Simulation of memristive crossbar arrays for seizure detection and prediction using parallel Convolutional Neural Networks [Formula presented]

Li, Chenqi, Lammie, Corey, Amirsoleimani, Amirali, Rahimi Azghadi, Mostafa, and Genov, Roman (2023) Simulation of memristive crossbar arrays for seizure detection and prediction using parallel Convolutional Neural Networks [Formula presented]. Software Impacts, 15 (March). 100473.

Preview

PDF (Published Version) - Published Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.
Download (671kB) | Preview

DOI: 10.1016/j.simpa.2023.100473

View at Publisher Website: https://doi.org/10.1016/j.simpa.2023.100...

230

Abstract

For epileptic seizure detection and prediction, to address the computational bottleneck of the von Neumann architecture, we develop an in-memory memristive crossbar-based accelerator simulator. The simulator software is composed of a Python-based neural network training component and a MATLAB-based memristive crossbar array component. The software provides a baseline network for developing deep learning-based signal processing tasks, as well as a platform to investigate the impact of weight mapping schemes and device and peripheral circuitry non-idealities.


Item ID:	78382
Item Type:	Article (Research - C1)
ISSN:	2665-9638
Keywords:	CNN, EEG, Memristive crossbar array, RRAM, Seizure detection, Seizure prediction
Copyright Information:	© 2023 The Author(s). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
Date Deposited:	16 Oct 2023 23:25
FoR Codes:	40 ENGINEERING > 4009 Electronics, sensors and digital hardware > 400901 Analog electronics and interfaces @ 50% 46 INFORMATION AND COMPUTING SCIENCES > 4602 Artificial intelligence > 460207 Modelling and simulation @ 50%
SEO Codes:	22 INFORMATION AND COMMUNICATION SERVICES > 2204 Information systems, technologies and services > 220403 Artificial intelligence @ 50% 28 EXPANDING KNOWLEDGE > 2801 Expanding knowledge > 280103 Expanding knowledge in the biomedical and clinical sciences @ 50%
Downloads:	Total: 230 Last 12 Months: 6
	More Statistics

Actions (Repository Staff Only)

Item Control Page