English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Precise monitoring of respiratory rate in premature infants is essential toinitiate medical interventions as required. Wired technologies can be invasiveand obtrusive to the patients. We propose a Deep Learning enabled wearablemonitoring system for premature newborn infants, where respiratory cessation ispredicted using signals that are collected wirelessly from a non-invasivewearable Bellypatch put on infant's body. We propose a five-stage designpipeline involving data collection and labeling, feature scaling, modelselection with hyperparameter tuning, model training and validation, modeltesting and deployment. The model used is a 1-D Convolutional Neural Network(1DCNN) architecture with 1 convolutional layer, 1 pooling layer and 3fully-connected layers, achieving 97.15% accuracy. To address energylimitations of wearable processing, several quantization techniques areexplored and their performance and energy consumption are analyzed. We proposea novel Spiking-Neural-Network(SNN) based respiratory classification solution,which can be implemented on event-driven neuromorphic hardware. We propose anapproach to convert the analog operations of our baseline 1DCNN to theirspiking equivalent. We perform a design-space exploration using the parametersof the converted SNN to generate inference solutions having different accuracyand energy footprints. We select a solution that achieves 93.33% accuracy with18 times lower energy compared with baseline 1DCNN model. Additionally theproposed SNN solution achieves similar accuracy but with 4 times less energy.

Energy-Efficient Respiratory Anomaly Detection in Premature Newborn Infants