Federated Quality Profiling: A quality evaluation of patient monitoring at the Edge

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Continuous monitoring of patients involves collecting and analyzing sensory data from a multitude of sources. To overcome communication overhead, ensure data privacy and security, reduce data loss, and maintain efficient resource usage the processing and analytics are moved close to where the data is located (e.g., the Edge). Data quality (DQ) can be degraded because of imprecise or malfunctioning sensors, dynamic changes in the environment, transmission failures, or delays. Therefore, can mislead clinical judgments and cause incorrect actions, if not managed properly. In this paper, inspired by Federated Learning (FL), we propose a novel approach using Federated Data Quality (FDQ) Profiling to assess DQ at the edge considering a global quality profile aggregated based on local profiles. We conducted experiments to evaluate the effect of FDQ profiling on DQ improvement considering the assessment of outlier detection and unbalanced data. The results demonstrated that the improved DQ has a positive impact on the accuracy of four conventional machine learning models.

Original languageEnglish
Title of host publication2022 International Wireless Communications and Mobile Computing, IWCMC 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1015-1021
Number of pages7
ISBN (Electronic)9781665467490
DOIs
Publication statusPublished - 2022
Event18th IEEE International Wireless Communications and Mobile Computing, IWCMC 2022 - Dubrovnik, Croatia
Duration: May 30 2022Jun 3 2022

Publication series

Name2022 International Wireless Communications and Mobile Computing, IWCMC 2022

Conference

Conference18th IEEE International Wireless Communications and Mobile Computing, IWCMC 2022
Country/TerritoryCroatia
CityDubrovnik
Period5/30/226/3/22

Keywords

  • Data Quality Profiling
  • Deep Learning
  • Edge computing
  • eHealth
  • Federated Learning
  • Federated Profiling

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Signal Processing
  • Instrumentation

Fingerprint

Dive into the research topics of 'Federated Quality Profiling: A quality evaluation of patient monitoring at the Edge'. Together they form a unique fingerprint.

Cite this