NanoHydra: Energy-Efficient Time-Series Classification at the Edge

TL;DR

NanoHydra is a novel, ultra-efficient TinyML approach for time-series classification on edge devices, achieving high accuracy with minimal energy consumption and enabling multi-year device operation.

Contribution

NanoHydra introduces a lightweight binary convolutional kernel-based method for TSC, optimized for ultra-low-power microcontrollers with parallel processing capabilities.

Findings

Achieves 94.47% accuracy on ECG5000 dataset.

Classifies 1-second ECG signals in 0.33 ms.

Consumes only 7.69 uJ per inference, 18x more efficient than previous methods.

Abstract

Time series classification (TSC) on extreme edge devices represents a stepping stone towards intelligent sensor nodes that preserve user privacy and offer real-time predictions. Resource-constrained devices require efficient TinyML algorithms that prolong the device lifetime of battery-operated devices without compromising the classification accuracy. We introduce NanoHydra, a TinyML TSC methodology relying on lightweight binary random convolutional kernels to extract meaningful features from data streams. We demonstrate our system on the ultra-low-power GAP9 microcontroller, exploiting its eight-core cluster for the parallel execution of computationally intensive tasks. We achieve a classification accuracy of up to 94.47% on ECG5000 dataset, comparable with state-of-the-art works. Our efficient NanoHydra requires only 0.33 ms to accurately classify a 1-second long ECG signal. With a modest energy consumption of 7.69 uJ per inference, 18x more efficient than the state-of-the-art, NanoHydra is suitable for smart wearable devices, enabling a device lifetime of over four years.