Key result
A subtractive fuzzy inference classifier using sym8 wavelet features achieves ~79% accuracy detecting driver distraction.
Why the study?
Classification of driver distraction levels using wireless EEG signals with different wavelets and classifiers requires evaluation for accuracy and discrimination.
EEG signals processed with discrete wavelet packet transform and specific classifiers can achieve approximately 79% accuracy in detecting driver distraction levels.
Hypothesis-generating for EEG-based monitoring; requires prospective validation before any clinical or safety applications.
We classify the driver distraction level (neutral, low, medium, and high) based on different wavelets and classifiers using wireless electroencephalogram (EEG) signals. 50 subjects were used for data collection using 14 electrodes. We considered for this research 4 distraction stimuli such as Global Position Systems (GPS), music player, short message service (SMS), and mental tasks. Deriving the amplitude spectrum of three different frequency bands theta, alpha, and beta of EEG signals was based on fusion of discrete wavelet packet transform (DWPT) and FFT. Comparing the results of three different classifiers (subtractive fuzzy clustering probabilistic neural network, -nearest neighbor) was based on spectral centroid, and power spectral features extracted by different wavelets (db4, db8, sym8, and coif5). The results of this study indicate that the best average accuracy achieved by subtractive fuzzy inference system classifier is 79.21% based on power spectral density feature extracted by sym8 wavelet which gave a good class discrimination under ANOVA test.
No takes yet. Share an insight, caveat, or question.
Wali et al. (2013) studied Driver distraction (n=50). EEG-based driver distraction classification using subtractive fuzzy inference system vs. Other classifiers (probabilistic neural network, k-nearest neighbor) and wavelets was evaluated on Classification accuracy of driver distraction level. A subtractive fuzzy inference system classifier using power spectral density features extracted by a sym8 wavelet achieved a best average accuracy of 79.21% for classifying driver distraction levels.
Synapse has enriched one closely related paper. Consider it for comparative context: