Feature selection methods for accelerometry-based seizure detection in children
Abstract We investigate the application of feature selection methods and their influence on distinguishing nocturnal motor seizures in epileptic children from normal nocturnal movements using accelerometry signals. We studied two feature selection methods applied one after the other to reduce the co...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Milošević, Milica [verfasserIn] |
|---|
| Format: |
Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2016 |
|---|
| Schlagwörter: |
|---|
| Anmerkung: |
© International Federation for Medical and Biological Engineering 2016 |
|---|
| Übergeordnetes Werk: |
Enthalten in: Medical & biological engineering & computing - Springer Berlin Heidelberg, 1977, 55(2016), 1 vom: 22. Apr., Seite 151-165 |
|---|---|
| Übergeordnetes Werk: |
volume:55 ; year:2016 ; number:1 ; day:22 ; month:04 ; pages:151-165 |
| Links: |
|---|
| DOI / URN: |
10.1007/s11517-016-1506-9 |
|---|
| Katalog-ID: |
OLC2038695539 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | OLC2038695539 | ||
| 003 | DE-627 | ||
| 005 | 20230509071341.0 | ||
| 007 | tu | ||
| 008 | 200819s2016 xx ||||| 00| ||eng c | ||
| 024 | 7 | |a 10.1007/s11517-016-1506-9 |2 doi | |
| 035 | |a (DE-627)OLC2038695539 | ||
| 035 | |a (DE-He213)s11517-016-1506-9-p | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | 4 | |a 610 |a 660 |a 570 |q VZ |
| 084 | |a 12 |2 ssgn | ||
| 100 | 1 | |a Milošević, Milica |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Feature selection methods for accelerometry-based seizure detection in children |
| 264 | 1 | |c 2016 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ohne Hilfsmittel zu benutzen |b n |2 rdamedia | ||
| 338 | |a Band |b nc |2 rdacarrier | ||
| 500 | |a © International Federation for Medical and Biological Engineering 2016 | ||
| 520 | |a Abstract We investigate the application of feature selection methods and their influence on distinguishing nocturnal motor seizures in epileptic children from normal nocturnal movements using accelerometry signals. We studied two feature selection methods applied one after the other to reduce the complexity and computation costs of least-squares support vector machine (LS-SVM) models. Simultaneous feature selection analyses were performed for each seizure type individually and jointly. Starting from 140 features, a filter method based on mutual information was applied to remove irrelevant and redundant features. The obtained subset was further reduced through a wrapper feature selection strategy using an LS-SVM classifier with both forward search and backward elimination. The discriminative power of each feature subset was evaluated on the test data in terms of the area under the receiver operating characteristic curve, sensitivity, and false detection rate per hour. We showed that, by using only a filter method for feature selection, it was possible to obtain classification results of comparable or slightly reduced performance with respect to the complete feature set. The attained results could facilitate further development of accelerometry-based seizure detection and alarm systems. | ||
| 650 | 4 | |a Epilepsy | |
| 650 | 4 | |a Children | |
| 650 | 4 | |a Seizure detection | |
| 650 | 4 | |a Accelerometers | |
| 650 | 4 | |a Feature selection | |
| 700 | 1 | |a Van de Vel, Anouk |4 aut | |
| 700 | 1 | |a Cuppens, Kris |4 aut | |
| 700 | 1 | |a Bonroy, Bert |4 aut | |
| 700 | 1 | |a Ceulemans, Berten |4 aut | |
| 700 | 1 | |a Lagae, Lieven |4 aut | |
| 700 | 1 | |a Vanrumste, Bart |4 aut | |
| 700 | 1 | |a Van Huffel, Sabine |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Medical & biological engineering & computing |d Springer Berlin Heidelberg, 1977 |g 55(2016), 1 vom: 22. Apr., Seite 151-165 |w (DE-627)129858552 |w (DE-600)282327-5 |w (DE-576)015165507 |x 0140-0118 |7 nnns |
| 773 | 1 | 8 | |g volume:55 |g year:2016 |g number:1 |g day:22 |g month:04 |g pages:151-165 |
| 856 | 4 | 1 | |u https://doi.org/10.1007/s11517-016-1506-9 |z lizenzpflichtig |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a SYSFLAG_A | ||
| 912 | |a GBV_OLC | ||
| 912 | |a SSG-OLC-TEC | ||
| 912 | |a SSG-OLC-CHE | ||
| 912 | |a SSG-OLC-PHA | ||
| 912 | |a SSG-OLC-DE-84 | ||
| 912 | |a SSG-OPC-MAT | ||
| 912 | |a GBV_ILN_70 | ||
| 912 | |a GBV_ILN_2018 | ||
| 912 | |a GBV_ILN_4012 | ||
| 912 | |a GBV_ILN_4219 | ||
| 951 | |a AR | ||
| 952 | |d 55 |j 2016 |e 1 |b 22 |c 04 |h 151-165 | ||
| author_variant |
m m mm d v a v dva dvav k c kc b b bb b c bc l l ll b v bv h s v hs hsv |
|---|---|
| matchkey_str |
article:01400118:2016----::etrslcinehdfrceeoerbsdezr |
| hierarchy_sort_str |
2016 |
| publishDate |
2016 |
| allfields |
