MulPi: A Multi-Class and Patient-Independent Computing-in-SRAM Seizure Classifier

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 multiclass 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 computing-in-memory (CIM) for efficiency. The fabricated MulPi chip is distinguished from prior CIMs in two folds, namely ISRWCIM: a) input-stationary (IS) CIM for resource-saving, and b) row-wise (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 $\mathbf{9 8. 5 \%}$ sensitivity and 99.2% specificity, classifying in 0.12 s and $0.348 \mathrm{~mm}^{2}$.