Energy-Efficient Respiratory Anomaly Detection in Premature Newborn Infants

TL;DR

This paper presents a deep learning wearable system for non-invasive respiratory monitoring in premature infants, achieving high accuracy and significantly reduced energy consumption through innovative quantization and spiking neural network techniques.

Contribution

It introduces a novel SNN-based respiratory classification method that drastically reduces energy use while maintaining high accuracy, suitable for wearable neuromorphic hardware.

Findings

Achieved 97.15% accuracy with 1D CNN model.

Reduced energy consumption by 18 times using SNN conversion.

SNN-based solution maintains accuracy with 4 times less energy.

Abstract

Precise monitoring of respiratory rate in premature infants is essential to initiate medical interventions as required. Wired technologies can be invasive and obtrusive to the patients. We propose a Deep Learning enabled wearable monitoring system for premature newborn infants, where respiratory cessation is predicted using signals that are collected wirelessly from a non-invasive wearable Bellypatch put on infant's body. We propose a five-stage design pipeline involving data collection and labeling, feature scaling, model selection with hyperparameter tuning, model training and validation, model testing and deployment. The model used is a 1-D Convolutional Neural Network (1DCNN) architecture with 1 convolutional layer, 1 pooling layer and 3 fully-connected layers, achieving 97.15% accuracy. To address energy limitations of wearable processing, several quantization techniques are explored and their performance and energy consumption are analyzed. We propose a novel Spiking-Neural-Network(SNN) based respiratory classification solution, which can be implemented on event-driven neuromorphic hardware. We propose an approach to convert the analog operations of our baseline 1DCNN to their spiking equivalent. We perform a design-space exploration using the parameters of the converted SNN to generate inference solutions having different accuracy and energy footprints. We select a solution that achieves 93.33% accuracy with 18 times lower energy compared with baseline 1DCNN model. Additionally the proposed SNN solution achieves similar accuracy but with 4 times less energy.