10.1007/s11517-016-1506-9 doi (DE-627)OLC2038695539 (DE-He213)s11517-016-1506-9-p DE-627 ger DE-627 rakwb eng 610 660 570 VZ 12 ssgn Milošević, Milica verfasserin aut Feature selection methods for accelerometry-based seizure detection in children 2016 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © International Federation for Medical and Biological Engineering 2016 Abstract We investigate the application of feature selection methods and their influence on distinguishing nocturnal motor seizures in epileptic children from normal nocturnal movements using accelerometry signals. We studied two feature selection methods applied one after the other to reduce the complexity and computation costs of least-squares support vector machine (LS-SVM) models. Simultaneous feature selection analyses were performed for each seizure type individually and jointly. Starting from 140 features, a filter method based on mutual information was applied to remove irrelevant and redundant features. The obtained subset was further reduced through a wrapper feature selection strategy using an LS-SVM classifier with both forward search and backward elimination. The discriminative power of each feature subset was evaluated on the test data in terms of the area under the receiver operating characteristic curve, sensitivity, and false detection rate per hour. We showed that, by using only a filter method for feature selection, it was possible to obtain classification results of comparable or slightly reduced performance with respect to the complete feature set. The attained results could facilitate further development of accelerometry-based seizure detection and alarm systems. Epilepsy Children Seizure detection Accelerometers Feature selection Van de Vel, Anouk aut Cuppens, Kris aut Bonroy, Bert aut Ceulemans, Berten aut Lagae, Lieven aut Vanrumste, Bart aut Van Huffel, Sabine aut Enthalten in Medical & biological engineering & computing Springer Berlin Heidelberg, 1977 55(2016), 1 vom: 22. Apr., Seite 151-165 (DE-627)129858552 (DE-600)282327-5 (DE-576)015165507 0140-0118 nnns volume:55 year:2016 number:1 day:22 month:04 pages:151-165 https://doi.org/10.1007/s11517-016-1506-9 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC SSG-OLC-CHE SSG-OLC-PHA SSG-OLC-DE-84 SSG-OPC-MAT GBV_ILN_70 GBV_ILN_2018 GBV_ILN_4012 GBV_ILN_4219 AR 55 2016 1 22 04 151-165 |
| spelling |
10.1007/s11517-016-1506-9 doi (DE-627)OLC2038695539 (DE-He213)s11517-016-1506-9-p DE-627 ger DE-627 rakwb eng 610 660 570 VZ 12 ssgn Milošević, Milica verfasserin aut Feature selection methods for accelerometry-based seizure detection in children 2016 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © International Federation for Medical and Biological Engineering 2016 Abstract We investigate the application of feature selection methods and their influence on distinguishing nocturnal motor seizures in epileptic children from normal nocturnal movements using accelerometry signals. We studied two feature selection methods applied one after the other to reduce the complexity and computation costs of least-squares support vector machine (LS-SVM) models. Simultaneous feature selection analyses were performed for each seizure type individually and jointly. Starting from 140 features, a filter method based on mutual information was applied to remove irrelevant and redundant features. The obtained subset was further reduced through a wrapper feature selection strategy using an LS-SVM classifier with both forward search and backward elimination. The discriminative power of each feature subset was evaluated on the test data in terms of the area under the receiver operating characteristic curve, sensitivity, and false detection rate per hour. We showed that, by using only a filter method for feature selection, it was possible to obtain classification results of comparable or slightly reduced performance with respect to the complete feature set. The attained results could facilitate further development of accelerometry-based seizure detection and alarm systems. Epilepsy Children Seizure detection Accelerometers Feature selection Van de Vel, Anouk aut Cuppens, Kris aut Bonroy, Bert aut Ceulemans, Berten aut Lagae, Lieven aut Vanrumste, Bart aut Van Huffel, Sabine aut Enthalten in Medical & biological engineering & computing Springer Berlin Heidelberg, 1977 55(2016), 1 vom: 22. Apr., Seite 151-165 (DE-627)129858552 (DE-600)282327-5 (DE-576)015165507 0140-0118 nnns volume:55 year:2016 number:1 day:22 month:04 pages:151-165 https://doi.org/10.1007/s11517-016-1506-9 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC SSG-OLC-CHE SSG-OLC-PHA SSG-OLC-DE-84 SSG-OPC-MAT GBV_ILN_70 GBV_ILN_2018 GBV_ILN_4012 GBV_ILN_4219 AR 55 2016 1 22 04 151-165 |
| allfields_unstemmed |
