Tailoring SVM Inference for Resource-Efficient ECG-Based Epilepsy Monitors
(2019) 22nd Design, Automation and Test in Europe Conference and Exhibition, DATE 2019 p.948-951- Abstract
Event detection and classification algorithms are resilient towards aggressive resource-aware optimisations. In this paper, we leverage this characteristic in the context of smart health monitoring systems. In more detail, we study the attainable benefits resulting from tailoring Support Vector Machine (SVM) inference engines devoted to the detection of epileptic seizures from ECG-derived features. We conceive and explore multiple optimisations, each effectively reducing resource budgets while minimally impacting classification performance. These strategies can be seamlessly combined, which results in 12.5X and 16X gains in energy and area, respectively, with a negligible loss, 3.2% in classification performance.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/7f1259fd-dc20-4984-adb2-6284e19c2b18
- author
- Ferretti, Lorenzo ; Ansaloni, Giovanni ; Pozzi, Laura ; Aminifar, Amir LU ; Atienza, David ; Cammoun, Leila and Ryvlin, Philippe
- publishing date
- 2019-05-14
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- Algorithmic optimisation, Seizure detection, Ultra-low-power design, Wireless Body Sensor Nodes
- host publication
- Proceedings of the 2019 Design, Automation and Test in Europe Conference and Exhibition, DATE 2019
- article number
- 8714858
- pages
- 4 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- 22nd Design, Automation and Test in Europe Conference and Exhibition, DATE 2019
- conference location
- Florence, Italy
- conference dates
- 2019-03-25 - 2019-03-29
- external identifiers
-
- scopus:85066610552
- ISBN
- 9783981926323
- DOI
- 10.23919/DATE.2019.8714858
- language
- English
- LU publication?
- no
- additional info
- Publisher Copyright: © 2019 EDAA.
- id
- 7f1259fd-dc20-4984-adb2-6284e19c2b18
- date added to LUP
- 2022-02-05 01:23:48
- date last changed
- 2022-04-22 07:31:27
@inproceedings{7f1259fd-dc20-4984-adb2-6284e19c2b18, abstract = {{<p>Event detection and classification algorithms are resilient towards aggressive resource-aware optimisations. In this paper, we leverage this characteristic in the context of smart health monitoring systems. In more detail, we study the attainable benefits resulting from tailoring Support Vector Machine (SVM) inference engines devoted to the detection of epileptic seizures from ECG-derived features. We conceive and explore multiple optimisations, each effectively reducing resource budgets while minimally impacting classification performance. These strategies can be seamlessly combined, which results in 12.5X and 16X gains in energy and area, respectively, with a negligible loss, 3.2% in classification performance.</p>}}, author = {{Ferretti, Lorenzo and Ansaloni, Giovanni and Pozzi, Laura and Aminifar, Amir and Atienza, David and Cammoun, Leila and Ryvlin, Philippe}}, booktitle = {{Proceedings of the 2019 Design, Automation and Test in Europe Conference and Exhibition, DATE 2019}}, isbn = {{9783981926323}}, keywords = {{Algorithmic optimisation; Seizure detection; Ultra-low-power design; Wireless Body Sensor Nodes}}, language = {{eng}}, month = {{05}}, pages = {{948--951}}, publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}}, title = {{Tailoring SVM Inference for Resource-Efficient ECG-Based Epilepsy Monitors}}, url = {{http://dx.doi.org/10.23919/DATE.2019.8714858}}, doi = {{10.23919/DATE.2019.8714858}}, year = {{2019}}, }