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

2025/10/22 by Cioflan, Cristian, Fonseca, Jose, Wang, Xiaying +1
#FOS: Electrical engineering #Signal Processing (eess.SP) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2510.20038

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.

Citations

• Train-On-Request: An On-Device Continual Learning Workflow for Adaptive Real-World Brain Machine Interfaces
• Time series classification with random convolution kernels: pooling operators and input representations matter
• Deeploy: Enabling Energy-Efficient Deployment of Small Language Models On Heterogeneous Microcontrollers
• AdaFSNet: Time Series Classification Based on Convolutional Network with a Adaptive and Effective Kernel Size Configuration
• On-Device Domain Learning for Keyword Spotting on Low-Power Extreme Edge Embedded Systems
• Optimizing IoT-Based Asset and Utilization Tracking: Efficient Activity Classification with MiniRocket on Resource-Constrained Devices
• BioGAP: a 10-Core FP-capable Ultra-Low Power IoT Processor, with Medical-Grade AFE and BLE Connectivity for Wearable Biosignal Processing
• WEASEL 2.0 -- A Random Dilated Dictionary Transform for Fast, Accurate and Memory Constrained Time Series Classification
• HYDRA: Competing convolutional kernels for fast and accurate time series classification
• ECG-TCN: Wearable Cardiac Arrhythmia Detection with a Temporal\n Convolutional Network
• MultiRocket: Multiple pooling operators and transformations for fast and effective time series classification

Related

• Optimizing TinyML: The Impact of Reduced Data Acquisition Rates for Time Series Classification on Microcontrollers
• On-Device Inference versus Wireless Streaming: Energy-Efficient Multi-Modal Deep Learning for Wearable Cardiovascular Patches
• A High GOPs/Slice Time Series Classifier for Portable and Embedded Biomedical Applications
• Energy-Efficient Real-Time Heart Monitoring on Edge-Fog-Cloud Internet-of-Medical-Things
• Tiny-HR: Towards an interpretable machine learning pipeline for heart rate estimation on edge devices