10.1007/s11517-016-1506-9 doi (DE-627)OLC2038695539 (DE-He213)s11517-016-1506-9-p DE-627 ger DE-627 rakwb eng 610 660 570 VZ 12 ssgn Milošević, Milica verfasserin aut Feature selection methods for accelerometry-based seizure detection in children 2016 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © International Federation for Medical and Biological Engineering 2016 Abstract We investigate the application of feature selection methods and their influence on distinguishing nocturnal motor seizures in epileptic children from normal nocturnal movements using accelerometry signals. We studied two feature selection methods applied one after the other to reduce the complexity and computation costs of least-squares support vector machine (LS-SVM) models. Simultaneous feature selection analyses were performed for each seizure type individually and jointly. Starting from 140 features, a filter method based on mutual information was applied to remove irrelevant and redundant features. The obtained subset was further reduced through a wrapper feature selection strategy using an LS-SVM classifier with both forward search and backward elimination. The discriminative power of each feature subset was evaluated on the test data in terms of the area under the receiver operating characteristic curve, sensitivity, and false detection rate per hour. We showed that, by using only a filter method for feature selection, it was possible to obtain classification results of comparable or slightly reduced performance with respect to the complete feature set. The attained results could facilitate further development of accelerometry-based seizure detection and alarm systems. Epilepsy Children Seizure detection Accelerometers Feature selection Van de Vel, Anouk aut Cuppens, Kris aut Bonroy, Bert aut Ceulemans, Berten aut Lagae, Lieven aut Vanrumste, Bart aut Van Huffel, Sabine aut Enthalten in Medical & biological engineering & computing Springer Berlin Heidelberg, 1977 55(2016), 1 vom: 22. Apr., Seite 151-165 (DE-627)129858552 (DE-600)282327-5 (DE-576)015165507 0140-0118 nnns volume:55 year:2016 number:1 day:22 month:04 pages:151-165 https://doi.org/10.1007/s11517-016-1506-9 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC SSG-OLC-CHE SSG-OLC-PHA SSG-OLC-DE-84 SSG-OPC-MAT GBV_ILN_70 GBV_ILN_2018 GBV_ILN_4012 GBV_ILN_4219 AR 55 2016 1 22 04 151-165 |
| allfieldsGer |
10.1007/s11517-016-1506-9 doi (DE-627)OLC2038695539 (DE-He213)s11517-016-1506-9-p DE-627 ger DE-627 rakwb eng 610 660 570 VZ 12 ssgn Milošević, Milica verfasserin aut Feature selection methods for accelerometry-based seizure detection in children 2016 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © International Federation for Medical and Biological Engineering 2016 Abstract We investigate the application of feature selection methods and their influence on distinguishing nocturnal motor seizures in epileptic children from normal nocturnal movements using accelerometry signals. We studied two feature selection methods applied one after the other to reduce the complexity and computation costs of least-squares support vector machine (LS-SVM) models. Simultaneous feature selection analyses were performed for each seizure type individually and jointly. Starting from 140 features, a filter method based on mutual information was applied to remove irrelevant and redundant features. The obtained subset was further reduced through a wrapper feature selection strategy using an LS-SVM classifier with both forward search and backward elimination. The discriminative power of each feature subset was evaluated on the test data in terms of the area under the receiver operating characteristic curve, sensitivity, and false detection rate per hour. We showed that, by using only a filter method for feature selection, it was possible to obtain classification results of comparable or slightly reduced performance with respect to the complete feature set. The attained results could facilitate further development of accelerometry-based seizure detection and alarm systems. Epilepsy Children Seizure detection Accelerometers Feature selection Van de Vel, Anouk aut Cuppens, Kris aut Bonroy, Bert aut Ceulemans, Berten aut Lagae, Lieven aut Vanrumste, Bart aut Van Huffel, Sabine aut Enthalten in Medical & biological engineering & computing Springer Berlin Heidelberg, 1977 55(2016), 1 vom: 22. Apr., Seite 151-165 (DE-627)129858552 (DE-600)282327-5 (DE-576)015165507 0140-0118 nnns volume:55 year:2016 number:1 day:22 month:04 pages:151-165 https://doi.org/10.1007/s11517-016-1506-9 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC SSG-OLC-CHE SSG-OLC-PHA SSG-OLC-DE-84 SSG-OPC-MAT GBV_ILN_70 GBV_ILN_2018 GBV_ILN_4012 GBV_ILN_4219 AR 55 2016 1 22 04 151-165 |
| allfieldsSound |
10.1007/s11517-016-1506-9 doi (DE-627)OLC2038695539 (DE-He213)s11517-016-1506-9-p DE-627 ger DE-627 rakwb eng 610 660 570 VZ 12 ssgn Milošević, Milica verfasserin aut Feature selection methods for accelerometry-based seizure detection in children 2016 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © International Federation for Medical and Biological Engineering 2016 Abstract We investigate the application of feature selection methods and their influence on distinguishing nocturnal motor seizures in epileptic children from normal nocturnal movements using accelerometry signals. We studied two feature selection methods applied one after the other to reduce the complexity and computation costs of least-squares support vector machine (LS-SVM) models. Simultaneous feature selection