Key result
An EEG-based identification system exploiting Mallows distance achieved an f-score accuracy of 96.18% and a half total error rate of 2.223% for personal identification.
Why the study?
Quantifying EEG feature distribution for brain biometrics remains an unsolved problem due to the complexity of the brain.
A novel EEG distribution model using Mallows distance demonstrates high accuracy for personal identification applications.
May enable EEG biometrics for identification; leaves open validation in larger, diverse cohorts.
Electroencephalogram (EEG) activity from the brain is a promising biological marker that can serve as personal identification. Despite substantial efforts, it still remains unsolved problems to quantify EEG feature distribution for brain biometrics due to the complexity of the brain. In this study, we attempt to tackle EEG-based identification challenges by exploiting a novel distribution model. The distribution dissimilarity is measured by Mallows distance, a cluster similarity sensitive distance that is robust to signal noises. Specifically, EEG signals are decomposed through several statistical feature extraction methods, autoregressive (AR) model, discrete wavelet transform (DWT), and fast Fourier transform (FFT). With the dataset obtained from the real-world application, our proposed system achieves the f-score accuracy of 96.18% and half total error rate of 2.223%, which demonstrates the feasibility and effectiveness of utilizing EEG biometrics for personal identification applications.
No takes yet. Share an insight, caveat, or question.
Chen et al. (2019) studied Personal identification (brain biometrics). EEG-based identification using Mallows distance was evaluated on f-score accuracy and half total error rate. An EEG-based identification system exploiting Mallows distance achieved an f-score accuracy of 96.18% and a half total error rate of 2.223% for personal identification.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: