IQ estimation by means of EEG-fNIRS recordings during a logical-mathematical intelligence test

Intelligence differences of individuals are attributed to the structural and functional differences of the brain. Neural processing operations of the human brain vary according to the difficulty level of the problem and the intelligence level of individuals. In this study, we used a bimodal system consisting of functional Near-Infrared Spectroscopy (fNIRS) and Electroencephalogram (EEG) to investigate these inter-individual differences. A continuous wave 32-channel fNIRS from OxyMonfNIRS device (Artinis) and 19-channel EEG from (g.tec's company) were utilized to study the oxygenation procedure as well as the electrical activity of the brain when doing the problems of Raven's Progressive Matrix (RPM) intelligence test. We used this information to estimate the Intelligence Quotient (IQ) of the individual without performing a complete logical-mathematical intelligence test in a long-time period and examining the answers of people to the questions. After EEG preprocessing, different features including Higuchi's fractal dimension, Shannon entropy values from wavelet transform coefficients, and average power of frequency sub-bands were extracted. Clean fNIRS signals were also used to compute features such as slope, mean, variance, kurtosis, skewness, and peak. Then dimension reduction algorithms such as Linear Discriminant Analysis (LDA) and Principal Component Analysis (PCA) were applied to select an effective feature set from fNIRS and EEG in order to improve the IQ estimation process. We utilized two regression methods, i.e., Linear Regression (LR) and Support Vector Regression (SVR), to extract optimum models for the IQ determination. The best regression models based on fNIRS-EEG and fNIRS presented 3.093% and 3.690% relative error for 11 subjects, respectively.

[1]  R. Gur,et al.  Development of Abbreviated Nine-Item Forms of the Raven’s Standard Progressive Matrices Test , 2012, Assessment.

[2]  Eric O. Postma,et al.  Dimensionality Reduction: A Comparative Review , 2008 .

[3]  H. Jasper,et al.  The ten-twenty electrode system of the International Federation. The International Federation of Clinical Neurophysiology. , 1999, Electroencephalography and clinical neurophysiology. Supplement.

[4]  Xiaorong Gao,et al.  Spectra-temporal patterns underlying mental addition: An ERP and ERD/ERS study , 2010, Neuroscience Letters.

[5]  Maithilee Kunda,et al.  Taking a Look (Literally!) at the Raven’s Intelligence Test: Two Visual Solution Strategies , 2010 .

[6]  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..

[7]  Ulrike Basten,et al.  Intelligence is differentially related to neural effort in the task-positive and the task-negative brain network , 2013 .

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

[9]  Vikramvarun Kannan Adikarapatti.  OPTIMAL EEG CHANNELS AND RHYTHM SELECTION FOR TASK CLASSIFICATION , 2007 .

[10]  Ulrike Basten,et al.  Where smart brains are different: A quantitative meta-analysis of functional and structural brain imaging studies on intelligence , 2015 .

[11]  Richard Mankiewicz.  The Story of Mathematics , 2001 .

[12]  M. HernánDíaz,et al.  Inter-channel Correlation in the EEG Activity During a Cognitive Problem Solving Task with an Increasing Difficulty Questions Progression , 2015, ITQM.

[13]  G. Domino,et al.  Psychological Testing: An Introduction , 1999 .

[14]  Minghui Meng,et al.  Application of Support Vector Machines to a Small-Sample Prediction , 2015 .

[15]  Christopher A. Paynter,et al.  Problem-solving without awareness: An ERP investigation , 2010, Neuropsychologia.

[16]  Cornelis J. Stam,et al.  Neural networks involved in mathematical thinking: evidence from linear and non-linear analysis of electroencephalographic activity , 2005, Neuroscience Letters.

[17]  M. Balconi,et al.  Motor planning and performance in transitive and intransitive gesture execution and imagination: Does EEG (RP) activity predict hemodynamic (fNIRS) response? , 2017, Neuroscience Letters.

[18]  Giorgio Roffo,et al.  Feature Selection Library (MATLAB Toolbox) , 2016, 1607.01327.

[19]  M. Balconi,et al.  What hemodynamic (fNIRS), electrophysiological (EEG) and autonomic integrated measures can tell us about emotional processing , 2015, Brain and Cognition.

[20]  Farshad Almasganj,et al.  Support vector wavelet adaptation for pathological voice assessment , 2011, Comput. Biol. Medicine.

[21]  A. Mognon,et al.  ADJUST: An automatic EEG artifact detector based on the joint use of spatial and temporal features. , 2011, Psychophysiology.

