Unobtrusive Cognitive Assessment in Smart-Homes: Leveraging Visual Encoding and Synthetic Movement Traces Data Mining
Contact us if these videos are not relevant.
Contact us if these videos are not relevant.
View abstract on PubMed
Summary
This summary is machine-generated.Smart-home sensors detect abnormal indoor movement patterns to identify cognitive decline in older adults. This innovative approach accurately distinguishes between cognitively healthy individuals and those with dementia.
Area Of Science
- Gerontology
- Artificial Intelligence
- Biomedical Engineering
Background
- Smart-home sensors offer non-intrusive methods for monitoring older adults.
- Movement traces are increasingly used to detect early signs of cognitive impairment.
Purpose Of The Study
- To develop an innovative system for identifying cognitive decline in seniors using smart-home sensor data.
- To analyze indoor movement patterns for early detection of cognitive impairment.
Main Methods
- Utilized non-intrusive smart-home sensors (PIR, object-embedded) to collect movement data.
- Visualized user locomotion traces and object interactions on floor plans.
- Employed image descriptor features and synthetic minority oversampling techniques for analysis.
Main Results
- A functional prototype system was tested on a dataset of 99 seniors.
- The system achieved a macro-averaged F1-score of 72.22% in distinguishing between cognitively healthy individuals and those with dementia.
- Demonstrated superior performance compared to existing state-of-the-art methods.
Conclusions
- The proposed system effectively identifies cognitive status in seniors through abnormal indoor movement patterns.
- Smart-home sensor data integration offers a flexible and effective approach for cognitive health assessment.
- This technology supports independent living and early intervention for cognitive decline.
Contact us if these videos are not relevant.
Contact us if these videos are not relevant.