Analysis of factors that influence the performance of biometric systems based on EEG signals

Dustin Carrión-Ojeda, Rigoberto Fonseca-Delgado, Israel Pineda

Abstract: Highlights•SVM and Adaboost obtain the best electroencephalogram classification results.•1.75s of electroencephalogram recording is enough for classification.•Classification depends on the decomposition levels of Discrete Wavelet Transform.•The relative wavelet energy is a promising feature vector for biometrics.