Home > Research > Publications & Outputs > Modeling and forecasting of at home activity in...


Text available via DOI:

View graph of relations

Modeling and forecasting of at home activity in older adults using passive sensor technology

Research output: Contribution to Journal/MagazineJournal articlepeer-review

<mark>Journal publication date</mark>31/10/2022
<mark>Journal</mark>Statistics in Medicine
Issue number23
Number of pages18
Pages (from-to)4629-4646
Publication StatusPublished
Early online date20/07/22
<mark>Original language</mark>English


Life expectancy in the UK has increased since the 19th century. As of 2019, there are just under 12 million people in the UK aged 65 or over, with close to a quarter living by themselves. Thus, many families and carers are looking for new ways to improve the health and care of older people. Passive sensors such as infra‐red motion and plug sensors have had success as a noninvasive way to help the older people. These provide a series of categorical sensor events throughout the day. Modeling this categorical dataset can help to understand and predict behavior. This article proposes a method to model the probability a sensor will trigger throughout the day for a household whilst accounting for the prior data and other sensors within the home. We present our results on a dataset from Howz, a company helping people to passively identify changes in their behavior over time.