Towards Long-term Non-invasive Monitoring for Epilepsy via Wearable EEG Devices

We present the implementation of seizure detection algorithms based on a minimal number of EEG channels on a parallel ultra-low-power embedded platform. The analyses are based on the CHB-MIT dataset, and include explorations of different classification approaches (Support Vector Machines, Random For...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2021 IEEE Biomedical Circuits and Systems Conference (BioCAS) S. 01 - 04
Hauptverfasser: Ingolfsson, Thorir Mar, Cossettini, Andrea, Wang, Xiaying, Tabanelli, Enrico, Tagliavini, Giuseppe, Ryvlin, Philippe, Benini, Luca, Benatti, Simone
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 07.10.2021
Schlagworte:
deep learning
Electroencephalography
Epilepsy
healthcare
Inference algorithms
machine learning
Prediction algorithms
Sensitivity
smart edge computing
Support vector machines
time series classification
Wearable computers
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract We present the implementation of seizure detection algorithms based on a minimal number of EEG channels on a parallel ultra-low-power embedded platform. The analyses are based on the CHB-MIT dataset, and include explorations of different classification approaches (Support Vector Machines, Random Forest, Extra Trees, AdaBoost) and different pre/post-processing techniques to maximize sensitivity while guaranteeing no false alarms. We analyze global and subject-specific approaches, considering all 23-electrodes or only 4 temporal channels. For 8 s window size and subject-specific approach, we report zero false positives and 100% sensitivity. These algorithms are parallelized and optimized for a parallel ultra-low power (PULP) platform, enabling 300h of continuous monitoring on a 300 mAh battery, in a wearable form factor and power budget. These results pave the way for the implementation of affordable, wearable, long-term epilepsy monitoring solutions with low false-positive rates and high sensitivity, meeting both patient and caregiver requirements.
AbstractList We present the implementation of seizure detection algorithms based on a minimal number of EEG channels on a parallel ultra-low-power embedded platform. The analyses are based on the CHB-MIT dataset, and include explorations of different classification approaches (Support Vector Machines, Random Forest, Extra Trees, AdaBoost) and different pre/post-processing techniques to maximize sensitivity while guaranteeing no false alarms. We analyze global and subject-specific approaches, considering all 23-electrodes or only 4 temporal channels. For 8 s window size and subject-specific approach, we report zero false positives and 100% sensitivity. These algorithms are parallelized and optimized for a parallel ultra-low power (PULP) platform, enabling 300h of continuous monitoring on a 300 mAh battery, in a wearable form factor and power budget. These results pave the way for the implementation of affordable, wearable, long-term epilepsy monitoring solutions with low false-positive rates and high sensitivity, meeting both patient and caregiver requirements.
Author Wang, Xiaying
Tabanelli, Enrico
Benatti, Simone
Benini, Luca
Ryvlin, Philippe
Ingolfsson, Thorir Mar
Cossettini, Andrea
Tagliavini, Giuseppe
Author_xml – sequence: 1
  givenname: Thorir Mar
  surname: Ingolfsson
  fullname: Ingolfsson, Thorir Mar
  email: thoriri@iis.ee.ethz.ch
  organization: Integrated Systems Laboratory,ETH Zürich,Zürich,Switzerland
– sequence: 2
  givenname: Andrea
  surname: Cossettini
  fullname: Cossettini, Andrea
  organization: Integrated Systems Laboratory,ETH Zürich,Zürich,Switzerland
– sequence: 3
  givenname: Xiaying
  surname: Wang
  fullname: Wang, Xiaying
  organization: Integrated Systems Laboratory,ETH Zürich,Zürich,Switzerland
– sequence: 4
  givenname: Enrico
  surname: Tabanelli
  fullname: Tabanelli, Enrico
  organization: University of Bologna,DEI,Bologna,Italy
– sequence: 5
  givenname: Giuseppe
  surname: Tagliavini
  fullname: Tagliavini, Giuseppe
  organization: University of Bologna,DEI,Bologna,Italy
– sequence: 6
