Conditional Entropy Approach to Multichannel EEG-Based Person Identification

Dinh PHUNG, Dat TRAN, Wanli MA, Tien PHAM

Research output: A Conference proceeding or a Chapter in BookConference contribution

2 Citations (Scopus)

Abstract

Person identification using electroencephalogram (EEG) as biometric has been widely used since it is capable of achieving high identification rate. Since single-channel EEG signal does not provide sufficient information for person identification, multi-channel EEG signals are used to record brain activities distributed over the entire scalp. However extracting brain features from multi-channel EEG signals is still a challenge. In this paper, we propose to use Conditional Entropy (CEN) as a feature extraction method for multi-channel EEG-based person identification. The use of entropy-based method is based on the fact that EEG signal is complex, non-linear, and random in nature. CEN is capable of quantifying how much uncertainty an EEG channel has if the outcome of another EEG channel is known. The mechanism of CEN in correlating pairs of channels would be a solution for feature extraction from multi-channel EEG signals. Our experimental results on EEG signals from 80 persons have shown that CEN provides higher identification rate, yet less number of features than the baseline Autoregressive modelling method.
Original languageEnglish
Title of host publicationInternational Joint Conference CISIS 2015 and ICEUTE 2015
Subtitle of host publicationCISIS'15 and ICEUTE'15
EditorsAlvaro Herrero, Bruno Baruque, Javier Sedano, Hector Quintian, Emilio Corchado
Place of PublicationCham, Switzerland
PublisherSpringer
Pages157-165
Number of pages9
Volume369
ISBN (Electronic)9783319197135
ISBN (Print)9783319197128
DOIs
Publication statusPublished - 2015
EventThe 8th International Conference on Computational Intelligence in Security for Information Systems - http://cisis.usal.es , Burgos, Spain
Duration: 15 Jun 201517 Jun 2015
http://cisis.usal.es

Publication series

NameAdvances in Intelligent Systems and Computing
PublisherSpringer
Volume369
ISSN (Print)2194-5357
ISSN (Electronic)2194-5356

Conference

ConferenceThe 8th International Conference on Computational Intelligence in Security for Information Systems
Abbreviated titleCISIS 2015
CountrySpain
CityBurgos
Period15/06/1517/06/15
Internet address

Fingerprint

Electroencephalography
Entropy
Feature extraction
Brain
Biometrics

Cite this

PHUNG, D., TRAN, D., MA, W., & PHAM, T. (2015). Conditional Entropy Approach to Multichannel EEG-Based Person Identification. In A. Herrero, B. Baruque, J. Sedano, H. Quintian, & E. Corchado (Eds.), International Joint Conference CISIS 2015 and ICEUTE 2015: CISIS'15 and ICEUTE'15 (Vol. 369, pp. 157-165). (Advances in Intelligent Systems and Computing ; Vol. 369). Cham, Switzerland: Springer. https://doi.org/10.1007/978-3-319-19713-5_14
PHUNG, Dinh ; TRAN, Dat ; MA, Wanli ; PHAM, Tien. / Conditional Entropy Approach to Multichannel EEG-Based Person Identification. International Joint Conference CISIS 2015 and ICEUTE 2015: CISIS'15 and ICEUTE'15. editor / Alvaro Herrero ; Bruno Baruque ; Javier Sedano ; Hector Quintian ; Emilio Corchado. Vol. 369 Cham, Switzerland : Springer, 2015. pp. 157-165 (Advances in Intelligent Systems and Computing ).
@inproceedings{51b9e488662b42d69eeb166a7fa06c08,
title = "Conditional Entropy Approach to Multichannel EEG-Based Person Identification",
abstract = "Person identification using electroencephalogram (EEG) as biometric has been widely used since it is capable of achieving high identification rate. Since single-channel EEG signal does not provide sufficient information for person identification, multi-channel EEG signals are used to record brain activities distributed over the entire scalp. However extracting brain features from multi-channel EEG signals is still a challenge. In this paper, we propose to use Conditional Entropy (CEN) as a feature extraction method for multi-channel EEG-based person identification. The use of entropy-based method is based on the fact that EEG signal is complex, non-linear, and random in nature. CEN is capable of quantifying how much uncertainty an EEG channel has if the outcome of another EEG channel is known. The mechanism of CEN in correlating pairs of channels would be a solution for feature extraction from multi-channel EEG signals. Our experimental results on EEG signals from 80 persons have shown that CEN provides higher identification rate, yet less number of features than the baseline Autoregressive modelling method.",
keywords = "Autoregressive model, Conditional Entropy, EEG, Multi-channel EEG, Person identification",
author = "Dinh PHUNG and Dat TRAN and Wanli MA and Tien PHAM",
year = "2015",
doi = "10.1007/978-3-319-19713-5_14",
language = "English",
isbn = "9783319197128",
volume = "369",
series = "Advances in Intelligent Systems and Computing",
publisher = "Springer",
pages = "157--165",
editor = "Alvaro Herrero and Bruno Baruque and Javier Sedano and Hector Quintian and Emilio Corchado",
booktitle = "International Joint Conference CISIS 2015 and ICEUTE 2015",
address = "Netherlands",

