Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2012;12(6):7828-54.
doi: 10.3390/s120607828. Epub 2012 Jun 8.

A novel human autonomy assessment system

Marco Munstermann  1 , Torsten Stevens, Wolfram Luther
Affiliations

A novel human autonomy assessment system

Marco Munstermann et al. Sensors (Basel). 2012.

Abstract

This article presents a novel human autonomy assessment system for generating context and discovering the behaviors of older people who use ambulant services. Our goal is to assist caregivers in assessing possibly abnormal health conditions in their clients concerning their level of autonomy, thus enabling caregivers to take countermeasures as soon as possible.

Keywords: Petri nets; activities of daily living; activity recognition; concur task trees; context awareness; data mining; probabilistic models; task models; transition system miner.

PubMed Disclaimer

Figures

Figure 1.
Figure 1.
System overview with two main building blocks: context generation module and behavior discovery module.
Figure 2.
Figure 2.
System process chain with four core modules (sensor middleware, context generation, behavior discovery and setup tool) and three roles (client, caregiver and supervisor).
Figure 3.
Figure 3.
Transforming the sequential enabling-operator from CTT to PN representation.
Figure 4.
Figure 4.
Transforming the choice-operator from CTT to PN representation.
Figure 5.
Figure 5.
Transforming the independent concurrency-operator from CTT to PN representation.
Figure 6.
Figure 6.
Typical behavior mined from the example event log in Table 1 using the Transition System Miner (TSM) with starting state 1 and final state 7; arcs labeled with activity names and probabilities (in parentheses).
Figure 7.
Figure 7.
Typical behavior mined from the example event log in Table 1 using TSM (starting state 1 and final states 7 and 16); arcs labeled with activity names and probabilities (in parentheses).
Figure 8.
Figure 8.
Toilet environment with three sensors: (1) toilet presence; (2) toilet paper use and (3) toilet flush.
Figure 9.
Figure 9.
CTT model of the ADL “Using_Toilet” (including all six possible variations).
Figure 10.
Figure 10.
Typical daily behavior in terms of ADLs of five test persons P1–P5 (from left to right).
Figure 11.
Figure 11.
Metric values of P1 after 21 days (green: normal behavior; red: abnormal behavior).
Figure 12.
Figure 12.
Dependency between optimal threshold and time (including root regression).
See this image and copyright information in PMC

References

    1. Carone G., Costello D. Can Europe afford to grow old? Fund Financ. Dev. Mag. 2006;45 Available online: www.imf.org/external/pubs/ft/fandd/2006/09/carone.htm (accessed on 18 April 2012)
    1. García-Vázquez J.R., Rodríguez M.D., Andrade A.G., Bravo J. Supporting the strategies to improve elders' medication compliance by providing ambient aids. Pers. Ubiquitous Comput. 2011;15:389–397.
    1. Choudhury T., Philipose M., Wyatt D., Lester J. Towards activity databases: Using sensors and statistical models to summarize people's lives. IEEE Data Eng. Bull. 2006;29:49–58.
    1. Chandola V., Banerjee A., Kumar V. Anomaly detection: A survey. ACM Comput. Surv. 2009;41:15:1–15:58.
    1. Hong X., Nugent C., Mulvenna M., McClean S., Scotney B., Devlin S. Evidential fusion of sensor data for activity recognition in smart homes. Pervasive Mobile Comput. 2009;5:236–252.

Publication types

LinkOut - more resources