tinyML Talks India: Single Lead ECG Classification On Wearable and Implantable Devices
tinyML Talks – India meetup
Single Lead ECG Classification On Wearable and Implantable Devices
Arijit Ukil
Senior Scientist in TCS Research
Tata Consultancy Services, India
Gitesh Kulkarni
Scientist, Embedded Devices, and Intelligent Systems,
TCS Research, Bangalore, India
Electrocardiogram (ECG) is one of the fundamental markers to detect different cardiovascular diseases (CVDs). Owing to the widespread availability of ECG sensors (single lead) as well as smartwatches with ECG recording capability, ECG classification using wearable devices to detect different CVDs has become a basic requirement for a smart healthcare ecosystem. We demonstrate that novel method of model compression with robust detection capability for CVDs from ECG signals can be aptly ported to the resource constrained micro-controller platform suitable for wearable devices while minimizing the performance loss. We employ knowledge distillation-based model compression approach where the baseline (teacher) deep neural network model is compressed to a TinyML (student) model using piece-wise linear approximation. Our proposed ECG TinyML has achieved ~156x compression factor to suit to the requirement of 100KB memory availability for model deployment on wearable devices including implantable loop recorder (ILR).
source
