Improved Cognitive Vigilance Assessment after Artifact Reduction with Wavelet Independent Component Analysis

• Main Authors: Al-Nashash, H. (Author), Al-Shargie, F. (Author), Farha, N.A (Author), Tariq, U. (Author)
• Format: Article
• Language: English
• Published: MDPI 2022
• Subjects: Air traffic control; Analysis method; Artefact reduction; Brain; dimensionality reduction; Dimensionality reduction; Electroencephalography; Extraction; Eye movements; feature extraction; Feature extraction; Features extraction; independent component analysis; Independent component analysis; Independent components analysis; noise; Noise; Spectral density; Threshold; thresholds; vigilance assessment; Vigilance assessment; Vigilance levels; wavelet transform; Wavelet transforms; Wavelets transform
• Online Access: View Fulltext in Publisher

 Vigilance level assessment is of prime importance to avoid life-threatening human error. Critical working environments such as air traffic control, driving, or military surveillance require the operator to be alert the whole time. The electroencephalogram (EEG) is a very common modality that can be used in assessing vigilance. Unfortunately, EEG signals are prone to artifacts due to eye movement, muscle contraction, and electrical noise. Mitigating these artifacts is important for an accurate vigilance level assessment. Independent Component Analysis (ICA) is an effective method and has been extensively used in the suppression of EEG artifacts. However, in vigilance assessment applications, it was found to suffer from leakage of the cerebral activity into artifacts. In this work, we show that the wavelet ICA (wICA) method provides an alternative for artifact reduction, leading to improved vigilance level assessment results. We conducted an experiment in nine human subjects to induce two vigilance states, alert and vigilance decrement, while performing a Stroop Color–Word Test for approximately 45 min. We then compared the performance of the ICA and wICA preprocessing methods using five classifiers. Our classification results showed that in terms of features extraction, the wICA method outperformed the existing ICA method. In the delta, theta, and alpha bands, we obtained a mean classification accuracy of 84.66% using the ICA method, whereas the mean accuracy using the wICA methodwas 96.9%. However, no significant improvement was observed in the beta band. In addition, we compared the topographical map to show the changes in power spectral density across the brain regions for the two vigilance states. The proposed method showed that the frontal and central regions were most sensitive to vigilance decrement. However, in this application, the proposed wICA shows a marginal improvement compared to the Fast-ICA. © 2022 by the authors. Licensee MDPI, Basel, Switzerland.