Multi-Level Attention Recognition of EEG Based on Feature Selection

Abstract

In view of the fact that current attention-recognition studies are mostly single-level-based, this paper proposes a multi-level attention-recognition method based on feature selection. Four experimental scenarios are designed to induce high, medium, low, and non-externally directed attention states. A total of 10 features are extracted from 10 electroencephalogram (EEG) channels, respectively, including time-domain measurements, sample entropy, and frequency band energy ratios. Based on all extracted features, an 88.7% recognition accuracy is achieved when classifying the four different attention states using the support vector machine (SVM) classifier. Afterwards, the sequence-forward-selection method is employed to select the optimal feature subset with high discriminating power from the original feature set. Experimental results show that the classification accuracy can be improved to 94.1% using the filtered feature subsets. In addition, the average recognition accuracy based on single subject classification is improved from 90.03% to 92.00%. The promising results indicate the effectiveness of feature selection in improving the performance of multi-level attention-recognition tasks.

Enhancement of Visual Attention by Color Revealed Using Electroencephalography

“…Alpha waves are predominant in a calm state and are mainly detected in the occipital and parietal lobes [9]. Finally, beta waves are more prominent during excitement and are mainly distributed in the frontal and central areas [1]. A relationship between visual attention accuracy and increased EEG beta frequency power in the occipital region has been reported [22].…”

“…Attention is a fundamental psychological feature that directs our mental effort toward specific objects, accompanying processes such as memory, reasoning, and imagination [1]. There are five attentional components: focused, sustained, selective, alternating, and divided [2].…”

“…Electroencephalogram (EEG) signals can measure attention levels [1]. An EEG records nerve activity in the brain through electrodes placed on the scalp, and changes in activity correlate to changes in mental state, emotion, and cognitive activity [5] [6].…”

“…Physiological measures using EEGs are considered accurate [7] and reliable [8]. However, few studies have assessed multilevel attention classification based on EEG, and feature screening has rarely been considered [1].…”

A Bio-Inspired Chaos Sensor Model Based on the Perceptron Neural Network: Machine Learning Concept and Application for Computational Neuro-Science

“…On the other hand, a mild form of ECG chaos may indicate congestive heart failure [ 11 ]. Studying the orderliness of the ensemble functioning of brain neurons by measuring electroencephalograms makes it possible to: identify pathological conditions (neurodegenerative diseases, epilepsy) [ 12 , 13 , 14 ]; determine the level of concentration and mental fatigue [ 15 , 16 , 17 ]; evaluate the emotional state [ 18 , 19 ]; and produce biometric identification of a person [ 20 , 21 ].…”