Capturing Regularity of ADL Routines Using Hierarchical Clustering Models

Abstract

Nearly one in four community-dwelling elders are affected by mild cognitive impairment, such as dementia. As gradual changes in daily routine is a major symptom of cognitive diseases, the longitudinal monitoring of routine uniformity in a smart home environment can greatly contribute to the early identification and tracking of progression of such diseases. However, the high level of complexity in activity patterns and large amount of noise stemming from real life behaviors pose great challenges in achieving this task. We propose a method to quantify the degree of routineness by representing the daily activities over a span of several days as an image and identifying clusters of similar activities through hierarchical bottom-up clustering. Results from this study provide a foundation towards quantifying routine patterns and bouts from the daily routine within an elderly person's life with potential significance to early detection of outcomes of clinical interest.