Feature extraction from electroencephalograms for Bayesian assessment of newborn brain maturity

Livija Jakaite; Vitaly Schetinin; Joachim Schult

doi:10.1109/CBMS.2011.5999109

Feature extraction from electroencephalograms for Bayesian assessment of newborn brain maturity

Livija Jakaite
, Vitaly Schetinin
, Joachim Schult

Institute for Research in Applicable Computing (IRAC)

University of Hamburg

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

30 Citations (Scopus)

6 Downloads (Pure)

Abstract

We explored the feature extraction techniques for Bayesian assessment of EEG maturity of newborns in the context that the continuity of EEG is the most important feature for assessment of the brain development. The continuity is associated with EEG “stationarity” which we propose to evaluate with adaptive segmentation of EEG into pseudo-stationary intervals. The histograms of these intervals are then used as new features for the assessment of EEG maturity. In our experiments, we used Bayesian model averaging over decision trees to differentiate two age groups, each included 110 EEG recordings. The use of the proposed EEG features has shown, on average, a 6% increase in the accuracy of age differentiation.

Original language	English
Title of host publication	nan
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781457711893
ISBN (Print)	9781457711893
DOIs	https://doi.org/10.1109/CBMS.2011.5999109
Publication status	Published - 25 Aug 2011
Event	2011 24th International Symposium on Computer-Based Medical Systems (CBMS) - Bristol Duration: 27 Jun 2011 → 30 Jun 2011

Conference

Conference	2011 24th International Symposium on Computer-Based Medical Systems (CBMS)
City	Bristol
Period	27/06/11 → 30/06/11
Other	2011 24th International Symposium on Computer-Based Medical Systems (CBMS) (27/06/2011-30/06/2011, Bristol)

Keywords

Bayesian predictive modelling

Access to Document

10.1109/CBMS.2011.5999109

Feature Extraction Accepted author manuscript, 539 KBLicence: CC BY-NC-ND

https://ieeexplore.ieee.org/document/5999109

Handle.net

Persistent link

Cite this

@inproceedings{f1508508488c4e3198db50aa45025c15,

title = "Feature extraction from electroencephalograms for Bayesian assessment of newborn brain maturity",

abstract = "We explored the feature extraction techniques for Bayesian assessment of EEG maturity of newborns in the context that the continuity of EEG is the most important feature for assessment of the brain development. The continuity is associated with EEG “stationarity” which we propose to evaluate with adaptive segmentation of EEG into pseudo-stationary intervals. The histograms of these intervals are then used as new features for the assessment of EEG maturity. In our experiments, we used Bayesian model averaging over decision trees to differentiate two age groups, each included 110 EEG recordings. The use of the proposed EEG features has shown, on average, a 6\% increase in the accuracy of age differentiation.",

keywords = "Bayesian predictive modelling",

author = "Livija Jakaite and Vitaly Schetinin and Joachim Schult",

year = "2011",

month = aug,

day = "25",

doi = "10.1109/CBMS.2011.5999109",

language = "English",

isbn = "9781457711893",

booktitle = "nan",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "2011 24th International Symposium on Computer-Based Medical Systems (CBMS) ; Conference date: 27-06-2011 Through 30-06-2011",

}

TY - GEN

T1 - Feature extraction from electroencephalograms for Bayesian assessment of newborn brain maturity

AU - Jakaite, Livija

AU - Schetinin, Vitaly

AU - Schult, Joachim

PY - 2011/8/25

Y1 - 2011/8/25

N2 - We explored the feature extraction techniques for Bayesian assessment of EEG maturity of newborns in the context that the continuity of EEG is the most important feature for assessment of the brain development. The continuity is associated with EEG “stationarity” which we propose to evaluate with adaptive segmentation of EEG into pseudo-stationary intervals. The histograms of these intervals are then used as new features for the assessment of EEG maturity. In our experiments, we used Bayesian model averaging over decision trees to differentiate two age groups, each included 110 EEG recordings. The use of the proposed EEG features has shown, on average, a 6% increase in the accuracy of age differentiation.

AB - We explored the feature extraction techniques for Bayesian assessment of EEG maturity of newborns in the context that the continuity of EEG is the most important feature for assessment of the brain development. The continuity is associated with EEG “stationarity” which we propose to evaluate with adaptive segmentation of EEG into pseudo-stationary intervals. The histograms of these intervals are then used as new features for the assessment of EEG maturity. In our experiments, we used Bayesian model averaging over decision trees to differentiate two age groups, each included 110 EEG recordings. The use of the proposed EEG features has shown, on average, a 6% increase in the accuracy of age differentiation.

KW - Bayesian predictive modelling

U2 - 10.1109/CBMS.2011.5999109

DO - 10.1109/CBMS.2011.5999109

M3 - Conference contribution

SN - 9781457711893

BT - nan

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2011 24th International Symposium on Computer-Based Medical Systems (CBMS)

Y2 - 27 June 2011 through 30 June 2011

ER -

Feature extraction from electroencephalograms for Bayesian assessment of newborn brain maturity

Abstract

Conference

Keywords

Access to Document

Handle.net

Fingerprint

Cite this