Change search
ReferencesLink to record
Permanent link

Direct link
Classification of Burst and Suppression in the Neonatal EEG
University of Borås, School of Engineering.
2007 (English)Licentiate thesis, monograph (Other academic)
Abstract [en]

The brain requires a continuous supply of oxygen and even a short period of reduced oxygen supply risks severe and lifelong consequences for the affected individual. The delivery is a vulnerable period for a baby who may experience for example hypoxia (lack of oxygen) that can damage the brain. Babies who experience problems are placed in an intensive care unit where their vital signs are monitored, but there is no reliable way to monitor the brain directly. Monitoring the brain would provide valuable information about the processes going on in it and could influence the treatment and help to improve the quality of neonatal care. The scope of this project is to develop methods that eventually can be put together to form a monitoring system for the brain that can function as decision-support for the physician in charge of treating the patient. The specific technical problem that is the topic of this thesis is detection of burst and suppression in the electroencephalogram (EEG) signal. The thesis starts with a brief description of the brain, with a focus on where the EEG originates, what types of activity can be found in this signal and what they mean. The data that have been available for the project are described, followed by the signal processing methods that have been used for preprocessing, and the feature functions that can be used for extracting certain types of characteristics from the data are defined. The next section describes classification methodology and how it can be used for making decisions based on combinations of several features extracted from a signal. The classification methods Fisher’s Linear Discriminant, Neural Networks and Support Vector Machines are described and are finally compared with respect to their ability to discriminate between burst and suppression. An experiment with different combinations of features in the classification has also been carried out. The results show similar results for the three methods but it can be seen that the SVM is the best method with respect to handling multiple features.

Place, publisher, year, edition, pages
Göteborg : Chalmers tekniska högskola , 2007.
Skrifter från Högskolan i Borås, ISSN 0280-381X ; 7
, Technical report, ISSN 1403-266X ; R018/2007
Keyword [en]
electroencephalogram, neonatal care, EEG
National Category
Biomedical Laboratory Science/Technology
URN: urn:nbn:se:hb:diva-3448Local ID: 2320/2809OAI: diva2:876837
Available from: 2015-12-04 Created: 2015-12-04

Open Access in DiVA

fulltext(1785 kB)82 downloads
File information
File name FULLTEXT01.pdfFile size 1785 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Löfhede, Johan
By organisation
School of Engineering
Biomedical Laboratory Science/Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 82 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 22 hits
ReferencesLink to record
Permanent link

Direct link