FITsense: Employing Multi-modal Sensors in Smart Homes to Predict Falls

Abstract

As people live longer, the increasing average age of the population places additional strains on our health and social services. There are widely recognised benefits to both the individual and society from supporting people to live independently for longer in their own homes. However, falls in particular have been found to be a leading cause of the elderly moving into care, and yet surprisingly preventative approaches are not in place; fall detection and rehabilitation are too late. In this paper we present FITsense, which is building a Smart Home environment to identify increased risk of falls for residents, and so allow timely interventions before falls occurs. An ambient sensor network, installed in the Smart Home, identifies low level events taking place which is analysed to generate a resident's profile of activities of daily living (ADLs). These ADL profiles are compared to both the resident's typical profile and to known "risky" profiles to allow evidence-driven intervention recommendations. Human activity recognition to identify ADLs from sensor data is a key challenge. Here we compare a windowing-based and a sequence-based event representation on four existing datasets. We find that windowing works well, giving consistent performance but may lack sufficient granularity for more complex multi-part activities.

Preventing falls: the use of machine learning for the prediction of future falls in individuals without history of fall

“…With the increasing available computed parameters, the available acquisition systems, and the general trend of fusing information from different modalities, there is a legitimate interest in utilizing modern machine learning algorithms to assess the risk of fall. Recent research on wearable technologies (such as accelerometers and gyroscopes) and force platforms for fall prediction has primarily focused on fusing information and computing parameters for fall risk assessment and applying predictive models to the available datasets [44][45][46][47][48][49].…”

Creating Community and Belonging in a Designated Housing Estate for Disabled People

“…The technology within the homes is a combination of passive sensors, such as movement sensors, 'internet of things'-enabled devices such as fridges, cookers, showers etc, and bed and chair sensors. The data generated is anonymously analysed by researchers at Robert Gordon University to help aid prediction of events which impact upon health, such as falls (Massie, Forbes, Craw, Fraser, & Hamilton, 2018). It is important to note that, at the time of interviewing, this data was not actively used to support residents' health by health services.…”