IRIS publication 241502551
Discriminative and generative classification techniques applied to automated neonatal seizure detection.
RIS format for Endnote and similar
TY - JOUR - Thomas EM, Temko A, Marnane WP, Boylan GB, Lightbody G - 2013 - March - IEEE journal of biomedical and health informatics - Discriminative and generative classification techniques applied to automated neonatal seizure detection. - Validated - () - 17 - 2 - 297 - 304 - A number of automated neonatal seizure detectors have been proposed in recent years. However, there exists a large variability in the morphology of seizure and background patterns, both across patients and over time. This has resulted in relatively poor performance from systems which have been tested over large datasets. Here, the benefits of employing a pattern recognition approach are discussed. Such a system may use numerous features paired with nonlinear classifiers. In particular, two types of nonlinear classifiers are contrasted for the task. Additionally, it is shown that the proposed architecture allows for efficient classifier combination which improves the performance of the algorithm. The resulting automated detector is shown to achieve field leading performance. A particular strength of the proposed algorithm is the performance of the algorithm when very low false detections are required, at 0.25 false detections per hour, the system is able to detect 75.4% of the seizure events. - 10.1109/JBHI.2012.2237035 DA - 2013/03 ER -
BIBTeX format for JabRef and similar
@article{V241502551, = {Thomas EM, Temko A and Marnane WP, Boylan GB and Lightbody G }, = {2013}, = {March}, = {IEEE journal of biomedical and health informatics}, = {Discriminative and generative classification techniques applied to automated neonatal seizure detection.}, = {Validated}, = {()}, = {17}, = {2}, pages = {297--304}, = {{A number of automated neonatal seizure detectors have been proposed in recent years. However, there exists a large variability in the morphology of seizure and background patterns, both across patients and over time. This has resulted in relatively poor performance from systems which have been tested over large datasets. Here, the benefits of employing a pattern recognition approach are discussed. Such a system may use numerous features paired with nonlinear classifiers. In particular, two types of nonlinear classifiers are contrasted for the task. Additionally, it is shown that the proposed architecture allows for efficient classifier combination which improves the performance of the algorithm. The resulting automated detector is shown to achieve field leading performance. A particular strength of the proposed algorithm is the performance of the algorithm when very low false detections are required, at 0.25 false detections per hour, the system is able to detect 75.4% of the seizure events.}}, = {10.1109/JBHI.2012.2237035}, source = {IRIS} }
Data as stored in IRIS
AUTHORS | Thomas EM, Temko A, Marnane WP, Boylan GB, Lightbody G | ||
YEAR | 2013 | ||
MONTH | March | ||
JOURNAL_CODE | IEEE journal of biomedical and health informatics | ||
TITLE | Discriminative and generative classification techniques applied to automated neonatal seizure detection. | ||
STATUS | Validated | ||
TIMES_CITED | () | ||
SEARCH_KEYWORD | |||
VOLUME | 17 | ||
ISSUE | 2 | ||
START_PAGE | 297 | ||
END_PAGE | 304 | ||
ABSTRACT | A number of automated neonatal seizure detectors have been proposed in recent years. However, there exists a large variability in the morphology of seizure and background patterns, both across patients and over time. This has resulted in relatively poor performance from systems which have been tested over large datasets. Here, the benefits of employing a pattern recognition approach are discussed. Such a system may use numerous features paired with nonlinear classifiers. In particular, two types of nonlinear classifiers are contrasted for the task. Additionally, it is shown that the proposed architecture allows for efficient classifier combination which improves the performance of the algorithm. The resulting automated detector is shown to achieve field leading performance. A particular strength of the proposed algorithm is the performance of the algorithm when very low false detections are required, at 0.25 false detections per hour, the system is able to detect 75.4% of the seizure events. | ||
PUBLISHER_LOCATION | |||
ISBN_ISSN | |||
EDITION | |||
URL | |||
DOI_LINK | 10.1109/JBHI.2012.2237035 | ||
FUNDING_BODY | |||
GRANT_DETAILS |