Estimation of Rest-Activity Patterns using Motion Sensors

Biomedical Engineering Department (BME) and the Oregon Center for Aging and Technology (ORCATECH), Oregon Health & Science University (OHSU), 3303 SW Bond Avenue, Portland, OR 97239, USA.
Conference proceedings: ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference 08/2010; 2010:2147-50. DOI: 10.1109/IEMBS.2010.5628022
Source: PubMed


Disrupted sleep patterns are a significant problem in the elderly, leading to increased cognitive dysfunction and risk of nursing home placement. A cost-effective and unobtrusive way to remotely monitor changing sleep patterns over time would enable improved management of this important health problem. We have developed an algorithm to derive sleep parameters such as bed time, rise time, sleep latency, and nap time from passive infrared sensors distributed around the home. We evaluated this algorithm using 404 days of data collected in the homes of 8 elderly community-dwelling elders. Data from this algorithm were highly correlated to ground truth measures (bed mats) and were surprisingly robust to variability in sensor layout and sleep habits.

Download full-text


Available from: Jeffrey Kaye, Mar 08, 2014
  • Source
    • "With these traditional sleep assessment methods, data are typically obtained over a brief period of time (e.g., less than 1 week) and not necessarily close in time to a relevant clinic visit, which limits our understanding of how sleep over longer periods of time, sleep the night before an evaluation, or sleep variability can impact cognitive functioning. Unobtrusive, passive, motion-sensor-based monitoring of sleep that occurs in one's home environment is a novel alternate approach to traditional objective sleep assessment methods (Hayes, Riley, Mattek, Pavel, & Kaye, 2013; Hayes, Riley, Pavel, & Kaye, 2010). Daily sleep assessment that requires no worn devices and that occurs within the everyday environment will make it possible to obtain larger and more accurate samples of sleep data than by episodic sleep assessment in a lab or by self-report. "
    [Show abstract] [Hide abstract]
    ABSTRACT: The relationship between recent episodes of poor sleep and cognitive testing performance in healthy cognitively intact older adults is not well understood. In this exploratory study we examined the impact of recent sleep disturbance, sleep duration, and sleep variability on cognitive performance in 63 cognitively intact older adults using a novel unobtrusive in-home sensor-based sleep assessment methodology. Specifically, we examined the impact of sleep the night prior, the week prior, and the month prior to a neuropsychological evaluation on cognitive performance. Results showed that mildly disturbed sleep the week prior and month prior to cognitive testing was associated with reduced working memory on cognitive evaluation. One night of mild sleep disturbance was not associated with decreased cognitive performance the next day. Sleep duration was unrelated to cognition. In-home, unobtrusive, sensor monitoring technologies provide a novel method for objective, long-term, and continuous assessment of sleep behavior and other everyday activities that might contribute to decreased or variable cognitive performance in healthy older adults.
    The Clinical Neuropsychologist 02/2015; 29(1):1-14. DOI:10.1080/13854046.2015.1005139 · 1.72 Impact Factor
  • Source
    • "III. RELATED WORK There is a vast amount of ongoing research within the aware home for AAL space, with past and current projects including initiatives at the ORCATECH living laboratory in Portland, Oregon [10] and the Enable project, with partners situated in five European countries [9]. The majority of such research focuses on how best to monitor older adults and their environments to detect changes, and possibly decline, in a person's bio-psycho-social wellbeing. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Aware homes support the monitoring of older adults, with the potential to detect a wealth of information regarding the person's functional, cognitive and social wellbeing. While much research in this space focuses on the collection and interpretation of sensor data, it is equally important to understand how we can begin to relay the information learned back to older adults, empowering them to play an active role in the management of their health. In this paper we discuss the results of the requirements gathering phase of our research with a number of older adults living in aware homes. The goal of this research is to explore issues surrounding the delivery of healthcare information, as collected through embedded sensors in the home, to the home owner. Our results reveal a number of emerging themes around this space, including a desire by older adults to play an active role in managing their health and potential concerns surrounding the delivery of such information through technology.
    5th International Conference on Pervasive Computing Technologies for Healthcare, PervasiveHealth 2011, Dublin, Ireland, May 23-26, 2011; 05/2011
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper describes novel ambient technologies for domestic gait velocity measurement and in-home daily activity monitoring. This was achieved through low cost, easily deployable passive infrared motion detectors and an unobtrusive wireless sensor network. This system was deployed in the houses of eight older adults (1 faller; 7 non-fallers) living independently over eight weeks. Inter-daily gait velocity and daily activity metrics were derived from this data set. Consistent daily rhythms were found, however no correlations to clinical or daily ethnographic data were found. Long-term data collection, particularly surrounding serious life events, would validate the ability of this system to highlight deviations in health status. This
    5th International Conference on Pervasive Computing Technologies for Healthcare, PervasiveHealth 2011, Dublin, Ireland, May 23-26, 2011; 01/2011
Show more