Biometric authentication, namely using biometric features for authentication is gaining popularity in recent years as further modalities, such as fingerprint, iris, face, voice, gait, and others are exploited. We explore the effectiveness of three simple Electroencephalography (EEG) related biometric authentication tasks, namely resting, thinking about a picture, and moving a single finger. We present details of the data processing steps we exploit for authentication, including extracting features from the frequency power spectrum and MFCC, and training a multilayer perceptron classifier for authentication. For evaluation purposes, we record an EEG dataset of 27 test subjects. We use three setups, baseline, task-agnostic, and task-specific, to investigate whether person-specific features can be detected across different tasks for authentication. We further evaluate, whether different tasks can be distinguished. Our results suggest that tasks are distinguishable, as well as that our authentication approach can work both exploiting features from a specific, fixed, task as well as using features across different tasks.
Eeva-Sofia HAUKIPURO
Aalto University
Ville KOLEHMAINEN
Aalto University
Janne MYLLÄRINEN
Aalto University
Sebastian REMANDER
Aalto University
Janne SALO
Aalto University
Tuomas TAKKO
Aalto University
Le Ngu NGUYEN
Aalto University
Stephan SIGG
Aalto University
Rainhard Dieter FINDLING
Aalto University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Eeva-Sofia HAUKIPURO, Ville KOLEHMAINEN, Janne MYLLÄRINEN, Sebastian REMANDER, Janne SALO, Tuomas TAKKO, Le Ngu NGUYEN, Stephan SIGG, Rainhard Dieter FINDLING, "Mobile Brainwaves: On the Interchangeability of Simple Authentication Tasks with Low-Cost, Single-Electrode EEG Devices" in IEICE TRANSACTIONS on Communications,
vol. E102-B, no. 4, pp. 760-767, April 2019, doi: 10.1587/transcom.2018SEP0016.
Abstract: Biometric authentication, namely using biometric features for authentication is gaining popularity in recent years as further modalities, such as fingerprint, iris, face, voice, gait, and others are exploited. We explore the effectiveness of three simple Electroencephalography (EEG) related biometric authentication tasks, namely resting, thinking about a picture, and moving a single finger. We present details of the data processing steps we exploit for authentication, including extracting features from the frequency power spectrum and MFCC, and training a multilayer perceptron classifier for authentication. For evaluation purposes, we record an EEG dataset of 27 test subjects. We use three setups, baseline, task-agnostic, and task-specific, to investigate whether person-specific features can be detected across different tasks for authentication. We further evaluate, whether different tasks can be distinguished. Our results suggest that tasks are distinguishable, as well as that our authentication approach can work both exploiting features from a specific, fixed, task as well as using features across different tasks.
URL: https://global.ieice.org/en_transactions/communications/10.1587/transcom.2018SEP0016/_p
Copy
@ARTICLE{e102-b_4_760,
author={Eeva-Sofia HAUKIPURO, Ville KOLEHMAINEN, Janne MYLLÄRINEN, Sebastian REMANDER, Janne SALO, Tuomas TAKKO, Le Ngu NGUYEN, Stephan SIGG, Rainhard Dieter FINDLING, },
journal={IEICE TRANSACTIONS on Communications},
title={Mobile Brainwaves: On the Interchangeability of Simple Authentication Tasks with Low-Cost, Single-Electrode EEG Devices},
year={2019},
volume={E102-B},
number={4},
pages={760-767},
abstract={Biometric authentication, namely using biometric features for authentication is gaining popularity in recent years as further modalities, such as fingerprint, iris, face, voice, gait, and others are exploited. We explore the effectiveness of three simple Electroencephalography (EEG) related biometric authentication tasks, namely resting, thinking about a picture, and moving a single finger. We present details of the data processing steps we exploit for authentication, including extracting features from the frequency power spectrum and MFCC, and training a multilayer perceptron classifier for authentication. For evaluation purposes, we record an EEG dataset of 27 test subjects. We use three setups, baseline, task-agnostic, and task-specific, to investigate whether person-specific features can be detected across different tasks for authentication. We further evaluate, whether different tasks can be distinguished. Our results suggest that tasks are distinguishable, as well as that our authentication approach can work both exploiting features from a specific, fixed, task as well as using features across different tasks.},
keywords={},
doi={10.1587/transcom.2018SEP0016},
ISSN={1745-1345},
month={April},}
Copy
TY - JOUR
TI - Mobile Brainwaves: On the Interchangeability of Simple Authentication Tasks with Low-Cost, Single-Electrode EEG Devices
T2 - IEICE TRANSACTIONS on Communications
SP - 760
EP - 767
AU - Eeva-Sofia HAUKIPURO
AU - Ville KOLEHMAINEN
AU - Janne MYLLÄRINEN
AU - Sebastian REMANDER
AU - Janne SALO
AU - Tuomas TAKKO
AU - Le Ngu NGUYEN
AU - Stephan SIGG
AU - Rainhard Dieter FINDLING
PY - 2019
DO - 10.1587/transcom.2018SEP0016
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E102-B
IS - 4
JA - IEICE TRANSACTIONS on Communications
Y1 - April 2019
AB - Biometric authentication, namely using biometric features for authentication is gaining popularity in recent years as further modalities, such as fingerprint, iris, face, voice, gait, and others are exploited. We explore the effectiveness of three simple Electroencephalography (EEG) related biometric authentication tasks, namely resting, thinking about a picture, and moving a single finger. We present details of the data processing steps we exploit for authentication, including extracting features from the frequency power spectrum and MFCC, and training a multilayer perceptron classifier for authentication. For evaluation purposes, we record an EEG dataset of 27 test subjects. We use three setups, baseline, task-agnostic, and task-specific, to investigate whether person-specific features can be detected across different tasks for authentication. We further evaluate, whether different tasks can be distinguished. Our results suggest that tasks are distinguishable, as well as that our authentication approach can work both exploiting features from a specific, fixed, task as well as using features across different tasks.
ER -