Disrupted sleep is a common problem in the elderly, due to age-related changes in health, lifestyle, and the physiological aspects of sleep. Severe sleep disturbances lead to impaired functioning, reduced quality of life, and increased health care costs. Therefore, monitoring of sleep patterns in the elderly is important. However, current methods for monitoring sleep are inadequate. In this paper, we use load cells for unobtrusive continuous monitoring of sleep patterns. Load cells are placed under a bed, and sleep characteristics such as bedtime, wake up time, and number and duration of naps are inferred from the load cell data. Using information from each load cell individually, we can also identify a person's position in bed, and, consequently, detect position shifts. We describe the algorithms for computation of the sleep characteristics and for assessment of the person's position in bed. We conclude by discussing the limitations in our approach, and the work we intend to pursue in the future.
