A fair comparison of the EEG signal classification methods for alcoholic subject identification

The electroencephalogram (EEG) signal, which records the electrical activity in the brain, is useful for assessing the mental state of the alcoholic subject. Since the public release of an EEG dataset by the University of California, Irvine, there have been many attempts to classify the EEG signals of alcoholic' and `healthy' subjects. These classification methods are hard to compare as they use different subsets of the dataset and many of their algorithmic settings are unknown. The comparison of their published results using the inconsistent and unknown information is unfair. This paper attempts a fair comparison by presenting a level playing field where a public subset of the dataset is employed with known algorithmic settings. Two recently proposed high performing EEG signal classification methods are implemented with different classifiers and cross-validation techniques. While compared it is observed that the wavelet packet decomposition method with the Naïve Bayes classifier and the k-fold cross validation technique outperforms the other method.