Skip to main navigation Skip to search Skip to main content

Exploiting Mallows Distance to Quantify EEG Distribution for Personal Identification

  • SUNY Buffalo
  • Princeton University
  • Zhejiang University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

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.

Original languageEnglish
Title of host publication2019 IEEE Conference on Dependable and Secure Computing, DSC 2019 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728123196
DOIs
StatePublished - Nov 2019
Event3rd IEEE Conference on Dependable and Secure Computing, DSC 2019 - Hangzhou, China
Duration: Nov 18 2019Nov 20 2019

Publication series

Name2019 IEEE Conference on Dependable and Secure Computing, DSC 2019 - Proceedings

Conference

Conference3rd IEEE Conference on Dependable and Secure Computing, DSC 2019
Country/TerritoryChina
CityHangzhou
Period11/18/1911/20/19

Keywords

  • Biometrics
  • Secure Authentication
  • Wearable Computing

Fingerprint

Dive into the research topics of 'Exploiting Mallows Distance to Quantify EEG Distribution for Personal Identification'. Together they form a unique fingerprint.

Cite this