Abstract
In this paper, we propose a novel vigilance enhancement method based on audio stimulation of pure tone at 250 Hz. We induced two different levels of vigilance state; vigilance decrement (VD) and vigilance enhancement (VE). The VD state was induced by performing a modified version of the Stroop Color-Word Task (SCWT) for approximately 45 minutes. Likewise, the VE state was induced by incorporating audio stimulation of 250 Hz into the SCWT for 45 minutes. We assessed the levels of vigilance on 20 healthy subjects by utilizing Electroencephalogram (EEG) signals and machine learning. The EEG signals were analyzed using four types of entropies; Approximate Entropy (AE), Sample Entropy (SE), Fuzzy Entropy (FE), and Differential Entropy (DE). We then quantified vigilance levels using statistical analysis and support vector machines (SVM) classifier. We found that the proposed VE method has significantly reduced the reaction time (RT) by 44% and improved the accuracy of target detection by 25%, (p <; 0.001) compared to VD state. Besides, we found that 30 min of audio stimulation has reduced the RT by 32% from the beginning to the end of VE phase of the experiment. The entropy measures show that the temporal profile of the EEG signals has significantly increased with VE. The classification results showed that SVM technique with DE features across all frequency bands can detect VE levels with accuracy varying between (92.10± 02.24)% to (98.32± 01.14)%, sensitivity of (92.50± 02.33)% to (98.66± 01.00)%, and specificity of (91.70± 02.32)% to (97.99± 01.05)%. Results also showed that the classification performance using DE has outperformed the other entropy measures by an average of +8.07%. Our results demonstrate the effectiveness of the proposed 250 Hz audio stimulation method in improving vigilance level and suggest using it for future cognitive enhancement studies.