analyses were performed for each seizure type individually and jointly. Starting from 140 features, a filter method based on mutual information was applied to remove irrelevant and redundant features. The obtained subset was further reduced through a wrapper feature selection strategy using an LS-SVM classifier with both forward search and backward elimination. The discriminative power of each feature subset was evaluated on the test data in terms of the area under the receiver operating characteristic curve, sensitivity, and false detection rate per hour. We showed that, by using only a filter method for feature selection, it was possible to obtain classification results of comparable or slightly reduced performance with respect to the complete feature set. The attained results could facilitate further development of accelerometry-based seizure detection and alarm systems. Epilepsy Children Seizure detection Accelerometers Feature selection Van de Vel, Anouk aut Cuppens, Kris aut Bonroy, Bert aut Ceulemans, Berten aut Lagae, Lieven aut Vanrumste, Bart aut Van Huffel, Sabine aut Enthalten in Medical & biological engineering & computing Springer Berlin Heidelberg, 1977 55(2016), 1 vom: 22. Apr., Seite 151-165 (DE-627)129858552 (DE-600)282327-5 (DE-576)015165507 0140-0118 nnns volume:55 year:2016 number:1 day:22 month:04 pages:151-165 https://doi.org/10.1007/s11517-016-1506-9 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC SSG-OLC-CHE SSG-OLC-PHA SSG-OLC-DE-84 SSG-OPC-MAT GBV_ILN_70 GBV_ILN_2018 GBV_ILN_4012 GBV_ILN_4219 AR 55 2016 1 22 04 151-165 |
| language |
English |
| source |
Enthalten in Medical & biological engineering & computing 55(2016), 1 vom: 22. Apr., Seite 151-165 volume:55 year:2016 number:1 day:22 month:04 pages:151-165 |
| sourceStr |
Enthalten in Medical & biological engineering & computing 55(2016), 1 vom: 22. Apr., Seite 151-165 volume:55 year:2016 number:1 day:22 month:04 pages:151-165 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| topic_facet |
Epilepsy Children Seizure detection Accelerometers Feature selection |
| dewey-raw |
610 |
| isfreeaccess_bool |
false |
| container_title |
Medical & biological engineering & computing |
| authorswithroles_txt_mv |
Milošević, Milica @@aut@@ Van de Vel, Anouk @@aut@@ Cuppens, Kris @@aut@@ Bonroy, Bert @@aut@@ Ceulemans, Berten @@aut@@ Lagae, Lieven @@aut@@ Vanrumste, Bart @@aut@@ Van Huffel, Sabine @@aut@@ |
| publishDateDaySort_date |
2016-04-22T00:00:00Z |
| hierarchy_top_id |
129858552 |
| dewey-sort |
3610 |
| id |
OLC2038695539 |
| language_de |
englisch |
| fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">OLC2038695539</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230509071341.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">200819s2016 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s11517-016-1506-9</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2038695539</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s11517-016-1506-9-p</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">610</subfield><subfield code="a">660</subfield><subfield code="a">570</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">12</subfield><subfield code="2">ssgn</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Milošević, Milica</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Feature selection methods for accelerometry-based seizure detection in children</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2016</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">ohne Hilfsmittel zu benutzen</subfield><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Band</subfield><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© International Federation for Medical and Biological Engineering 2016</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract We investigate the application of feature selection methods and their influence on distinguishing nocturnal motor seizures in epileptic children from normal nocturnal movements using accelerometry signals. We studied two feature selection methods applied one after the other to reduce the complexity and computation costs of least-squares support vector machine (LS-SVM) models. Simultaneous feature selection analyses were performed for each seizure type individually and jointly. Starting from 140 features, a filter method based on mutual information was applied to remove irrelevant and redundant features. The obtained subset was further reduced through a wrapper feature selection strategy using an LS-SVM classifier with both forward search and backward elimination. The discriminative power of each feature subset was evaluated on the test data in terms of the area under the receiver operating characteristic curve, sensitivity, and false detection rate per hour. We showed that, by using only a filter method for feature selection, it was possible to obtain classification results of comparable or slightly reduced performance with respect to the complete feature set. The attained results could facilitate further development of accelerometry-based seizure detection and alarm systems.