Analysis of Viewer EEG Data to Determine Categorization of Short Video Clip

This paper discusses some very early research results for a Machine Learning System using Brain-Machine Interface data to categorize whether a viewer likes a short video. Prior art teaches that Machine Learning can be used to categorize alertness of volunteers using Brain-Machine Interface Electroencephalogram (EEG) data. Also, published research has described how EEG data can be correlated to the ability of participants to remember television commercials. This paper advances this research one step further. The paper examines whether or not Machine Learning can tell whether or not a participant likes a short YouTube video using only EEG data. The research is in the preliminary stage (two subjects thus far), but early results are promising. Also discussed in the paper is information regarding commercialization of the invention which is of interest to many universities. A provisional patent application was filed and a critique was gathered from executives from a famous advertising agency regarding commercialization of the invention for Neuromarketing. These executives provided valuable detailed feedback regarding pros and cons of different commercialization possibilities. Presented in the paper are the results of these discussions including specific areas where the research would and would not likely yield a successful commercial product.

[1]  Fabrizio De Vico Fallani,et al.  Structure of the cortical networks during successful memory encoding in TV commercials , 2008, Clinical Neurophysiology.

[2]  R. Palaniappan,et al.  Utilizing Gamma Band to Improve Mental Task Based Brain-Computer Interface Design , 2006, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[3]  R. Srinivasan,et al.  Removal of ocular artifacts from EEG using an efficient neural network based adaptive filtering technique , 1999, IEEE Signal Processing Letters.

[4]  Qi Li,et al.  Principal feature classification , 1997, IEEE Trans. Neural Networks.

[5]  Osman Erogul,et al.  Automatic recognition of vigilance state by using a wavelet-based artificial neural network , 2005, Neural Computing & Applications.

[6]  T. Sejnowski,et al.  Estimating alertness from the EEG power spectrum , 1997, IEEE Transactions on Biomedical Engineering.

[7]  K. Oguri,et al.  Individualized drowsiness detection during driving by pulse wave analysis with neural network , 2005, Proceedings. 2005 IEEE Intelligent Transportation Systems, 2005..

[8]  Sneh Anand,et al.  Classification of Five Mental Tasks from EEG Data using Neural Network Based on Principal Component Analysis , 2010 .

[9]  Anna Anund,et al.  Detecting Driver Sleepiness Using Optimized Nonlinear Combinations of Sleepiness Indicators , 2011, IEEE Transactions on Intelligent Transportation Systems.

[10]  Christine L. Lisetti,et al.  Using Noninvasive Wearable Computers to Recognize Human Emotions from Physiological Signals , 2004, EURASIP J. Adv. Signal Process..

[11]  B. J. Wilson,et al.  Alertness monitor using neural networks for EEG analysis , 2000, Neural Networks for Signal Processing X. Proceedings of the 2000 IEEE Signal Processing Society Workshop (Cat. No.00TH8501).

[12]  Amit Konar,et al.  Correlation between stimulated emotion extracted from EEG and its manifestation on facial expression , 2009, 2009 IEEE International Conference on Systems, Man and Cybernetics.

[13]  Bernard Widrow,et al.  The basic ideas in neural networks , 1994, CACM.

[14]  Qinyu Zhang,et al.  Application of neural networks to brain dynamics identification by EEG , 2002, 7th International Conference on Control, Automation, Robotics and Vision, 2002. ICARCV 2002..