Permutation entropy: A new feature for brain-computer interfaces

Nicoletta Nicolaou; Julius Georgiou

doi:10.1109/BIOCAS.2010.5709568

Permutation entropy: A new feature for brain-computer interfaces

Nicoletta Nicolaou
, Julius Georgiou

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

This paper investigates the use of Permutation Entropy (PE) as a feature for mental task classification for a Brain-Computer Interface system. PE is a recently introduced measure which quantifies signal complexity by measuring the departure of a time series from a random one. More regular signals are characterized by lower PE values. Here, PE is utilized to characterize signals from electroencephalograms of 3 subjects performing 4 motor imagery tasks, which are then classified using a Support Vector Machine. Even though it is possible to obtain 100% single-trial classification accuracy, this is very much subject-dependent.

Original language	English
Title of host publication	2010 IEEE Biomedical Circuits and Systems Conference, BioCAS 2010
Pages	49-52
Number of pages	4
DOIs	https://doi.org/10.1109/BIOCAS.2010.5709568
Publication status	Published - 1 Dec 2010
Externally published	Yes
Event	2010 IEEE Biomedical Circuits and Systems Conference, BioCAS 2010 - Paphos, Cyprus Duration: 3 Nov 2010 → 5 Nov 2010

Conference

Conference	2010 IEEE Biomedical Circuits and Systems Conference, BioCAS 2010
Country/Territory	Cyprus
City	Paphos
Period	3/11/10 → 5/11/10

Access to Document

10.1109/BIOCAS.2010.5709568

Cite this

@inproceedings{cd98646bbd1646869184c30a9eaba568,

title = "Permutation entropy: A new feature for brain-computer interfaces",

abstract = "This paper investigates the use of Permutation Entropy (PE) as a feature for mental task classification for a Brain-Computer Interface system. PE is a recently introduced measure which quantifies signal complexity by measuring the departure of a time series from a random one. More regular signals are characterized by lower PE values. Here, PE is utilized to characterize signals from electroencephalograms of 3 subjects performing 4 motor imagery tasks, which are then classified using a Support Vector Machine. Even though it is possible to obtain 100\% single-trial classification accuracy, this is very much subject-dependent.",

author = "Nicoletta Nicolaou and Julius Georgiou",

year = "2010",

month = dec,

day = "1",

doi = "10.1109/BIOCAS.2010.5709568",

language = "English",

isbn = "9781424472703",

pages = "49--52",

booktitle = "2010 IEEE Biomedical Circuits and Systems Conference, BioCAS 2010",

note = "2010 IEEE Biomedical Circuits and Systems Conference, BioCAS 2010 ; Conference date: 03-11-2010 Through 05-11-2010",

}

TY - GEN

T1 - Permutation entropy

T2 - 2010 IEEE Biomedical Circuits and Systems Conference, BioCAS 2010

AU - Nicolaou, Nicoletta

AU - Georgiou, Julius

PY - 2010/12/1

Y1 - 2010/12/1

N2 - This paper investigates the use of Permutation Entropy (PE) as a feature for mental task classification for a Brain-Computer Interface system. PE is a recently introduced measure which quantifies signal complexity by measuring the departure of a time series from a random one. More regular signals are characterized by lower PE values. Here, PE is utilized to characterize signals from electroencephalograms of 3 subjects performing 4 motor imagery tasks, which are then classified using a Support Vector Machine. Even though it is possible to obtain 100% single-trial classification accuracy, this is very much subject-dependent.

AB - This paper investigates the use of Permutation Entropy (PE) as a feature for mental task classification for a Brain-Computer Interface system. PE is a recently introduced measure which quantifies signal complexity by measuring the departure of a time series from a random one. More regular signals are characterized by lower PE values. Here, PE is utilized to characterize signals from electroencephalograms of 3 subjects performing 4 motor imagery tasks, which are then classified using a Support Vector Machine. Even though it is possible to obtain 100% single-trial classification accuracy, this is very much subject-dependent.

UR - https://www.scopus.com/pages/publications/79952390220

U2 - 10.1109/BIOCAS.2010.5709568

DO - 10.1109/BIOCAS.2010.5709568

M3 - Conference contribution

AN - SCOPUS:79952390220

SN - 9781424472703

SP - 49

EP - 52

BT - 2010 IEEE Biomedical Circuits and Systems Conference, BioCAS 2010

Y2 - 3 November 2010 through 5 November 2010

ER -

Permutation entropy: A new feature for brain-computer interfaces

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this