EEG-Based Age and Gender Recognition Using Tensor Decomposition and Speech Features

Extracting age and gender information from EEG data has not been investigated. This information is useful in building automatic systems that can classify a person into gender or age groups based on EEG characteristics of that person, index EEG data for searching, identify or verify a person, and improve performance of brain-computer interface systems. In this paper, we propose a framework based on PARAFAC and SVM that can automatically classify age and gender using EEG data. We also propose a method using N-PLS and SVM to improve the classification rate. Experimental results for the proposed method are presented.

[1]  Tamara G. Kolda,et al.  Tensor Decompositions and Applications , 2009, SIAM Rev..

[2]  G. Lightbody,et al.  Speech recognition features for EEG signal description in detection of neonatal seizures , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[3]  Saeid Sanei,et al.  Parallel space-time-frequency decomposition of EEG signals for brain computer interfacing , 2006, 2006 14th European Signal Processing Conference.

[4]  Rasmus Bro,et al.  Multiway analysis of epilepsy tensors , 2007, ISMB/ECCB.

[5]  O. Rosso,et al.  The Australian EEG Database , 2005, Clinical EEG and neuroscience.

[6]  Florian Roemer,et al.  Multi-dimensional space-time-frequency component analysis of event related EEG data using closed-form PARAFAC , 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

[7]  Fumikazu Miwakeichi,et al.  Concurrent EEG/fMRI analysis by multiway Partial Least Squares , 2004, NeuroImage.

[8]  Pierluigi Amadori,et al.  Macroprolactinemia: Predictability on clinical basis and detection by PEG precipitation with two different immunometric methods , 2003, Journal of endocrinological investigation.

[9]  Björn Schuller,et al.  Opensmile: the munich versatile and fast open-source audio feature extractor , 2010, ACM Multimedia.

[10]  William P. Marnane,et al.  EEG Signal Description with Spectral-Envelope-Based Speech Recognition Features for Detection of Neonatal Seizures , 2011, IEEE Transactions on Information Technology in Biomedicine.

[11]  Patrick Dupont,et al.  Canonical decomposition of ictal scalp EEG reliably detects the seizure onset zone , 2007, NeuroImage.

[12]  Lars Kai Hansen,et al.  Parallel Factor Analysis as an exploratory tool for wavelet transformed event-related EEG , 2006, NeuroImage.

[13]  Jr. J.P. Campbell,et al.  Speaker recognition: a tutorial , 1997, Proc. IEEE.

[14]  Saeid Sanei,et al.  EEG signal processing , 2000, Clinical Neurophysiology.

[15]  Robert J Barry,et al.  Age and sex effects in the EEG: development of the normal child , 2001, Clinical Neurophysiology.

[16]  T. Gasser,et al.  Development of the EEG of school-age children and adolescents. I. Analysis of band power. , 1988, Electroencephalography and clinical neurophysiology.

[17]  T H Monk,et al.  The effects of age and gender on sleep EEG power spectral density in the middle years of life (ages 20-60 years old). , 2001, Psychophysiology.

[18]  Rasmus Bro,et al.  Multi-way Analysis with Applications in the Chemical Sciences , 2004 .

[19]  S. Huffel,et al.  Neonatal seizure localization using PARAFAC decomposition , 2009, Clinical Neurophysiology.