ZEN: A flexible energy-efficient hardware classifier exploiting temporal sparsity in ECG data
Authors:
- 13 June 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 214-217
Abstract
State-of-the-art low-power ECG hardware classifiers rely on extraction of pre-defined, hand-tuned features. This hinders their usage in different applications, because of the time-consuming redesign of features for any new classification task. As an alternative, we present a machine-learning based approach to ECG classification in hardware that still relies on feature extraction but is much more flexible to use. We utilize a recurrent neural network with temporal sparsity inspired by biologically motivated event-based systems. Features are extracted by freely configurable time-domain filters that are fully integrated in the training process. These are sparsified via delta encoding, so that further processing only acts on changes in the features or the recurrent connections. A scalable hardware architecture derived from this concept allows for stand-alone classification on input data streams. Despite its flexibility, our design achieves a peak energy efficiency of 37 nJ per heartbeat and an ultra-low power consumption of 532 nW in real-time operation, driven by temporal sparsity and a systematic low-power implementation strategy. At the same time, its classification performance is on par with state-of-the-art software-based classifiers.Keywords
Funding Information
- German Research Foundation (DFG, Deutsche Forschungs-gemeinschaft) (390696704)
- Federal German ministry for science and education (BMBF) (16ESl147)
This publication has 13 references indexed in Scilit:
- Comparison of Artificial Neural Networks for Low-Power ECG-Classification SystemJournal of Sensor Science and Technology, 2020
- Adaptive Body Bias Aware Implementation for Ultra-Low-Voltage Designs in 22FDX TechnologyIEEE Transactions on Circuits and Systems II: Express Briefs, 2019
- A 13.34 μW Event-Driven Patient-Specific ANN Cardiac Arrhythmia Classifier for Wearable ECG SensorsIEEE Transactions on Biomedical Circuits and Systems, 2019
- A 1.06-$\mu$ W Smart ECG Processor in 65-nm CMOS for Real-Time Biometric Authentication and Personal Cardiac MonitoringIEEE Journal of Solid-State Circuits, 2019
- Inter- and Intra- Patient ECG Heartbeat Classification for Arrhythmia Detection: A Sequence to Sequence Deep Learning Approach2019
- Robust ECG Signal Classification for the Detection of Atrial Fibrillation Using Novel Neural Networks2017
- An Energy-Efficient ECG Processor With Weak-Strong Hybrid Classifier for Arrhythmia DetectionIEEE Transactions on Circuits and Systems II: Express Briefs, 2017
- An Injectable 64 nW ECG Mixed-Signal SoC in 65 nm for Arrhythmia MonitoringIEEE Journal of Solid-State Circuits, 2014
- The impact of the MIT-BIH Arrhythmia DatabaseIEEE Engineering in Medicine and Biology Magazine, 2001
- PhysioBank, PhysioToolkit, and PhysioNetCirculation, 2000