Improving classification performance of four class FNIRS-BCI using Mel Frequency Cepstral Coefficients (MFCC)

Abstract Experimentation and analysis of Functional near-infrared spectroscopy (fNIRS) in Brain-Computer Interface (BCI) has increasingly been studied as a communication possibility for patients who are severely paralyzed. This study has applied this technique to distinguish brain activities during four different mental tasks. These tasks include Mental Arithmetic (MA), Motor Imagery of Left-Hand (LHMI) and Right-Hand (RHMI) and Rest. fNIRS data used is from an open access dataset of 29 individuals which was collected by Continuous-wave imaging system (NIR Scout). In this research Data integration is performed before the data is preprocessed. Usual preprocessing is done using Butterworth filter to minimize or eliminate any unwanted signal distortion. After that an extensive signal analysis is done in which six different statistical features (Signal Mean (SM), Skewness (SK), Kurtosis (KR), Standard Deviation (SD), Signal Peak (SP), and Signal Variance (SV)) are obtained in the time domain and 13 Mel Frequency Cepstral Coefficients (MFCC) features are obtained from the frequency domain. As per literature review, MFCC has never been used as feature towards classification of fNIRS signal, which is a novel contribution towards this study. Separate Classification analysis is performed on each domain features. We were able to compare, differentiate and distinguish the brain signal activities captured while performing four different tasks using three different classifiers i.e. Linear Discriminant Analysis (LDA), Support Vector Machine (SVM) and K Nearest Neighbor (KNN). The average classification accuracy of 90.54% is achieved from K Nearest Neighbors (KNN) using the time domain features and accuracy achieved from Support Vector Machine (SVM) using the frequency domain features is 95.7%. Comparison with benchmark study shows the efficiency of MFCC as suitable features for improved classification accuracy.

[1]  Muhammad Jawad Khan,et al.  Enhanced Accuracy for Multiclass Mental Workload Detection Using Long Short-Term Memory for Brain–Computer Interface , 2020, Frontiers in Neuroscience.

[2]  Andrew B Schwartz,et al.  Cortical neural prosthetics. , 2004, Annual review of neuroscience.

[3]  Noman Naseer,et al.  fNIRS-based Neurorobotic Interface for gait rehabilitation , 2018, Journal of NeuroEngineering and Rehabilitation.

[4]  N. V. Thakor,et al.  Translating the Brain-Machine Interface , 2013, Science Translational Medicine.

[5]  Sungho Tak,et al.  Statistical analysis of fNIRS data: A comprehensive review , 2014, NeuroImage.

[6]  Shuzhi Sam Ge,et al.  Detection of event-related hemodynamic response to neuroactivation by dynamic modeling of brain activity , 2012, NeuroImage.

[7]  S. Arridge,et al.  Estimation of optical pathlength through tissue from direct time of flight measurement , 1988 .

[8]  A. Villringer,et al.  Near infrared spectroscopy (NIRS): A new tool to study hemodynamic changes during activation of brain function in human adults , 1993, Neuroscience Letters.

[9]  Keum-Shik Hong,et al.  Classification of functional near-infrared spectroscopy signals corresponding to the right- and left-wrist motor imagery for development of a brain–computer interface , 2013, Neuroscience Letters.

[10]  Keum-Shik Hong,et al.  Feature Extraction and Classification Methods for Hybrid fNIRS-EEG Brain-Computer Interfaces , 2018, Front. Hum. Neurosci..

[11]  Noman Naseer,et al.  Enhancing Classification Performance of Functional Near-Infrared Spectroscopy- Brain–Computer Interface Using Adaptive Estimation of General Linear Model Coefficients , 2017, Front. Neurorobot..

[12]  Miguel A. L. Nicolelis,et al.  Brain–machine interfaces: past, present and future , 2006, Trends in Neurosciences.

[13]  K. Hong,et al.  Determining Optimal Feature-Combination for LDA Classification of Functional Near-Infrared Spectroscopy Signals in Brain-Computer Interface Application , 2016, Front. Hum. Neurosci..

[14]  张国亮,et al.  Comparison of Different Implementations of MFCC , 2001 .

[15]  Keum Shik Hong,et al.  Reduction of Delay in Detecting Initial Dips from Functional Near-Infrared Spectroscopy Signals Using Vector-Based Phase Analysis , 2016, Int. J. Neural Syst..

[16]  Hasan Onur Keles,et al.  Hybrid EEG-fNIRS Asynchronous Brain-Computer Interface for Multiple Motor Tasks , 2016, PloS one.

[17]  F. Jöbsis Noninvasive, infrared monitoring of cerebral and myocardial oxygen sufficiency and circulatory parameters. , 1977, Science.

