Journal of Biomedical Engineering Research (대한의용생체공학회:의공학회지)

The Korean Society of Medical and Biological Engineering (대한의용생체공학회)
권호 표지
DOI QR코드

DOI QR Code

Assessment of Classification Accuracy of fNIRS-Based Brain-computer Interface Dataset Employing Elastic Net-Based Feature Selection

Elastic net 기반 특징 선택을 적용한 fNIRS 기반 뇌-컴퓨터 인터페이스 데이터셋 분류 정확도 평가

  • Shin, Jaeyoung (Department of Electronic Engineering, Wonkwang University)
  • 신재영 (원광대학교 전자공학과)
  • Received : 2021.07.23
  • Accepted : 2021.12.14
  • Published : 2021.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Functional near-infrared spectroscopy-based brain-computer interface (fNIRS-based BCI) has been receiving much attention. However, we are practically constrained to obtain a lot of fNIRS data by inherent hemodynamic delay. For this reason, when employing machine learning techniques, a problem due to the high-dimensional feature vector may be encountered, such as deteriorated classification accuracy. In this study, we employ an elastic net-based feature selection which is one of the embedded methods and demonstrate the utility of which by analyzing the results. Using the fNIRS dataset obtained from 18 participants for classifying brain activation induced by mental arithmetic and idle state, we calculated classification accuracies after performing feature selection while changing the parameter α (weight of lasso vs. ridge regularization). Grand averages of classification accuracy are 80.0 ± 9.4%, 79.3 ± 9.6%, 79.0 ± 9.2%, 79.7 ± 10.1%, 77.6 ± 10.3%, 79.2 ± 8.9%, and 80.0 ± 7.8% for the various values of α = 0.001, 0.005, 0.01, 0.05, 0.1, 0.2, and 0.5, respectively, and are not statistically different from the grand average of classification accuracy estimated with all features (80.1 ± 9.5%). As a result, no difference in classification accuracy is revealed for all considered parameter α values. Especially for α = 0.5, we are able to achieve the statistically same level of classification accuracy with even 16.4% features of the total features. Since elastic net-based feature selection can be easily applied to other cases without complicated initialization and parameter fine-tuning, we can be looking forward to seeing that the elastic-based feature selection can be actively applied to fNIRS data.

Keywords

Acknowledgement

이 논문은 2020년도 원광대학교 교비지원에 의해 수행됨.