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Epilepsy</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Children</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Seizure detection</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Accelerometers</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Feature selection</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Van de Vel, Anouk</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Cuppens, Kris</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Bonroy, Bert</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Ceulemans, Berten</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Lagae, Lieven</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Vanrumste, Bart</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Van Huffel, Sabine</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Medical & biological engineering & computing</subfield><subfield code="d">Springer Berlin Heidelberg, 1977</subfield><subfield code="g">55(2016), 1 vom: 22. Apr., Seite 151-165</subfield><subfield code="w">(DE-627)129858552</subfield><subfield code="w">(DE-600)282327-5</subfield><subfield code="w">(DE-576)015165507</subfield><subfield code="x">0140-0118</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:55</subfield><subfield code="g">year:2016</subfield><subfield code="g">number:1</subfield><subfield code="g">day:22</subfield><subfield code="g">month:04</subfield><subfield code="g">pages:151-165</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s11517-016-1506-9</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_OLC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-TEC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-CHE</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-PHA</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-DE-84</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OPC-MAT</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2018</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4219</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">55</subfield><subfield code="j">2016</subfield><subfield code="e">1</subfield><subfield code="b">22</subfield><subfield code="c">04</subfield><subfield code="h">151-165</subfield></datafield></record></collection>
|
| author |
Milošević, Milica |
| spellingShingle |
Milošević, Milica ddc 610 ssgn 12 misc Epilepsy misc Children misc Seizure detection misc Accelerometers misc Feature selection Feature selection methods for accelerometry-based seizure detection in children |
| authorStr |
Milošević, Milica |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)129858552 |
| format |
Article |
| dewey-ones |
610 - Medicine & health 660 - Chemical engineering 570 - Life sciences; biology |
| delete_txt_mv |
keep |
| author_role |
aut aut aut aut aut aut aut aut |
| collection |
OLC |
| remote_str |
false |
| illustrated |
Not Illustrated |
| issn |
0140-0118 |
| topic_title |
610 660 570 VZ 12 ssgn Feature selection methods for accelerometry-based seizure detection in children Epilepsy Children Seizure detection Accelerometers Feature selection |
| topic |
ddc 610 ssgn 12 misc Epilepsy misc Children misc Seizure detection misc Accelerometers misc Feature selection |
| topic_unstemmed |
ddc 610 ssgn 12 misc Epilepsy misc Children misc Seizure detection misc Accelerometers misc Feature selection |
| topic_browse |
ddc 610 ssgn 12 misc Epilepsy misc Children misc Seizure detection misc Accelerometers misc Feature selection |
| format_facet |
Aufsätze Gedruckte Aufsätze |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
nc |
| hierarchy_parent_title |
Medical & biological engineering & computing |
| hierarchy_parent_id |
129858552 |
| dewey-tens |
610 - Medicine & health 660 - Chemical engineering 570 - Life sciences; biology |
| hierarchy_top_title |
Medical & biological engineering & computing |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)129858552 (DE-600)282327-5 (DE-576)015165507 |
| title |
Feature selection methods for accelerometry-based seizure detection in children |
| ctrlnum |
(DE-627)OLC2038695539 (DE-He213)s11517-016-1506-9-p |
| title_full |
Feature selection methods for accelerometry-based seizure detection in children |
| author_sort |
Milošević, Milica |
| journal |
Medical & biological engineering & computing |
| journalStr |
Medical & biological engineering & computing |
| lang_code |
eng |
| isOA_bool |
false |
| dewey-hundreds |
600 - Technology 500 - Science |
| recordtype |
marc |
| publishDateSort |
2016 |
| contenttype_str_mv |
txt |
| container_start_page |
151 |
| author_browse |
Milošević, Milica Van de Vel, Anouk Cuppens, Kris Bonroy, Bert Ceulemans, Berten Lagae, Lieven Vanrumste, Bart Van Huffel, Sabine |
| container_volume |
55 |
| class |
610 660 570 VZ 12 ssgn |
| format_se |
Aufsätze |
| author-letter |
Milošević, Milica |
| doi_str_mv |
10.1007/s11517-016-1506-9 |
| dewey-full |
