A 2.52 μΑ Wearable Single Lead Ternary Neural Network Based Cardiac Arrhythmia Detection Processor

Abstract

A Ternary neural network (TNN) based patientspecific single lead Electrocardiography (ECG) processor for the early detection of cardiac arrhythmias (CA) is presented. The designed system detects upward/downward turning points in the ECG to detect the slope variation and calculates the fiducial points of the PQRST beats, with high auto-patient adaptability. A 3-layer Feedforward Neural Network with ternary weights is integrated on the sensor to classify eight different types of Shockable CA (SCA) and non-SCA (NSCA) with sensitivity and specificity of 99.1% and 99.8% respectively. The proposed processor is also synthesized using 65nm CMOS technology having an area of 1.08 mm 2 with an overall power consumption of 2.52 μA, energy efficiency of 72 nJ/detection.

Cardiac Arrhythmia Classification using Antidictionaries

“…Table VII shows a comparison of implemented CAC with recent works. In [3], the classification accuracy is high but no indication on the training scheme is given. In [5], an ASIC implementation of a SNN for cardiac arrhythmia classification is presented.…”