Hjorth Descriptor as Feature Extraction for Classification of Familiarity in EEG Signal

Deficiency in identifying human emotional stages occurs in most of the existing contemporary Human-Computer Interactions (HCI) systems. There are vast areas of the human stages that can be identified. One of them is the stage when a human feels familiar. Electroencephalogram (EEG) signal can be used to detect human affective stage in familiarity category. This research classifies familiarity in EEG signal using data from DEAP: A Database for Emotion Analysis Using Physiological Signals. The signal feature was extracted using Hjorth Descriptor producing three parameters. The parameters then fed to the Multilayer Perceptron as the classifier. The best accuracy achieved was 92.85% using three features combination, with 2.132 seconds of computation time.

[1]  Jessie J. Peissig,et al.  The Effects of Familiarity on Genuine Emotion Recognition , 2009 .

[2]  Inung Wijayanto,et al.  Multilevel Wavelet Packet Entropy and Support Vector Machine for Epileptic EEG Classification , 2018, 2018 4th International Conference on Science and Technology (ICST).

[3]  J. Satheesh Kumar,et al.  Analysis of Electroencephalography (EEG) Signals and Its Categorization–A Study , 2012 .

[4]  Sugondo Hadiyoso,et al.  Sample Entropy on Multidistance Signal Level Difference for Epileptic EEG Classification , 2018, TheScientificWorldJournal.

[5]  Thierry Pun,et al.  DEAP: A Database for Emotion Analysis ;Using Physiological Signals , 2012, IEEE Transactions on Affective Computing.

[6]  Jeffrey A Bonnell.  Implementation of a New Sigmoid Function in Backpropagation Neural Networks. , 2011 .

[7]  S. Anitha,et al.  Application of a radial basis function neural network for diagnosis of diabetes mellitus , 2006 .

[8]  Sugondo Hadiyoso,et al.  Mild Cognitive Impairment Classification using Hjorth Descriptor Based on EEG Signal , 2018, 2018 International Conference on Control, Electronics, Renewable Energy and Communications (ICCEREC).

[9]  Masayuki Numao,et al.  Familiarity effects in EEG-based emotion recognition , 2016, Brain Informatics.

[10]  Phil Turner,et al.  Being-with: A study of familiarity , 2008, Interact. Comput..

[11]  Sugondo Hadiyoso,et al.  ECG signal classification using Hjorth Descriptor , 2015, 2015 International Conference on Automation, Cognitive Science, Optics, Micro Electro-Mechanical System, and Information Technology (ICACOMIT).

[12]  E. Brattico,et al.  Music and Emotions in the Brain: Familiarity Matters , 2011, PloS one.

[13]  Yu-Ri Lee,et al.  A Novel EEG Feature Extraction Method Using Hjorth Parameter , 2014 .

[14]  Ahmad Setiadi.  PENERAPAN ALGORITMA MULTILAYER PERCEPTRON UNTUK DETEKSI DINI PENYAKIT DIABETES , 2012 .

[15]  Carlo Vercellis,et al.  Business Intelligence: Data Mining and Optimization for Decision Making , 2009 .

[16]  Areej Al-Wabil,et al.  Review and Classification of Emotion Recognition Based on EEG Brain-Computer Interface System Research: A Systematic Review , 2017 .

[17]  B. Hjorth.  EEG analysis based on time domain properties. , 1970, Electroencephalography and clinical neurophysiology.

[18]  S. R. Khot,et al.  Emotion recognition using Principal Component Analysis with Singular Value Decomposition , 2014, 2014 International Conference on Electronics and Communication Systems (ICECS).