Theta-Beta Ratios Are Prominent EEG Features for Visual Tracking Tasks

Visual tracking is a vital task in various control systems such as air traffic control. Analysing mental processing indicators during such tasks can lead to a better understanding of changes in the cognitive state of human operators. In this paper, we conducted an electroencephalography experiment for simulated visual tracking tasks using 10 subjects. A descriptive model based on decision trees is adopted for electroencephalography feature selection. Our analysis methodology involved four steps. First, we generated a large pool of features. Second, we formed a descriptive decision tree for each subject. Third, we contrasted the features found among all subjects’ decision trees to identify those commonly used features, which we then ranked. Fourth, we compared the classification accuracy when using the selected features against the whole dataset and unselected features. Results showed that Theta-Beta Ratio for different channels contributed to approximately 90% of the highly rated selected features. These features also yielded better generalization and classification accuracy. This finding indicates that Theta-Beta Ratios can be used as an effective cognitive indicator for visual tracking tasks.

[1]  Julien Penders,et al.  Wearable, Wireless EEG Solutions in Daily Life Applications: What are we Missing? , 2015, IEEE Journal of Biomedical and Health Informatics.

[2]  M. Teplan.  FUNDAMENTALS OF EEG MEASUREMENT , 2002 .

[3]  Dimitrios Gunopulos,et al.  Feature selection for the naive bayesian classifier using decision trees , 2003, Appl. Artif. Intell..

[4]  Kewei Cheng,et al.  Feature Selection , 2016, ACM Comput. Surv..

[5]  Ney Lemke,et al.  Analysis of EEG Sleep Spindle Parameters from Apnea Patients Using Massive Computing and Decision Tree , 2014 .

[6]  Dylan D. Schmorrow,et al.  Augmented Cognition: An Overview , 2009 .

[7]  H WittenIan,et al.  The WEKA data mining software , 2009 .

[8]  D. Montgomery,et al.  Single Channel QEEG Amplitudes in a Bright, Normal Young Adult Sample , 1998 .

[9]  S. Nickolas,et al.  Feature Selection Using Decision Tree Induction in Class level Metrics Dataset for Software Defect Predictions , 2010 .

[10]  Norbert Jankowski,et al.  Feature selection with decision tree criterion , 2005, Fifth International Conference on Hybrid Intelligent Systems (HIS'05).

[11]  M Congedo,et al.  A review of classification algorithms for EEG-based brain–computer interfaces , 2007, Journal of neural engineering.

[12]  Wei Ma,et al.  EEG feature selection method based on decision tree. , 2015, Bio-medical materials and engineering.

[13]  K. I. Ramachandran,et al.  Feature selection using Decision Tree and classification through Proximal Support Vector Machine for fault diagnostics of roller bearing , 2007 .

[14]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.

[15]  Hussein A. Abbass,et al.  Augmented Cognition using Real-time EEG-based Adaptive Strategies for Air Traffic Control , 2014 .

[16]  Onder Aydemir,et al.  Decision tree structure based classification of EEG signals recorded during two dimensional cursor movement imagery , 2014, Journal of Neuroscience Methods.

[17]  Song Xing,et al.  Reading the mind: The potential of electroencephalography in brain computer interfaces , 2012, 2012 19th International Conference on Mechatronics and Machine Vision in Practice (M2VIP).