Evaluation of the Performance of Methods for Classifying EEG Signal Processing

Over the past few decades the popularity of artificial neural networks has been continuously increasing in the fields of machine learning, data mining and pattern recognition. However, it has been suggested that in many scenarios artificial neural networks do not always deliver the best performance when compared to other data classification methods, like tree-based models. This article evaluates and compares the performance of different classification algorithms and methods employing electroencephalography data. Both artificial neural networks and classic methods are benchmarked and compared.