Compression-ratio-based seizure detection

Chung Lin Sha, Taehoon Kim, N. Sertac Artan, H. Jonathan Chao

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

For wireless seizure monitoring devices seizure detection and data compression are two critical tasks that need to be carefully designed against a very tight power budget to maximize the battery life. These two tasks are usually considered separately and algorithms for each are developed separately. In this paper, we consider having a single low-power algorithm for implementing both seizure detection and data compression. Towards that end, we investigated compression ratio (CR) as a seizure marker and show that the seizure detection can be achieved as a by-product of compression with no additional cost, and thus overall system power can be reduced. We show that the proposed method, the CR-based seizure detection has promising performance with 88% seizure detection accuracy, and 5.5 false positives per hour (FPh) without any computation overhead.

Original languageEnglish (US)
Title of host publication2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2013
Pages1009-1012
Number of pages4
DOIs
StatePublished - 2013
Event2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2013 - Osaka, Japan
Duration: Jul 3 2013Jul 7 2013

Other

Other2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2013
CountryJapan
CityOsaka
Period7/3/137/7/13

Fingerprint

Data compression
Seizures
Byproducts
Compaction
Data Compression
Monitoring
Costs
Budgets
Costs and Cost Analysis
Equipment and Supplies

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Biomedical Engineering
  • Health Informatics

Cite this

Sha, C. L., Kim, T., Artan, N. S., & Chao, H. J. (2013). Compression-ratio-based seizure detection. In 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2013 (pp. 1009-1012). [6609674] https://doi.org/10.1109/EMBC.2013.6609674

Compression-ratio-based seizure detection. / Sha, Chung Lin; Kim, Taehoon; Artan, N. Sertac; Chao, H. Jonathan.

2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2013. 2013. p. 1009-1012 6609674.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sha, CL, Kim, T, Artan, NS & Chao, HJ 2013, Compression-ratio-based seizure detection. in 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2013., 6609674, pp. 1009-1012, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2013, Osaka, Japan, 7/3/13. https://doi.org/10.1109/EMBC.2013.6609674
Sha CL, Kim T, Artan NS, Chao HJ. Compression-ratio-based seizure detection. In 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2013. 2013. p. 1009-1012. 6609674 https://doi.org/10.1109/EMBC.2013.6609674
Sha, Chung Lin ; Kim, Taehoon ; Artan, N. Sertac ; Chao, H. Jonathan. / Compression-ratio-based seizure detection. 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2013. 2013. pp. 1009-1012
@inproceedings{f57f6e46235744c1961153fe30ac5bd3,
title = "Compression-ratio-based seizure detection",
abstract = "For wireless seizure monitoring devices seizure detection and data compression are two critical tasks that need to be carefully designed against a very tight power budget to maximize the battery life. These two tasks are usually considered separately and algorithms for each are developed separately. In this paper, we consider having a single low-power algorithm for implementing both seizure detection and data compression. Towards that end, we investigated compression ratio (CR) as a seizure marker and show that the seizure detection can be achieved as a by-product of compression with no additional cost, and thus overall system power can be reduced. We show that the proposed method, the CR-based seizure detection has promising performance with 88{\%} seizure detection accuracy, and 5.5 false positives per hour (FPh) without any computation overhead.",
author = "Sha, {Chung Lin} and Taehoon Kim and Artan, {N. Sertac} and Chao, {H. Jonathan}",
year = "2013",
doi = "10.1109/EMBC.2013.6609674",
language = "English (US)",
isbn = "9781457702167",
pages = "1009--1012",
booktitle = "2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2013",

}

TY - GEN

T1 - Compression-ratio-based seizure detection

AU - Sha, Chung Lin

AU - Kim, Taehoon

AU - Artan, N. Sertac

AU - Chao, H. Jonathan

PY - 2013

Y1 - 2013

N2 - For wireless seizure monitoring devices seizure detection and data compression are two critical tasks that need to be carefully designed against a very tight power budget to maximize the battery life. These two tasks are usually considered separately and algorithms for each are developed separately. In this paper, we consider having a single low-power algorithm for implementing both seizure detection and data compression. Towards that end, we investigated compression ratio (CR) as a seizure marker and show that the seizure detection can be achieved as a by-product of compression with no additional cost, and thus overall system power can be reduced. We show that the proposed method, the CR-based seizure detection has promising performance with 88% seizure detection accuracy, and 5.5 false positives per hour (FPh) without any computation overhead.

AB - For wireless seizure monitoring devices seizure detection and data compression are two critical tasks that need to be carefully designed against a very tight power budget to maximize the battery life. These two tasks are usually considered separately and algorithms for each are developed separately. In this paper, we consider having a single low-power algorithm for implementing both seizure detection and data compression. Towards that end, we investigated compression ratio (CR) as a seizure marker and show that the seizure detection can be achieved as a by-product of compression with no additional cost, and thus overall system power can be reduced. We show that the proposed method, the CR-based seizure detection has promising performance with 88% seizure detection accuracy, and 5.5 false positives per hour (FPh) without any computation overhead.

UR - http://www.scopus.com/inward/record.url?scp=84886460485&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84886460485&partnerID=8YFLogxK

U2 - 10.1109/EMBC.2013.6609674

DO - 10.1109/EMBC.2013.6609674

M3 - Conference contribution

SN - 9781457702167

SP - 1009

EP - 1012

BT - 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2013

ER -