ArrythML: An Autoencoder-Based TinyML Approach for On-Device Arrhythmia Detection on Resource-Constrained Embedded Systems
arXiv:2606.02256v1 Announce Type: new Abstract: Our work presents a method for ECG segmentation and arrhythmia detection using Tiny Machine Learning (TinyML) models for real-time, on-device inference on resource-constrained embedded systems. We develop INT8 quantized autoencoder-based TinyML models with minimal layers and parameters for embedded deployment. These models are evaluated using a custom dataset derived from the MIT-BIH Arrhythmia Database and validated in both PC-based simulations and on-device environments. For the evaluations, over 95,000 ECG segments are processed on an ESP32-S3
The proliferation of IoT devices and advancements in TinyML enable on-device AI for critical applications, addressing real-time processing needs and data privacy concerns.
This development allows for rapid, personalized medical intervention and proactive health monitoring without reliance on cloud processing, enhancing accessibility and responsiveness of healthcare.
Real-time, embedded AI for health monitoring becomes more efficient and widely deployable on resource-constrained devices, moving sophisticated analysis closer to the data source.
- · Medical device manufacturers
- · Patients with cardiovascular conditions
- · Embedded systems developers
- · TinyML platform providers
- · Cloud-dependent diagnostic services
- · Traditional bulky monitoring equipment
Widespread adoption of on-device arrhythmia detection in wearables and portable medical devices.
Increased demand for specialized hardware and software for TinyML development and deployment in healthcare.
The acceleration of AI integration into other real-time, critical embedded applications beyond healthcare, fostering a new era of proactive edge computing.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG