Using ambient assisted living infrastructures to monitor emotional change: Applications in supporting dementia interventions

Abstract

Background: This project aims to create a new method of preventative care based on early prediction of changes in emotional state and, based on this early detection, use novel “human-in-the-loop” interventionmethods specific to the needs of the individual to improve the quality of life of the older person before severe problems arise. The project is forged from two independent research and development activities currently on-going: Ambient Assisted Living (AAL) at the Netwell Centre and the study of human emotion at Queen’s University.Methods: On-going covariance and sensitivity analysis between quantitative sensor data and “ground truth” validated measures of emotional change inform the predictive model. Results: Visualization of sensor data has begun to reveal specific patterns of behavior over hours, days, weeks, and months. Collection of “ground truth” affect and health data has now commenced. Initial multivariate analysis is ongoing and will be discussed. Conclusions: To aid in the establishment and application of home-based interventions for cognitive decline and dementia, AAL environments can be used to observe, understand, and eventually model the needs of the older person. This work has created the infrastructure and is now beginning to analyze the data necessary to begin to instantiate this approach.