EEG-based human recognition is increasingly becoming a popular modality for biometric authentication. Two important features of EEG signals are liveliness and the robustness against falsification. However, a comprehensive study on human authentication using EEG signal is still remains. On the other hand, low-cost wireless EEG recording devices are now growing in the market places. Although these devices have the potential to many applications, researches have yet to be done to find the feasibility of these devices. In this study, we propose a method for human identification using EEG signals obtained from such low-cost devices. EEG signal is first preprocessed to remove noise and artifacts using Bandpass FIR filter. These signals are then divided into disjoint segments. Three feature extraction methods, namely multiscale shape description (MSD), multiscale wavelet packet statistics (WPS) and multiscale wavelet packet energy statistics (WPES) are then applied. These features are finally used to train a supervised error-correcting output code multiclass model (ECOC) using support vector machine (SVM) classifier, which ultimately can recognize humans from test EEG signals. A preliminary experiment with 9 EEG records from 9 subjects shows the true positive rate of 94.44% of the proposed method.