References

  1. Boas DA, Elwell CE, Ferrari M, Taga G. Twenty years of functional near-infrared spectroscopy: introduction for the special issue. 2014;85:Part 1:1-5.
  2. Scholkmann F, Kleiser S, Metz AJ, Zimmermann R, Mata Pavia J, Wolf U, Wolf M. A review on continuous wave functional near-infrared spectroscopy and imaging instrumentation and methodology. 2014;85:Part 1:6-27. https://doi.org/10.1016/j.neuroimage.2013.05.004
  3. Quaresima V, Ferrari M. A mini-review on functional near-infrared spectroscopy (fNIRS): where do we stand, and where should we go? 2019;6(3):87. https://doi.org/10.3390/photonics6030087
  4. Nazeer H, Naseer N, Khan RA, Noori FM, Qureshi NK, Khan US, Khan MJ. Enhancing classification accuracy of fNIRS-BCI using features acquired from vector-based phase analysis. 2020;17(5):056025. https://doi.org/10.1088/1741-2552/abb417
  5. Qureshi NK, Naseer N, Noori FM, Nazeer H, Khan RA, Saleem S. Enhancing classification performance of functional near-infrared spectroscopy-brain-computer interface using adaptive estimation of general linear model coefficients. 2017;11(33).
  6. Nazeer H, Naseer N, Mehboob A, Khan MJ, Khan RA, Khan US, Ayaz Y. Enhancing classification performance of fNIRS-BCI by identifying cortically active channels using the z-score method. 2020;20(23):6995. https://doi.org/10.3390/s20236995
  7. Shin J, Kwon J, Choi J, Im C-H. Performance enhancement of a brain-computer interface using high-density multi-distance NIRS. 2017;7:16545. https://doi.org/10.1038/s41598-017-16639-0
  8. Shin J, Im C-H. Performance Improvement of Near-Infrared Spectroscopy-Based Brain-Computer Interface Using Regularized Linear Discriminant Analysis Ensemble Classifier Based on Bootstrap Aggregating. 2020;14(168).
  9. Ma T, Wang S, Xia Y, Zhu X, Evans J, Sun Y, He S. CNN-based classification of fNIRS signals in motor imagery BCI system. 2021;18(5):056019. https://doi.org/10.1088/1741-2552/abf187
  10. Nagasawa T, Sato T, Nambu I, Wada Y. fNIRS-GANs: data augmentation using generative adversarial networks for classifying motor tasks from functional near-infrared spectroscopy. 2020;17(1):016068. https://doi.org/10.1088/1741-2552/ab6cb9
  11. Sm JA, Chhabra H, Shajil N, Venkatasubramanian G. Investigation of deep convolutional neural network for classification of motor imagery fNIRS signals for BCI applications. 2020;62:102133. https://doi.org/10.1016/j.bspc.2020.102133
  12. Cui X, Bray S, Reiss AL. Speeded near infrared spectroscopy (NIRS) response detection. 2010;5(11):15474.
  13. Shin J, von Luhmann A, Kim D-W, Mehnert J, Hwang H-J, Muller K-R. Simultaneous acquisition of EEG and NIRS during cognitive tasks for an open access dataset. 2018;5:180003. https://doi.org/10.1038/sdata.2018.3
  14. Shin J, von Luhmann A, Blankertz B, Kim D-W, Jeong J, Hwang H-J, Muller K-R. Open access dataset for EEG+NIRS single-trial classification. 2017;25(10):1735-1745. https://doi.org/10.1109/TNSRE.2016.2628057
  15. Shin J, Muller K-R, Hwang H-J. Near-infrared spectroscopy (NIRS) based eyes-closed brain-computer interface (BCI) using prefrontal cortex activation due to mental arithmetic. 2016;6(1):36203. https://doi.org/10.1038/srep36203
  16. Hwang H-J, Choi H, Kim J-Y, Chang W-D, Kim D-W, Kim K, Jo S, Im C-H. Toward more intuitive brain-computer interfacing: classification of binary covert intentions using functional near-infrared spectroscopy. 2016;21(9):091303. https://doi.org/10.1117/1.JBO.21.9.091303
  17. Hosseini R, Walsh B, Tian FH, Wang SY. An fNIRS-based Feature Learning and Classification Framework to Distinguish Hemodynamic Patterns in Children Who Stutter. 2018;26(6):1254-1263. https://doi.org/10.1109/tnsre.2018.2829083
  18. Radovic M, Ghalwash M, Filipovic N, Obradovic Z. Minimum redundancy maximum relevance feature selection approach for temporal gene expression data. 2017;18.
  19. Noori FM, Naseer N, Qureshi NK, Nazeer H, Khan RA. Optimal feature selection from fNIRS signals using genetic algorithms for BCI. 2017;647:61-66. https://doi.org/10.1016/j.neulet.2017.03.013
  20. Shin J, Kwon J, Im C-H. A Ternary Hybrid EEG-NIRS Brain-Computer Interface for the Classification of Brain Activation Patterns during Mental Arithmetic, Motor Imagery, and Idle State. 2018;23:5. https://doi.org/10.3389/fninf.2018.00005
  21. Zhang Q, Strangman GE, Ganis G. Adaptive filtering to reduce global interference in non-invasive NIRS measures of brain activation: How well and when does it work? 2009;45(3):788-794. https://doi.org/10.1016/j.neuroimage.2008.12.048
  22. Falk TH, Guirgis M, Power S, Chau T. Taking NIRS-BCIs outside the lab: towards achieving robustness against environment noise. 2011;19(2):136-146. https://doi.org/10.1109/TNSRE.2010.2078516
  23. Power SD, Kushki A, Chau T. Automatic single-trial discrimination of mental arithmetic, mental singing and the no-control state from prefrontal activity: toward a three-state NIRS-BCI. 2012;5(1):141. https://doi.org/10.1186/1756-0500-5-141
  24. Power SD, Kushki A, Chau T. Towards a system-paced near-infrared spectroscopy brain-computer interface: differentiating prefrontal activity due to mental arithmetic and mental singing from the no-control state. 2011;8(6):066004. https://doi.org/10.1088/1741-2560/8/6/066004
  25. Schudlo LC, Chau T. Towards a ternary NIRS-BCI: single-trial classification of verbal fluency task, Stroop task and unconstrained rest. 2015;12(6):066008. https://doi.org/10.1088/1741-2552/12/6/066008
  26. Tibshirani R. Regression shrinkage and selection via the lasso. 1996;58(1):267-288. https://doi.org/10.1111/j.2517-6161.1996.tb02080.x
  27. Zou H, Hastie T. Regularization and variable selection via the elastic net. 2005;67(2):301-320. https://doi.org/10.1111/j.1467-9868.2005.00503.x
  28. Svinkunaite L, Horschig J, Floor-Westerdijk, M. Employing cardiac and respiratory features extracted from fNIRS signals for mental workload classification. SPIE BiOS. online. 2021.
  29. Guyon I, Elisseeff A. An introduction to variable and feature selection. 2003;3(Mar.):1157-1182.
  30. Naseer N, Hong K-S. fNIRS-based brain-computer interfaces: a review. 2015;9(1):3.
  31. Yap BW, Sim CH. Comparisons of various types of normality tests. 2011;81(12):2141-2155. https://doi.org/10.1080/00949655.2010.520163
  32. Hochberg Y, Tamhane AC. Multiple comparison procedures. John Wiley & Sons, Inc. 1987.
  33. Fernandez Rojas R, Huang X, Ou K-L. A machine learning approach for the identification of a biomarker of human pain using fNIRS. 2019;9(1):5645. https://doi.org/10.1038/s41598-019-42098-w
  34. Chen L, Li Q, Song H, Gao R, Yang J, Dong W, Dang W. Classification of schizophrenia using general linear model and support vector machine via fNIRS. 2020;43(4):1151-1160. https://doi.org/10.1007/s13246-020-00920-0
  35. Herff C, Heger D, Fortmann O, Hennrich J, Putze F, Schultz T. Mental workload during n-back task-quantified in the prefrontal cortex using fNIRS. 2013;7(1):935.
  36. Grubbs FE. Sample criteria for testing outlying observations. 1950;21(1):27-58. https://doi.org/10.1214/aoms/1177729885