arrWNN: Arrhythmia-Detecting Weightless Neural Network FlexIC

This paper proposes a technique for incorporating machine learning into a wearable medical patch by combining two key technologies: weightless neural networks (WNNs), known for their efficiency and low hardware overhead, and Flexible Integrated Circuits (FlexICs) - ultra low-cost circuits on flexible substrates. We develop a special WNN model called “arrWNN” for detecting arrhythmia events from ECG signals that has an average prediction accuracy of 89% over the MIT BIH Arrhythmia datasets. We, then, design and implement the arrWNN model in hardware, and fabricate it using Pragmatic's FlexIC technology. The arrWNN FlexIC contains 5,706 NAND2-equivalent gates with a core area of 24 mm<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> consuming less than 10 mW at 3V. Our wafer-level test and measurement results show the full functionality of the fabricated arrWNN FlexICs validated against the simulation.

Authors

Institutions

Publication Details

Published
2024-09-15
DOI
https://doi.org/10.1109/ifetc61155.2024.10771885
Citations
7
Primary Topic
Neural Networks and Applications
Type
article
Field-Weighted Citation Impact
2.43
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

arrWNN: Arrhythmia-Detecting Weightless Neural Network FlexIC

Eugene John, Igor D. S. Miranda, Paulo Neto, Maurício Breternitz et al.
7 citations
Neural Networks and Applications
2.43
article

arrWNN: Arrhythmia-Detecting Weightless Neural Network FlexIC

Eugene John, Igor D. S. Miranda, Paulo Neto, Maurício Breternitz, Felipe M. G. França, Zachary Susskind, Tejas Musale, Priscila M. V. Lima, Velu Pillai, Emre Özer, Alan T. L. Bacellar, Lizy K. John, Diego Leonel Cadette Dutra, Mugdha Jadhao, Mael Lhostis
article en
7 citations

Abstract

This paper proposes a technique for incorporating machine learning into a wearable medical patch by combining two key technologies: weightless neural networks (WNNs), known for their efficiency and low hardware overhead, and Flexible Integrated Circuits (FlexICs) - ultra low-cost circuits on flexible substrates. We develop a special WNN model called “arrWNN” for detecting arrhythmia events from ECG signals that has an average prediction accuracy of 89% over the MIT BIH Arrhythmia datasets. We, then, design and implement the arrWNN model in hardware, and fabricate it using Pragmatic's FlexIC technology. The arrWNN FlexIC contains 5,706 NAND2-equivalent gates with a core area of 24 mm<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> consuming less than 10 mW at 3V. Our wafer-level test and measurement results show the full functionality of the fabricated arrWNN FlexICs validated against the simulation.

Iscte – Instituto Universitário de Lisboa (PT), Universidade Federal do Rio de Janeiro (BR), Universidade Federal do Recôncavo da Bahia (BR), Universidade do Porto (PT), PragmatIC (United Kingdom) (GB), Instituto de Telecomunicações (PT), The University of Texas at San Antonio (US), The University of Texas at Austin (US)
Openalex Percentile: Top 9%
Neural Networks and Applications
2.43
DOISourceOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.