EEG-Analysis for Classification of Touch-Induced Affection by Type-2 Fuzzy Sets

The paper aims at classifying the brain response to touch-induced affection aroused in human subjects into four classes: love, fondness, devotion and respect using a novel vertical slice based General Type-2 Fuzzy classifier. The novelty of research here lies in the design of vertical slice based General Type-2 Fuzzy Classifier, capable of classifying finer changes in the brain activation patterns due to changes in the touch nourishment on a subject by different people, including spouse, children, graces of the Almighty and parents. Experiments undertaken confirm that for most of the subjects the above four classes are prominent in the brain activation patterns. The frontal lobe is more activated in devotion and respect, whereas temporal lobe is more activated in fondness and love. The General Type-2 fuzzy classifier designed for classification of four affection classes yield high classification accuracy over 98 % in comparison to existing type-l fuzzy and other classifies. The proposed scheme of touch-induced affection classification can be interestingly applied to measure subjective sensitivity of healthy and psychologically disabled people.

[1]  Amit Konar,et al.  EEG classification to determine the degree of pleasure levels in touch-perception of human subjects , 2015, 2015 International Joint Conference on Neural Networks (IJCNN).

[2]  Jerry M. Mendel,et al.  Enhanced Karnik--Mendel Algorithms , 2009, IEEE Transactions on Fuzzy Systems.

[3]  Jerry M. Mendel,et al.  General Type-2 Fuzzy Logic Systems Made Simple: A Tutorial , 2014, IEEE Transactions on Fuzzy Systems.

[4]  Francesco Bianchi-Demicheli,et al.  Social neuroscience of love. , 2012 .

[5]  Amit Konar,et al.  Particle Swarm Optimization and Differential Evolution Algorithms: Technical Analysis, Applications and Hybridization Perspectives , 2008, Advances of Computational Intelligence in Industrial Systems.

[6]  T. Martin McGinnity,et al.  An approach for on-line extraction of fuzzy rules using a self-organising fuzzy neural network , 2005, Fuzzy Sets Syst..

[7]  Vittorio Gallese,et al.  Touching moments: desire modulates the neural anticipation of active romantic caress , 2014, Front. Behav. Neurosci..

[8]  Amit Konar,et al.  EEG Analysis for Cognitive Failure Detection in Driving Using Type-2 Fuzzy Classifiers , 2017, IEEE Transactions on Emerging Topics in Computational Intelligence.

[9]  C. Darwin,et al.  The Expression of the Emotions in Man and Animals: MEANS OF EXPRESSION IN ANIMALS , 2009 .

[10]  P. Comon,et al.  Ica: a potential tool for bci systems , 2008, IEEE Signal Processing Magazine.

[11]  J Dargahi,et al.  Human tactile perception as a standard for artificial tactile sensing—a review , 2004, The international journal of medical robotics + computer assisted surgery : MRCAS.

[12]  T.M. McGinnity,et al.  Comparative Analysis of Spectral Approaches to Feature Extraction for EEG-Based Motor Imagery Classification , 2008, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[13]  Xu Kejia,et al.  Reweighting Recognition Using Modified Kernel Principal Component Analysis via Manifold Learning , 2012 .

[14]  Kai Keng Ang,et al.  ERNN: A Biologically Inspired Feedforward Neural Network to Discriminate Emotion From EEG Signal , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[15]  Amit Konar,et al.  Emotional Intelligence: A Cybernetic Approach , 2009, Studies in Computational Intelligence.

[16]  Hafizah Husain,et al.  Fuzzy model of dominance emotions in affective computing , 2014, Neural Computing and Applications.

[17]  William Perrizo,et al.  Comprehensive vertical sample-based KNN/LSVM classification for gene expression analysis , 2004, J. Biomed. Informatics.

[18]  R. Pascual-Marqui,et al.  Functional connectivity assessed by resting state EEG correlates with cognitive decline of Alzheimer’s disease – An eLORETA study , 2016, Clinical Neurophysiology.

[19]  Amit Konar,et al.  General and Interval Type-2 Fuzzy Face-Space Approach to Emotion Recognition , 2013, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[20]  Hani Hagras,et al.  Toward General Type-2 Fuzzy Logic Systems Based on zSlices , 2010, IEEE Transactions on Fuzzy Systems.

[21]  Amit Konar,et al.  Improving particle swarm optimization with differentially perturbed velocity , 2005, GECCO '05.

[22]  Amit Konar,et al.  EEG-based mind driven type writer by fuzzy radial basis function neural classifier , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[23]  Amit Konar,et al.  EEG Analysis for Olfactory Perceptual-Ability Measurement Using a Recurrent Neural Classifier , 2014, IEEE Transactions on Human-Machine Systems.

[24]  Puja Padiya,et al.  Feature Selection Based Hybrid Anomaly Intrusion Detection System Using K Means and RBF Kernel Function , 2015 .

[25]  Amit Konar,et al.  Emotion Recognition: A Pattern Analysis Approach , 2015 .

[26]  Amir Hussain,et al.  Applications of Deep Learning and Reinforcement Learning to Biological Data , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[27]  D. B. Rane,et al.  Image Compression Using Discrete Wavelet Transform , 2013 .

[28]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[29]  Catello Vollono,et al.  Modification of EEG functional connectivity and EEG power spectra in overweight and obese patients with food addiction: An eLORETA study , 2014, Brain Imaging and Behavior.