Skip to main content

MulPi: A Multi-class and Patient-independent Epileptic Seizure Classifier with Co-designed Input-stationary Computing-in-SRAM

Publication ,  Journal Article
Kim, B; Huang, Q; Taylor, B; Zheng, Q; Ku, J; Chen, Y; Li, H
Published in: IEEE Transactions on Biomedical Circuits and Systems
January 1, 2025

Unprovoked seizures have threatened epilepsy patients over 70 million. Automated classification to detect and predict seizures could bring seizure-free lives to epilepsy patients, delivering them from fatal danger and increasing the quality of life. Authentic detection and prediction of seizures require 1) multi-class (Mul) and 2) patient-independent (Pi) classification. Recent implementable chips for seizure classification rarely satisfy the two requirements due to restricted resources in small chips; therefore, high efficiency is imperative along with accuracy. This paper introduces an efficient MulPi chip, fabricated for the first time to simultaneously fulfill multi-class and patient independence, based on a co-design approach. We develop a 5-layer convolutional neural network (CNN), MulPiCNN, with advanced training techniques for lightness and accuracy. At the hardware level, our SRAM-based chip leverages computingin- memory (CIM) for efficiency. The fabricated MulPi chip is distinguished from prior CIMs in two folds, namely ISRW-CIM: a) input-stationary (IS) CIM for resource-saving, and b) rowwise (RW) computing to address a challenge of SRAM CIM, empowered by our novel 2T-Hadamard product unit (HPU). MulPi outperforms state-of-the-art chips with 98.5% sensitivity and 99.2% specificity, classifying in 0.12s and 0.348mm2

Duke Scholars

Published In

IEEE Transactions on Biomedical Circuits and Systems

DOI

EISSN

1940-9990

ISSN

1932-4545

Publication Date

January 1, 2025

Related Subject Headings

  • Electrical & Electronic Engineering
  • 4009 Electronics, sensors and digital hardware
  • 4003 Biomedical engineering
  • 0906 Electrical and Electronic Engineering
  • 0903 Biomedical Engineering
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Kim, B., Huang, Q., Taylor, B., Zheng, Q., Ku, J., Chen, Y., & Li, H. (2025). MulPi: A Multi-class and Patient-independent Epileptic Seizure Classifier with Co-designed Input-stationary Computing-in-SRAM. IEEE Transactions on Biomedical Circuits and Systems. https://doi.org/10.1109/TBCAS.2025.3579273
Kim, B., Q. Huang, B. Taylor, Q. Zheng, J. Ku, Y. Chen, and H. Li. “MulPi: A Multi-class and Patient-independent Epileptic Seizure Classifier with Co-designed Input-stationary Computing-in-SRAM.” IEEE Transactions on Biomedical Circuits and Systems, January 1, 2025. https://doi.org/10.1109/TBCAS.2025.3579273.
Kim B, Huang Q, Taylor B, Zheng Q, Ku J, Chen Y, et al. MulPi: A Multi-class and Patient-independent Epileptic Seizure Classifier with Co-designed Input-stationary Computing-in-SRAM. IEEE Transactions on Biomedical Circuits and Systems. 2025 Jan 1;
Kim, B., et al. “MulPi: A Multi-class and Patient-independent Epileptic Seizure Classifier with Co-designed Input-stationary Computing-in-SRAM.” IEEE Transactions on Biomedical Circuits and Systems, Jan. 2025. Scopus, doi:10.1109/TBCAS.2025.3579273.
Kim B, Huang Q, Taylor B, Zheng Q, Ku J, Chen Y, Li H. MulPi: A Multi-class and Patient-independent Epileptic Seizure Classifier with Co-designed Input-stationary Computing-in-SRAM. IEEE Transactions on Biomedical Circuits and Systems. 2025 Jan 1;

Published In

IEEE Transactions on Biomedical Circuits and Systems

DOI

EISSN

1940-9990

ISSN

1932-4545

Publication Date

January 1, 2025

Related Subject Headings

  • Electrical & Electronic Engineering
  • 4009 Electronics, sensors and digital hardware
  • 4003 Biomedical engineering
  • 0906 Electrical and Electronic Engineering
  • 0903 Biomedical Engineering