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

Modern advances in machine learning (ML) and wearable medical sensors (WMSs)in edge devices have enabled ML-driven disease detection for smart healthcare.Conventional ML-driven methods for disease detection rely on customizingindividual models for each disease and its corresponding WMS data. However,such methods lack adaptability to distribution shifts and new taskclassification classes. In addition, they need to be rearchitected andretrained from scratch for each new disease. Moreover, installing multiple MLmodels in an edge device consumes excessive memory, drains the battery faster,and complicates the detection process. To address these challenges, we proposeDOCTOR, a multi-disease detection continual learning (CL) framework based onWMSs. It employs a multi-headed deep neural network (DNN) and a replay-style CLalgorithm. The CL algorithm enables the framework to continually learn newmissions where different data distributions, classification classes, anddisease detection tasks are introduced sequentially. It counteractscatastrophic forgetting with a data preservation method and a synthetic datageneration (SDG) module. The data preservation method preserves the mostinformative subset of real training data from previous missions for exemplarreplay. The SDG module models the probability distribution of the real trainingdata and generates synthetic data for generative replay while retaining dataprivacy. The multi-headed DNN enables DOCTOR to detect multiple diseasessimultaneously based on user WMS data. We demonstrate DOCTOR's efficacy inmaintaining high disease classification accuracy with a single DNN model invarious CL experiments. In complex scenarios, DOCTOR achieves 1.43 times betteraverage test accuracy, 1.25 times better F1-score, and 0.41 higher backwardtransfer than the naive fine-tuning framework with a small model size of lessthan 350KB.

DOCTOR: A Multi-Disease Detection Continual Learning Framework Based on Wearable Medical Sensors