[18]  Martin Wolf,et al.  Reproducibility and sensitivity of detecting brain activity by simultaneous electroencephalography and near-infrared spectroscopy , 2012, Experimental Brain Research.

[19]  Y. Kim,et al.  Classification of prefrontal and motor cortex signals for three-class fNIRS–BCI , 2015, Neuroscience Letters.

[20]  David R Busch,et al.  Modified Beer-Lambert law for blood flow. , 2014, Biomedical optics express.

[21]  Noman Naseer,et al.  Optimal feature selection from fNIRS signals using genetic algorithms for BCI , 2017, Neuroscience Letters.

[22]  G. Pfurtscheller,et al.  Brain-Computer Interfaces for Communication and Control. , 2011, Communications of the ACM.

[23]  Joseph Picone,et al.  Signal modeling techniques in speech recognition , 1993, Proc. IEEE.

[24]  Jichai Jeong,et al.  Dataset for EEG + NIRS Single-Trial Classification , 2022 .

[25]  Sarah D Power,et al.  Classification of prefrontal activity due to mental arithmetic and music imagery using hidden Markov models and frequency domain near-infrared spectroscopy , 2010, Journal of neural engineering.

[26]  Jinung An,et al.  Classification of frontal cortex haemodynamic responses during cognitive tasks using wavelet transforms and machine learning algorithms. , 2012, Medical engineering & physics.

[27]  Keum-Shik Hong,et al.  Detection and classification of three-class initial dips from prefrontal cortex. , 2017, Biomedical optics express.

[28]  G. Pfurtscheller,et al.  An SSVEP BCI to Control a Hand Orthosis for Persons With Tetraplegia , 2011, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[29]  Martin Wolf,et al.  Single-trial classification of motor imagery differing in task complexity: a functional near-infrared spectroscopy study , 2011, Journal of NeuroEngineering and Rehabilitation.

[30]  Nguyen Thanh Hai,et al.  Temporal hemodynamic classification of two hands tapping using functional near—infrared spectroscopy , 2013, Front. Hum. Neurosci..

[31]  Keum Shik Hong,et al.  Hybrid Brain–Computer Interface Techniques for Improved Classification Accuracy and Increased Number of Commands: A Review , 2017, Front. Neurorobot..

[32]  J. Wolpaw,et al.  Brain-computer communication: unlocking the locked in. , 2001, Psychological bulletin.

[33]  Masashi Kiguchi,et al.  A Communication Means for Totally Locked-in ALS Patients Based on Changes in Cerebral Blood Volume Measured with Near-Infrared Light , 2007, IEICE Trans. Inf. Syst..

[34]  Sungho Tak,et al.  NIRS-SPM: Statistical parametric mapping for near-infrared spectroscopy , 2009, NeuroImage.

[35]  Christopher J. C. Burges,et al.  A Tutorial on Support Vector Machines for Pattern Recognition , 1998, Data Mining and Knowledge Discovery.

[36]  Jonathan R Wolpaw,et al.  Control of a two-dimensional movement signal by a noninvasive brain-computer interface in humans. , 2004, Proceedings of the National Academy of Sciences of the United States of America.

[37]  Keum-Shik Hong,et al.  fNIRS-based brain-computer interfaces: a review , 2015, Front. Hum. Neurosci..

[38]  Theodore J Huppert,et al.  Commentary on the statistical properties of noise and its implication on general linear models in functional near-infrared spectroscopy. , 2016, Neurophotonics.

[39]  Yunfa Fu,et al.  A hybrid BCI based on EEG and fNIRS signals improves the performance of decoding motor imagery of both force and speed of hand clenching , 2015, Journal of neural engineering.

[40]  K. Sreenivasa Rao,et al.  Speech Recognition Using Articulatory and Excitation Source Features , 2017 .

[41]  Keum-Shik Hong,et al.  Reduction of physiological effects in fNIRS waveforms for efficient brain-state decoding , 2014, Neuroscience Letters.

[42]  David A. Boas,et al.  Motion artifacts in functional near-infrared spectroscopy: A comparison of motion correction techniques applied to real cognitive data , 2014, NeuroImage.

[43]  Kenneth M Boyd,et al.  The revision of the Declaration of Helsinki: past, present and future. , 2004, British journal of clinical pharmacology.

[44]  David A. Boas,et al.  The utility of near-infrared spectroscopy in the regression of low-frequency physiological noise from functional magnetic resonance imaging data , 2012, NeuroImage.

[45]  Keum-Shik Hong,et al.  Passive BCI based on drowsiness detection: an fNIRS study. , 2015, Biomedical optics express.

[46]  Jaime Gómez Gil,et al.  Brain Computer Interfaces, a Review , 2012, Sensors.