Fitbeat: COVID-19 estimation based on wristband heart rate using a contrastive convolutional auto-encoder

作者：

Highlights：

• Heart rate based identification of individuals with suspected COVID-19 infection.

• Semi-supervised framework using combination of auto-encoder and contrastive loss.

• Contrastive convolutional auto-encoder is capable of finding proper latent attributes.

• COVID-19 estimation performance declines with data shifted from symptom reported date.

摘要

•Heart rate based identification of individuals with suspected COVID-19 infection.•Semi-supervised framework using combination of auto-encoder and contrastive loss.•Contrastive convolutional auto-encoder is capable of finding proper latent attributes.•COVID-19 estimation performance declines with data shifted from symptom reported date.

论文关键词：COVID-19,Respiratory tract infection,Anomaly detection,Contrastive learning,Convolutional auto-encoder

论文评审过程：Received 5 April 2021, Revised 30 August 2021, Accepted 24 October 2021, Available online 26 October 2021, Version of Record 7 November 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108403