610 660 570 |
| title_sort |
feature selection methods for accelerometry-based seizure detection in children |
| title_auth |
Feature selection methods for accelerometry-based seizure detection in children |
| abstract |
Abstract We investigate the application of feature selection methods and their influence on distinguishing nocturnal motor seizures in epileptic children from normal nocturnal movements using accelerometry signals. We studied two feature selection methods applied one after the other to reduce the complexity and computation costs of least-squares support vector machine (LS-SVM) models. Simultaneous feature selection analyses were performed for each seizure type individually and jointly. Starting from 140 features, a filter method based on mutual information was applied to remove irrelevant and redundant features. The obtained subset was further reduced through a wrapper feature selection strategy using an LS-SVM classifier with both forward search and backward elimination. The discriminative power of each feature subset was evaluated on the test data in terms of the area under the receiver operating characteristic curve, sensitivity, and false detection rate per hour. We showed that, by using only a filter method for feature selection, it was possible to obtain classification results of comparable or slightly reduced performance with respect to the complete feature set. The attained results could facilitate further development of accelerometry-based seizure detection and alarm systems. © International Federation for Medical and Biological Engineering 2016 |
| abstractGer |
Abstract We investigate the application of feature selection methods and their influence on distinguishing nocturnal motor seizures in epileptic children from normal nocturnal movements using accelerometry signals. We studied two feature selection methods applied one after the other to reduce the complexity and computation costs of least-squares support vector machine (LS-SVM) models. Simultaneous feature selection analyses were performed for each seizure type individually and jointly. Starting from 140 features, a filter method based on mutual information was applied to remove irrelevant and redundant features. The obtained subset was further reduced through a wrapper feature selection strategy using an LS-SVM classifier with both forward search and backward elimination. The discriminative power of each feature subset was evaluated on the test data in terms of the area under the receiver operating characteristic curve, sensitivity, and false detection rate per hour. We showed that, by using only a filter method for feature selection, it was possible to obtain classification results of comparable or slightly reduced performance with respect to the complete feature set. The attained results could facilitate further development of accelerometry-based seizure detection and alarm systems. © International Federation for Medical and Biological Engineering 2016 |
| abstract_unstemmed |
Abstract We investigate the application of feature selection methods and their influence on distinguishing nocturnal motor seizures in epileptic children from normal nocturnal movements using accelerometry signals. We studied two feature selection methods applied one after the other to reduce the complexity and computation costs of least-squares support vector machine (LS-SVM) models. Simultaneous feature selection analyses were performed for each seizure type individually and jointly. Starting from 140 features, a filter method based on mutual information was applied to remove irrelevant and redundant features. The obtained subset was further reduced through a wrapper feature selection strategy using an LS-SVM classifier with both forward search and backward elimination. The discriminative power of each feature subset was evaluated on the test data in terms of the area under the receiver operating characteristic curve, sensitivity, and false detection rate per hour. We showed that, by using only a filter method for feature selection, it was possible to obtain classification results of comparable or slightly reduced performance with respect to the complete feature set. The attained results could facilitate further development of accelerometry-based seizure detection and alarm systems. © International Federation for Medical and Biological Engineering 2016 |
| collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC SSG-OLC-CHE SSG-OLC-PHA SSG-OLC-DE-84 SSG-OPC-MAT GBV_ILN_70 GBV_ILN_2018 GBV_ILN_4012 GBV_ILN_4219 |
| container_issue |
1 |
| title_short |
Feature selection methods for accelerometry-based seizure detection in children |
| url |
https://doi.org/10.1007/s11517-016-1506-9 |
| remote_bool |
false |
| author2 |
Van de Vel, Anouk Cuppens, Kris Bonroy, Bert Ceulemans, Berten Lagae, Lieven Vanrumste, Bart Van Huffel, Sabine |
| author2Str |
Van de Vel, Anouk Cuppens, Kris Bonroy, Bert Ceulemans, Berten Lagae, Lieven Vanrumste, Bart Van Huffel, Sabine |
| ppnlink |
129858552 |
| mediatype_str_mv |
