Coping with missing data in an unobtrusive monitoring system for office workers

Stavros Nousias, Giwrgos Papoulias, Otilia Kocsis, Miriam Cabrita, Aris S. Lalos, Konstantinos Moustakas

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

1 Citation (Scopus)

Abstract

Current trend of population ageing at global level is accompanied by increased prevalence of chronic diseases and higher rates of early retirement and labor market exit. In particular, the lifestyle of office workers is characterized by prolonged sitting and overall sedentary life, which alone is a high risk factor for cardiometabolic diseases, obesity and other related chronic diseases. The SmartWork unobtrusive monitoring system allows for continuous monitoring of various lifestyle, health, behavioural and work related parameters of office workers targeting to empower work ability sustainability. The large amounts of collected data in such systems are often characterized by the presence of missing entries. This work is an exploratory study on the potential of a Laplacian matrix completion variant for data imputation on the multi-channel time-series data collected with wearable or work devices in the SmartWork system.

Original languageEnglish
Title of host publication2019 International Conference on Biomedical Innovations and Applications (BIA)
EditorsValentina Markova, Todor Ganchev
PublisherIEEE
ISBN (Electronic)9781728147543
DOIs
Publication statusPublished - 27 Jan 2020
EventInternational Conference on Biomedical Innovations and Applications, BIA 2019 - Varna, Bulgaria
Duration: 8 Nov 20199 Nov 2019

Conference

ConferenceInternational Conference on Biomedical Innovations and Applications, BIA 2019
Abbreviated titleBIA 2019
CountryBulgaria
CityVarna
Period8/11/199/11/19

Keywords

  • activity tracker
  • data completion
  • heart rate
  • missing data
  • office worker

Fingerprint

Dive into the research topics of 'Coping with missing data in an unobtrusive monitoring system for office workers'. Together they form a unique fingerprint.

Cite this