Seizure Detection and Prediction by Parallel Memristive Convolutional Neural Networks

Li, Chenqi, Lammie, Corey, Dong, Xuening, Amirsoleimani, Amirali, Azghadi, Mostafa Rahimi, and Genov, Roman (2022) Seizure Detection and Prediction by Parallel Memristive Convolutional Neural Networks. IEEE Transactions on Biomedical Circuits and Systems, 16 (4). pp. 609-625.

[img] PDF (Published Version) - Published Version
Restricted to Repository staff only

View at Publisher Website: https://doi.org/10.1109/TBCAS.2022.31855...
 
10
2


Abstract

During the past two decades, epileptic seizure detection and prediction algorithms have evolved rapidly. However, despite significant performance improvements, their hardware implementation using conventional technologies, such as Complementary Metal–Oxide–Semiconductor (CMOS), in power and area-constrained settings remains a challenging task; especially when many recording channels are used. In this paper, we propose a novel low-latency parallel Convolutional Neural Network (CNN) architecture that has between 2-2,800x fewer network parameters compared to State-Of-The-Art (SOTA) CNN architectures and achieves 5-fold cross validation accuracy of 99.84% for epileptic seizure detection, and 99.01% and 97.54% for epileptic seizure prediction, when evaluated using the University of Bonn Electroencephalogram (EEG), CHB-MIT and SWEC-ETHZ seizure datasets, respectively. We subsequently implement our network onto analog crossbar arrays comprising Resistive Random-Access Memory (RRAM) devices, and provide a comprehensive benchmark by simulating, laying out, and determining hardware requirements of the CNN component of our system. We parallelize the execution of convolution layer kernels on separate analog crossbars to enable 2 orders of magnitude reduction in latency compared to SOTA hybrid Memristive-CMOS Deep Learning (DL) accelerators. Furthermore, we investigate the effects of non-idealities on our system and investigate Quantization Aware Training (QAT) to mitigate the performance degradation due to low Analog-to-Digital Converter (ADC)/Digital-to-Analog Converter (DAC) resolution. Finally, we propose a stuck weight offsetting methodology to mitigate performance degradation due to stuck RON/ROFF memristor weights, recovering up to 32% accuracy, without requiring retraining. The CNN component of our platform is estimated to consume approximately 2.791 W of power while occupying an area of 31.255 mm 2 in a 22 nm FDSOI CMOS process.

Item ID: 76604
Item Type: Article (Research - C1)
ISSN: 1940-9990
Keywords: CNN, Computer architecture, Convolution, Convolutional neural networks, EEG, Electroencephalography, Feature extraction, Hardware, Memristive Crossbar Array, Prediction algorithms, RRAM, Seizure Detection, Seizure Prediction
Related URLs:
Copyright Information: © 2022 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission.
Date Deposited: 06 Dec 2022 01:50
FoR Codes: 40 ENGINEERING > 4009 Electronics, sensors and digital hardware > 400901 Analog electronics and interfaces @ 30%
40 ENGINEERING > 4009 Electronics, sensors and digital hardware > 400908 Microelectronics @ 30%
46 INFORMATION AND COMPUTING SCIENCES > 4611 Machine learning > 461103 Deep learning @ 40%
SEO Codes: 20 HEALTH > 2001 Clinical health > 200101 Diagnosis of human diseases and conditions @ 100%
Downloads: Total: 2
More Statistics

Actions (Repository Staff Only)

Item Control Page Item Control Page