n |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| doi_str |
10.1007/s11517-016-1506-9 |
| up_date |
2024-07-03T19:54:27.584Z |
| _version_ |
1803588959034408960 |
| fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">OLC2038695539</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230509071341.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">200819s2016 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s11517-016-1506-9</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2038695539</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s11517-016-1506-9-p</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">610</subfield><subfield code="a">660</subfield><subfield code="a">570</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">12</subfield><subfield code="2">ssgn</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Milošević, Milica</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Feature selection methods for accelerometry-based seizure detection in children</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2016</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">ohne Hilfsmittel zu benutzen</subfield><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Band</subfield><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© International Federation for Medical and Biological Engineering 2016</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract We investigate the application of feature selection methods and their influence on distinguishing nocturnal motor seizures in epileptic children from normal nocturnal movements using accelerometry signals. We studied two feature selection methods applied one after the other to reduce the complexity and computation costs of least-squares support vector machine (LS-SVM) models. Simultaneous feature selection analyses were performed for each seizure type individually and jointly. Starting from 140 features, a filter method based on mutual information was applied to remove irrelevant and redundant features. The obtained subset was further reduced through a wrapper feature selection strategy using an LS-SVM classifier with both forward search and backward elimination. The discriminative power of each feature subset was evaluated on the test data in terms of the area under the receiver operating characteristic curve, sensitivity, and false detection rate per hour. We showed that, by using only a filter method for feature selection, it was possible to obtain classification results of comparable or slightly reduced performance with respect to the complete feature set. The attained results could facilitate further development of accelerometry-based seizure detection and alarm systems.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Epilepsy</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Children</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Seizure detection</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Accelerometers</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Feature selection</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Van de Vel, Anouk</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Cuppens, Kris</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Bonroy, Bert</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Ceulemans, Berten</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Lagae, Lieven</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Vanrumste, Bart</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Van Huffel, Sabine</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Medical & biological engineering & computing</subfield><subfield code="d">Springer Berlin Heidelberg, 1977</subfield><subfield code="g">55(2016), 1 vom: 22. Apr., Seite 151-165</subfield><subfield code="w">(DE-627)129858552</subfield><subfield code="w">(DE-600)282327-5</subfield><subfield code="w">(DE-576)015165507</subfield><subfield code="x">0140-0118</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:55</subfield><subfield code="g">year:2016</subfield><subfield code="g">number:1</subfield><subfield code="g">day:22</subfield><subfield code="g">month:04</subfield><subfield code="g">pages:151-165</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s11517-016-1506-9</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_OLC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-TEC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-CHE</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-PHA</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-DE-84</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OPC-MAT</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2018</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4219</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">55</subfield><subfield code="j">2016</subfield><subfield code="e">1</subfield><subfield code="b">22</subfield><subfield code="c">04</subfield><subfield code="h">151-165</subfield></datafield></record></collection>
|
| score |
7.4003057 |