}

PHUNG, D, TRAN, D, MA, W & PHAM, T 2015, Conditional Entropy Approach to Multichannel EEG-Based Person Identification. in A Herrero, B Baruque, J Sedano, H Quintian & E Corchado (eds), International Joint Conference CISIS 2015 and ICEUTE 2015: CISIS'15 and ICEUTE'15. vol. 369, Advances in Intelligent Systems and Computing , vol. 369, Springer, Cham, Switzerland, pp. 157-165, The 8th International Conference on Computational Intelligence in Security for Information Systems, Burgos, Spain, 15/06/15. https://doi.org/10.1007/978-3-319-19713-5_14

Conditional Entropy Approach to Multichannel EEG-Based Person Identification. / PHUNG, Dinh; TRAN, Dat; MA, Wanli; PHAM, Tien.

International Joint Conference CISIS 2015 and ICEUTE 2015: CISIS'15 and ICEUTE'15. ed. / Alvaro Herrero; Bruno Baruque; Javier Sedano; Hector Quintian; Emilio Corchado. Vol. 369 Cham, Switzerland : Springer, 2015. p. 157-165 (Advances in Intelligent Systems and Computing ; Vol. 369).

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - Conditional Entropy Approach to Multichannel EEG-Based Person Identification

AU - PHUNG, Dinh

AU - TRAN, Dat

AU - MA, Wanli

AU - PHAM, Tien

PY - 2015

Y1 - 2015

N2 - Person identification using electroencephalogram (EEG) as biometric has been widely used since it is capable of achieving high identification rate. Since single-channel EEG signal does not provide sufficient information for person identification, multi-channel EEG signals are used to record brain activities distributed over the entire scalp. However extracting brain features from multi-channel EEG signals is still a challenge. In this paper, we propose to use Conditional Entropy (CEN) as a feature extraction method for multi-channel EEG-based person identification. The use of entropy-based method is based on the fact that EEG signal is complex, non-linear, and random in nature. CEN is capable of quantifying how much uncertainty an EEG channel has if the outcome of another EEG channel is known. The mechanism of CEN in correlating pairs of channels would be a solution for feature extraction from multi-channel EEG signals. Our experimental results on EEG signals from 80 persons have shown that CEN provides higher identification rate, yet less number of features than the baseline Autoregressive modelling method.

AB - Person identification using electroencephalogram (EEG) as biometric has been widely used since it is capable of achieving high identification rate. Since single-channel EEG signal does not provide sufficient information for person identification, multi-channel EEG signals are used to record brain activities distributed over the entire scalp. However extracting brain features from multi-channel EEG signals is still a challenge. In this paper, we propose to use Conditional Entropy (CEN) as a feature extraction method for multi-channel EEG-based person identification. The use of entropy-based method is based on the fact that EEG signal is complex, non-linear, and random in nature. CEN is capable of quantifying how much uncertainty an EEG channel has if the outcome of another EEG channel is known. The mechanism of CEN in correlating pairs of channels would be a solution for feature extraction from multi-channel EEG signals. Our experimental results on EEG signals from 80 persons have shown that CEN provides higher identification rate, yet less number of features than the baseline Autoregressive modelling method.

KW - Autoregressive model

KW - Conditional Entropy

KW - EEG

KW - Multi-channel EEG

KW - Person identification

UR - http://www.scopus.com/inward/record.url?scp=84946730922&partnerID=8YFLogxK

UR - http://www.mendeley.com/research/conditional-entropy-approach-multichannel-eegbased-person-identification

U2 - 10.1007/978-3-319-19713-5_14

DO - 10.1007/978-3-319-19713-5_14

M3 - Conference contribution

SN - 9783319197128

VL - 369

T3 - Advances in Intelligent Systems and Computing

SP - 157

EP - 165

BT - International Joint Conference CISIS 2015 and ICEUTE 2015

A2 - Herrero, Alvaro

A2 - Baruque, Bruno

A2 - Sedano, Javier

A2 - Quintian, Hector

A2 - Corchado, Emilio

PB - Springer

CY - Cham, Switzerland

ER -

PHUNG D, TRAN D, MA W, PHAM T. Conditional Entropy Approach to Multichannel EEG-Based Person Identification. In Herrero A, Baruque B, Sedano J, Quintian H, Corchado E, editors, International Joint Conference CISIS 2015 and ICEUTE 2015: CISIS'15 and ICEUTE'15. Vol. 369. Cham, Switzerland: Springer. 2015. p. 157-165. (Advances in Intelligent Systems and Computing ). https://doi.org/10.1007/978-3-319-19713-5_14