An Ensemble of Hyperdimensional Classifiers: Hardware-Friendly Short-Latency Seizure Detection With Automatic iEEG Electrode Selection.
Saved in:
| Title: | An Ensemble of Hyperdimensional Classifiers: Hardware-Friendly Short-Latency Seizure Detection With Automatic iEEG Electrode Selection. |
|---|---|
| Authors: | Burrello, Alessio1 (AUTHOR) alessio.burrello@unibo.it, Benatti, Simone1 (AUTHOR) simone.benatti@unibo.it, Schindler, Kaspar2 (AUTHOR) kaspar.schindler@insel.ch, Benini, Luca3 (AUTHOR) lbenini@iis.ee.ethz.ch, Rahimi, Abbas4 (AUTHOR) abbas@ee.ethz.ch |
| Source: | IEEE Journal of Biomedical & Health Informatics. Apr2021, Vol. 25 Issue 4, p935-946. 12p. |
| Subjects: | Electrodes, Epilepsy, Seizures (Medicine) |
| Abstract: | We propose a new algorithm for detecting epileptic seizures. Our algorithm first extracts three features, namely mean amplitude, line length, and local binary patterns that are fed to an ensemble of classifiers using hyperdimensional (HD) computing. These features are embedded into prototype vectors representing ictal (during seizures) and interictal (between seizures) brain states are constructed. These vectors can be computed at different spatial scales ranging from a single electrode up to many electrodes. This flexibility allows our algorithm to identify the electrodes that discriminate best between ictal and interictal brain states. We assess our algorithm on the SWEC-ETHZ iEEG dataset that includes 99 short-time iEEG seizures recorded with 36 to 100 electrodes from 16 drug-resistant epilepsy patients. Using k-fold cross-validation and all electrodes, our algorithm surpasses state-of-the-art algorithms yielding significantly shorter latency (8.81 s vs. 11.57 s) in seizure onset detection, and higher specificity (97.31% vs. 94.84%) and accuracy (96.85% vs. 95.42%). We can further reduce the latency of our algorithm to 3.74 s by allowing a slightly higher percentage of false alarms (2% specificity loss). Using only the top 10% of the electrodes ranked by our algorithm, we still maintain superior latency, sensitivity, and specificity compared to the other algorithms with all the electrodes. We finally demonstrate the suitability of our algorithm to deployment on low-cost embedded hardware platforms, thanks to its robustness to noise/artifacts affecting the signal, its low computational complexity, and the small memory-footprint on a RISC-V microcontroller. [ABSTRACT FROM AUTHOR] |
| Copyright of IEEE Journal of Biomedical & Health Informatics is the property of IEEE and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 149773489 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: An Ensemble of Hyperdimensional Classifiers: Hardware-Friendly Short-Latency Seizure Detection With Automatic iEEG Electrode Selection. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Burrello%2C+Alessio%22">Burrello, Alessio</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> alessio.burrello@unibo.it</i><br /><searchLink fieldCode="AR" term="%22Benatti%2C+Simone%22">Benatti, Simone</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> simone.benatti@unibo.it</i><br /><searchLink fieldCode="AR" term="%22Schindler%2C+Kaspar%22">Schindler, Kaspar</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> kaspar.schindler@insel.ch</i><br /><searchLink fieldCode="AR" term="%22Benini%2C+Luca%22">Benini, Luca</searchLink><relatesTo>3</relatesTo> (AUTHOR)<i> lbenini@iis.ee.ethz.ch</i><br /><searchLink fieldCode="AR" term="%22Rahimi%2C+Abbas%22">Rahimi, Abbas</searchLink><relatesTo>4</relatesTo> (AUTHOR)<i> abbas@ee.ethz.ch</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22IEEE+Journal+of+Biomedical+%26+Health+Informatics%22">IEEE Journal of Biomedical & Health Informatics</searchLink>. Apr2021, Vol. 25 Issue 4, p935-946. 12p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Electrodes%22">Electrodes</searchLink><br /><searchLink fieldCode="DE" term="%22Epilepsy%22">Epilepsy</searchLink><br /><searchLink fieldCode="DE" term="%22Seizures+%28Medicine%29%22">Seizures (Medicine)</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: We propose a new algorithm for detecting epileptic seizures. Our algorithm first extracts three features, namely mean amplitude, line length, and local binary patterns that are fed to an ensemble of classifiers using hyperdimensional (HD) computing. These features are embedded into prototype vectors representing ictal (during seizures) and interictal (between seizures) brain states are constructed. These vectors can be computed at different spatial scales ranging from a single electrode up to many electrodes. This flexibility allows our algorithm to identify the electrodes that discriminate best between ictal and interictal brain states. We assess our algorithm on the SWEC-ETHZ iEEG dataset that includes 99 short-time iEEG seizures recorded with 36 to 100 electrodes from 16 drug-resistant epilepsy patients. Using k-fold cross-validation and all electrodes, our algorithm surpasses state-of-the-art algorithms yielding significantly shorter latency (8.81 s vs. 11.57 s) in seizure onset detection, and higher specificity (97.31% vs. 94.84%) and accuracy (96.85% vs. 95.42%). We can further reduce the latency of our algorithm to 3.74 s by allowing a slightly higher percentage of false alarms (2% specificity loss). Using only the top 10% of the electrodes ranked by our algorithm, we still maintain superior latency, sensitivity, and specificity compared to the other algorithms with all the electrodes. We finally demonstrate the suitability of our algorithm to deployment on low-cost embedded hardware platforms, thanks to its robustness to noise/artifacts affecting the signal, its low computational complexity, and the small memory-footprint on a RISC-V microcontroller. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of IEEE Journal of Biomedical & Health Informatics is the property of IEEE and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=149773489 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1109/JBHI.2020.3022211 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 12 StartPage: 935 Subjects: – SubjectFull: Electrodes Type: general – SubjectFull: Epilepsy Type: general – SubjectFull: Seizures (Medicine) Type: general Titles: – TitleFull: An Ensemble of Hyperdimensional Classifiers: Hardware-Friendly Short-Latency Seizure Detection With Automatic iEEG Electrode Selection. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Burrello, Alessio – PersonEntity: Name: NameFull: Benatti, Simone – PersonEntity: Name: NameFull: Schindler, Kaspar – PersonEntity: Name: NameFull: Benini, Luca – PersonEntity: Name: NameFull: Rahimi, Abbas IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 04 Text: Apr2021 Type: published Y: 2021 Identifiers: – Type: issn-print Value: 21682194 Numbering: – Type: volume Value: 25 – Type: issue Value: 4 Titles: – TitleFull: IEEE Journal of Biomedical & Health Informatics Type: main |
| ResultId | 1 |
