Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Real-Time Energy Measurement for Non-Intrusive Well-Being Monitoring of Elderly People -- a Case Study

Mateusz Brzozowski, Artur Janicki

TL;DR

This paper addresses privacy-preserving elderly well-being monitoring by avoiding wearables and cameras and by leveraging real-time energy measurements. It deploys a compact IEC 62056-21 beacon to collect 15-minute energy data, transmitted to a cloud platform for analysis. The authors apply $k$-Means clustering to daily mean power profiles to identify typical routines and use anomaly detection to flag deviations, validating findings against participant notes. The results indicate that non-intrusive energy monitoring can reveal daily activities and changes in well-being, with greater effectiveness when multiple electrical devices are used, offering a practical tool for discreet caregiver support.

Abstract

This article presents a case study demonstrating a non-intrusive method for the well-being monitoring of elderly people. It is based on our real-time energy measurement system, which uses tiny beacons attached to electricity meters. Four participants aged 67-82 years took part in our study. We observed their electric power consumption for approx. a month, and then we analyzed them, taking into account the participants' notes on their activities. We created typical daily usage profiles for each participant and used anomaly detection to find unusual energy consumption. We found out that real-time energy measurement can give significant insight into someone's daily activities and, consequently, bring invaluable information to caregivers about the well-being of an elderly person, while being discreet and entirely non-intrusive.

Real-Time Energy Measurement for Non-Intrusive Well-Being Monitoring of Elderly People -- a Case Study

TL;DR

This paper addresses privacy-preserving elderly well-being monitoring by avoiding wearables and cameras and by leveraging real-time energy measurements. It deploys a compact IEC 62056-21 beacon to collect 15-minute energy data, transmitted to a cloud platform for analysis. The authors apply -Means clustering to daily mean power profiles to identify typical routines and use anomaly detection to flag deviations, validating findings against participant notes. The results indicate that non-intrusive energy monitoring can reveal daily activities and changes in well-being, with greater effectiveness when multiple electrical devices are used, offering a practical tool for discreet caregiver support.

Abstract

This article presents a case study demonstrating a non-intrusive method for the well-being monitoring of elderly people. It is based on our real-time energy measurement system, which uses tiny beacons attached to electricity meters. Four participants aged 67-82 years took part in our study. We observed their electric power consumption for approx. a month, and then we analyzed them, taking into account the participants' notes on their activities. We created typical daily usage profiles for each participant and used anomaly detection to find unusual energy consumption. We found out that real-time energy measurement can give significant insight into someone's daily activities and, consequently, bring invaluable information to caregivers about the well-being of an elderly person, while being discreet and entirely non-intrusive.
Paper Structure (8 sections, 4 figures, 1 table)

This paper contains 8 sections, 4 figures, 1 table.

Table of Contents

  1. Introduction
  2. Monitoring Elderly People
  3. Proposed method
  4. Experiments
  5. Participants
  6. Data analysis
  7. Results
  8. Conclusions and Future Work

Figures (4)

  • Figure 1: OneMeter beacon with optical sensor attached to IEC 62056-21 port of electricity meter.
  • Figure 2: 15-min mean power profiles for clustered into three clusters for monitored user S4. The thick black line shows the mean profiles for each cluster.
  • Figure 3: Mean 15-min mean power profiles for three clusters identified per each monitored user.
  • Figure 4: Three anomalous days detected for user S1. Black lines denote the closest mean usage profile; red lines denote the usage from the anomalous days.