[22]  Dong Ming,et al.  How Physical Activities Affect Mental Fatigue Based on EEG Energy, Connectivity, and Complexity , 2018, Front. Neurol..

[23]  S. Setarehdan,et al.  Functional connectivity of the PFC via partial correlation , 2016 .

[24]  M. I. Núñez-Peña.  Effects of training on the arithmetic problem-size effect: an event-related potential study , 2008, Experimental Brain Research.

[25]  Amitash Ojha,et al.  Difference in brain activation patterns of individuals with high and low intelligence in linguistic and visuo-spatial tasks: An EEG study , 2017 .

[26]  Hanli Liu,et al.  Functional near-infrared spectroscopy to investigate hemodynamic responses to deception in the prefrontal cortex , 2009, Brain Research.

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

[28]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[29]  Ilias Tachtsidis,et al.  Current Status and Issues Regarding Pre-processing of fNIRS Neuroimaging Data: An Investigation of Diverse Signal Filtering Methods Within a General Linear Model Framework , 2019, Front. Hum. Neurosci..

[30]  Robert J. Sternberg,et al.  Encyclopedia of human intelligence , 1994 .

[31]  David J. Bartholomew,et al.  Measuring Intelligence: Facts and Fallacies , 2004 .

[32]  N. Phillips,et al.  Aging and sequential modulations of poorer strategy effects: An EEG study in arithmetic problem solving , 2016, Brain Research.

[33]  J. Raven.  The Raven's Progressive Matrices: Change and Stability over Culture and Time , 2000, Cognitive Psychology.

[34]  Salvatore Vitabile,et al.  Feature Dimensionality Reduction for Mammographic Report Classification , 2016, Resource Management for Big Data Platforms.

[35]  Bert De Smedt,et al.  Oscillatory EEG correlates of arithmetic strategy use in addition and subtraction , 2009, Experimental Brain Research.

[36]  Chaozhe Zhu,et al.  Use of fNIRS to assess resting state functional connectivity , 2010, Journal of Neuroscience Methods.

[37]  Nigel H. Lovell,et al.  Estimating cognitive workload using wavelet entropy-based features during an arithmetic task , 2013, Comput. Biol. Medicine.

[38]  M. HernánDíaz,et al.  Identifying Problem Solving Strategies for Learning Styles in Engineering Students Subjected to Intelligence Test and EEG Monitoring , 2015, ITQM.

[39]  Srdjan Kesic,et al.  Application of Higuchi's fractal dimension from basic to clinical neurophysiology: A review , 2016, Comput. Methods Programs Biomed..

[40]  F. Wallois,et al.  Usefulness of simultaneous EEG–NIRS recording in language studies , 2012, Brain and Language.

[41]  David A. Freedman,et al.  Statistical Models: Theory and Practice: References , 2005 .

[42]  Norbert Jaušovec,et al.  Differences in Cognitive Processes Between Gifted, Intelligent, Creative, and Average Individuals While Solving Complex Problems: An EEG Study , 2000 .

[43]  Yasser Shekofteh,et al.  Improvement of automatic speech recognition systems via nonlinear dynamical features evaluated from the recurrence plot of speech signals , 2017, Comput. Electr. Eng..

[44]  R. Lyman Ott.,et al.  An introduction to statistical methods and data analysis , 1977 .

[45]  Anthony J. Yezzi,et al.  Active contour algorithm with discriminant analysis for delineating tumors in positron emission tomography , 2019, Artif. Intell. Medicine.

[46]  Keum-Shik Hong,et al.  State-space models of impulse hemodynamic responses over motor, somatosensory, and visual cortices. , 2014, Biomedical optics express.

[47]  Jesus Gonzalez-Trejo,et al.  Fractal dimension algorithms and their application to time series associated with natural phenomena , 2013 .

[48]  M. Buchsbaum,et al.  Intelligence and changes in regional cerebral glucose metabolic rate following learning , 1992 .

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

[50]  M. HernánDíaz,et al.  Order and Chaos in the Brain: Fractal Time Series Analysis of the EEG Activity During a Cognitive Problem Solving Task , 2015, ITQM.

[51]  Sri Ramakrishna,et al.  FEATURE SELECTION METHODS AND ALGORITHMS , 2011 .

[52]  Yunqian Ma,et al.  Selection of Meta-parameters for Support Vector Regression , 2002, ICANN.

[53]  P. D. Bahirgonde,et al.  Feature Extraction of EEG Signal using Wavelet Transform , 2015 .

[54]  P. A. Bromiley,et al.  Shannon Entropy, Renyi Entropy, and Information , 2004 .