arrWNN: Arrhythmia-Detecting Weightless Neural Network FlexIC
Velu Pillai, Igor D. S. Miranda, Tejas Musale, Mugdha Jadhao, Paulo C. R. Souza Neto, Zachary Susskind, Alan T. L. Bacellar, Mael Lhostis, Priscila M. V. Lima, Diego Leonel Cadette Dutra, Eugene B John, Maurício Breternitz, Felipe M. G. França, Emre Özer, Lizy K. John · 2024
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 mm2consuming 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.