About this document
Multitask Residual Shrinkage Convolutional Neural Network For Sleep Apnea Detection Based On Wearable Bracelet Photoplethysmography by marveloussweetie is a document available to read on EtoBox.
The document presents a novel method for sleep apnea syndrome (SAS) detection using a 1-D multitask multiattention residual shrinkage convolutional neural network (1D-MMResSNet) and cost-sensitive classifier, leveraging photoplethysmography (PPG) data collected from wearable devices. The proposed model addresses challenges such as poor signal quality and class imbalance, achieving segment detection accuracy of 81.82% and individual detection accuracy of 95.65%. This method aims to facilitate low-cost, effec
- Author
- marveloussweetie
- Language
- EN