  givenname: Philippe
  surname: Ryvlin
  fullname: Ryvlin, Philippe
  organization: Lausanne University Hospital (CHUV),Switzerland
– sequence: 7
  givenname: Luca
  surname: Benini
  fullname: Benini, Luca
  organization: Integrated Systems Laboratory,ETH Zürich,Zürich,Switzerland
– sequence: 8
  givenname: Simone
  surname: Benatti
  fullname: Benatti, Simone
  organization: University of Bologna,DEI,Bologna,Italy
BookMark eNotj8tOwzAUBY0EC1r4Ajb-gQQ_bh5elhBapEAXFLGs7Pi6spTalRMF9e-pRBdHM6uRzoLchhiQEMpZzjlTzy8-NqsvUEqIXDDBc1UCKFA3ZMErUV_GoLon21381cmOtIvhkE2YjvQzhsyHWY9-RvoRg59i8uFAXUy0PfkBT-OZzl7TH9RJmwFp267pK86-x_GB3Dk9jPh45ZJ8v7W7ZpN12_V7s-oyLwo5Za4sBSu0UT1ajmAK17OLFNYaVlnQSlmwfVXa2piqBGklE-h4oQF6J7GWS_L03_WIuD8lf9TpvL9-lH88Wk3o
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/BioCAS49922.2021.9644949
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 1728172047
9781728172040
EndPage 04
ExternalDocumentID 9644949
Genre orig-research
GrantInformation_xml – fundername: Swiss National Science Foundation (Project PEDESITE)
  grantid: agreement
  funderid: 10.13039/501100001711
GroupedDBID 6IE
6IL
CBEJK
RIE
RIL
ID FETCH-LOGICAL-i253t-f66205ab9ced1e4b5fc0d1e5ddb07d4a99d4dc76d8bb7643d302ef15a44cf3e83
IEDL.DBID RIE
ISICitedReferencesCount 14
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000837980700023&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Thu Jun 29 18:37:53 EDT 2023
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i253t-f66205ab9ced1e4b5fc0d1e5ddb07d4a99d4dc76d8bb7643d302ef15a44cf3e83
OpenAccessLink https://ieeexplore.ieee.org/document/9644949
PageCount 4
ParticipantIDs ieee_primary_9644949
PublicationCentury 2000
PublicationDate 2021-Oct.-7
PublicationDateYYYYMMDD 2021-10-07
PublicationDate_xml – month: 10
  year: 2021
  text: 2021-Oct.-7
  day: 07
PublicationDecade 2020
PublicationTitle 2021 IEEE Biomedical Circuits and Systems Conference (BioCAS)
PublicationTitleAbbrev BIOCAS
PublicationYear 2021
Publisher IEEE
Publisher_xml – name: IEEE
Score 1.9240731
Snippet We present the implementation of seizure detection algorithms based on a minimal number of EEG channels on a parallel ultra-low-power embedded platform. The...
SourceID ieee
SourceType Publisher
StartPage 01
SubjectTerms deep learning
Electroencephalography
Epilepsy
healthcare
Inference algorithms
machine learning
Prediction algorithms
Sensitivity
smart edge computing
Support vector machines
time series classification
Wearable computers
Title Towards Long-term Non-invasive Monitoring for Epilepsy via Wearable EEG Devices
URI https://ieeexplore.ieee.org/document/9644949
WOSCitedRecordID wos000837980700023&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA5t8eBJpRW1Kjl4NO0-spudo9atHqQWrNhbySYT2ctu6Qv89yZprQhevIUQCEwyr-T7Zgi5UZHSKLKQobC5CZcYMyg4Mm1kAI58DUb7ZhNiNMqmUxg3yO2eC4OIHnyGPTf0f_m6Vmv3VNYH67yBQ5M0hUi3XK1vcE4A_fuyHty9cldo1eZ9UdjbLf_VN8W7jeHR_zY8Jp0f_h0d7z3LCWlg1SYvE49wXdLnuvpgzqLSUV2xstpIB0GnW-10z3TUBqI0n1t9ny8_6aaU9N3eZ8eRonn-SB_QW4cOeRvmk8ET27VDYGWUxCtm0jQKElmAQh0iLxKjAjtItC4CobkE0FwrkeqsKIQNNHQcRGjCRHKuTIxZfEpaVV3hGaEg0aRSIBjOuQEtM2kiY48T3EdkWJyTthPGbL6teDHbyeHi7-kuOXTy9hA3cUlaq8Uar8iB2qzK5eLaH9MX6ReX7g
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA61CnpSacW3OXg07T6ym81R69aKdS1YsbeSTSayl93SF_jvTdJaEbx4C4EQmGReyffNIHQtA6mAJT4BZnITKiAkPKdAlBYet-RrrpVrNsGyLBmN-KCGbjZcGABw4DNo2aH7y1eVXNinsjY3zptTvoW2I0oDb8XW-obneLx9V1Sd21dqS62azC_wW-sFvzqnOMfR3f_flgeo-cPAw4ONbzlENSgb6GXoMK4z3K_KD2JtKs6qkhTlUlgQOl7pp32owyYUxenEaPxk9omXhcDv5kZblhRO0wd8D84-NNFbNx12emTdEIEUQRTOiY7jwItEziUoH2geaemZQaRU7jFFBeeKKslileQ5M6GGCr0AtB8JSqUOIQmPUL2sSjhGmAvQsWDANaVUcyUSoQNtDpTbr0g_P0ENK4zxZFXzYryWw-nf01dotzd87o_7j9nTGdqzsneAN3aO6vPpAi7QjlzOi9n00h3ZF_2EmzU
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2021+IEEE+Biomedical+Circuits+and+Systems+Conference+%28BioCAS%29&rft.atitle=Towards+Long-term+Non-invasive+Monitoring+for+Epilepsy+via+Wearable+EEG+Devices&rft.au=Ingolfsson%2C+Thorir+Mar&rft.au=Cossettini%2C+Andrea&rft.au=Wang%2C+Xiaying&rft.au=Tabanelli%2C+Enrico&rft.date=2021-10-07&rft.pub=IEEE&rft.spage=01&rft.epage=04&rft_id=info:doi/10.1109%2FBioCAS49922.2021.9644949&rft.externalDocID=9644949