  • Received : 2018.12.07
  • Accepted : 2018.12.20
  • Published : 2018.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Electroencephalogram (EEG) is a tool used to study brain activity caused by external stimuli. In this process, artifacts are mixed and it is easy to distort the signal, so post-processing is necessary to remove it. Independent Component Analysis (ICA) is a widely used method for removing artifact. This method has a disadvantage in that it has excellent performance but some loss of brain wave information. In this paper, we propose a method to reduce EEG information loss by restricting the filter coverage using eye blink information obtained from Eyetracker. We then compared the results of the proposed method with the conventional method using quantization methods such as Signal to Noise Ratio (SNR) and Spectral Coherence (SC).

뇌파(Electroencephalogram, EEG)는 외부 자극 때문에 발생하는 뇌 활동을 연구하기 위해 사용되는 도구로 두피에 전극을 부착하여 기록한다. 이 과정에서 잡파(artifact)가 혼입되어 신호를 왜곡시키기 쉬워 이를 제거하기 위한 후처리가 필수적이다. 잡파 제거를 위해 널리 사용되는 방법으로 독립성분분석(Independent Component Analysis, ICA)이 존재한다. 이 방법은 성능은 우수하나 뇌파 정보를 일부 손실시키는 단점이 있다. 본 논문에서는 이러한 문제점을 보완하기 위해 시선 추적 센서(Eyetracker)를 통해 얻은 눈 깜빡임 정보를 이용하여 필터 적용 범위를 제한함으로써 뇌파 정보 손실을 줄이는 방법을 제안한다. 이후 신호 대 잡음 비(Signal to Noise Ratio, SNR), 스펙트럼 일관성(Spectral Coherence, SC) 등의 정량화 방법을 이용하여 기존의 방법과 제안하는 방법의 결과를 비교하였다.

Keywords

JGGJB@_2018_v22n4_1109_f0001.png 이미지

Fig. 1. Process of eye blink artifact removal from EEG. 그림 1. EEG 신호의 눈 깜빡임 잡파 제거 처리 과정

JGGJB@_2018_v22n4_1109_f0002.png 이미지

Fig. 2. Area of blink artifact on EEG signal. 그림 2. 뇌파 신호상 눈 깜빡임 잡파 영역

JGGJB@_2018_v22n4_1109_f0003.png 이미지

Fig. 3. Location of Muse sensor electrodes on 10-20 system. 그림 3. Muse 센서 10-20 system 전극 위치

JGGJB@_2018_v22n4_1109_f0004.png 이미지

Fig. 4. Comparison artifact removal methods. EEG raw signal filtered with bandpass filter(top), IC removal method(middle), The proposed method(bottom). 그림 4. 잡파 제거 결과 비교. 대역 통과 필터 적용 뇌파 신호(위), 기존 독립성분제거 방법(중간), 제안한 방법(아래)

JGGJB@_2018_v22n4_1109_f0005.png 이미지

Fig. 5. Comparison of coherence values between EEG signal and EEG signal before and after algorithm improvement. 그림 5. 개선 전, 후 잡파 제거 알고리즘 결과물과 뇌파 신호 사이의 일관성 수치 비교

Table 1. Quantitative numerical comparison of artifact removal algorithm 표 1. 잡파 제거 알고리즘의 정량적 수치 비교

JGGJB@_2018_v22n4_1109_t0001.png 이미지

References

  1. A. Jalilifard, E. B. Pizzolato and M. K. Islam, "Emotion classification using single-channel scalp-EEG recording," in Proc. of the 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp.845-849, 2016. DOI:10.1109/EMBC.2016.7590833
  2. W. Zheng, "Multichannel EEG-Based Emotion Recognition via Group Sparse Canonical Correlation Analysis," IEEE Trans. Cogn. Develop. Syst, Vol.9, No.3, pp.281-290, 2017. DOI:10.1109/TCDS.2016.2587290
  3. M. Li and B.L. Lu, "Emotion classification based on gamma-band EEG," in Proc. of the 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp.1223-1226, 2009. DOI:10.1109/IEMBS.2009.5334139
  4. B. Abibullaev, "Learning suite of kernel feature spaces enhances SMR-based EEG-BCI classification," in Proc. of the 2017 5th International Winter Conference on Brain-Computer Interface (BCI), pp.55-59, 2017. DOI:10.1109/IWW-BCI.2017.7858158
  5. M. Z. Ilyas, P. Saad, M.I. Ahmad and A. R. I. Ghani, "Classification of EEG signals for brain-computer interface applications: Performance comparison," in Proc. of the 2016 International Conference on Robotics, Automation and Sciences (ICORAS), pp.1-4, 2016. DOI:10.1109/ICORAS.2016.7872610
  6. P. Tan, W.S. and L. Yu, "Applying Extreme Learning Machine to classification of EEG BCI," in Proc. of the 2016 IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems (CYBER), pp.228-232, 2016. DOI:10.1109/CYBER.2016.7574827
  7. M. Z. Ahmad, M. Saeed, S. Saleem and A. M. Kamboh, "Seizure detection using EEG: A survey of different techniques," in Proc. of the 2016 International Conference on Emerging Technologies (ICET), pp.1-6, 2016. DOI:0.1109/ICET.2016.7813209 https://doi.org/10.1109/ICET.2016.7813209
  8. Y. Yuan, G. Xun, F. Ma, Q. Suo, H. Xue, K. Jia et al., "A novel channel-aware attention framework for multi-channel EEG seizure detection via multi-view deep learning," in Proc. of the 2018 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI), pp.206-209, 2018. DOI:10.1109/BHI.2018.8333405
  9. E. Kim and D. Shin, "Nonlinear and Independent Component Analysis of EEG with Artifacts," J. Fuzzy Log. Intell. Syst., Vol.12, No.5, pp.442-450, 2002.
  10. N. P. Castellanos and V. A. Makarov, "Recovering EEG brain signals: Artifact suppression with wavelet enhanced independent component analysis," J. Neurosci. Methods, Vol.158, No.2, pp.300-312, 2006. DOI:10.5391/JKIIS.2002.12.5.442
  11. M. A. Klados, C. Papadelis, C. Braun, and P. D. Bamidis, "REG-ICA: A hybrid methodology combining Blind Source Separation and regression techniques for the rejection of ocular artifacts," Biomed. Signal Process. Control, Vol.6, No.3, pp.291-300, 2011. DOI:10.1016/j.bspc.2011.02.001
  12. J. W. Matiko, S. Beeby, and J. Tudor, "Real time eye blink noise removal from EEG signals using morphological component analysis," in Proc. of the 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp.13-16, 2013. DOI:10.1109/EMBC.2013.6609425