Fraunhofer Center for Assistive Information and Communication Solutions – AICOSDescription:
Everyone has already experienced trouble sleeping at one time or another. This is normal and usually temporary, frequently due to stress or other outside factors. When this becomes a regular occurrence, then probably the person is facing any kind of sleep disorder.
Complaints of sleep difficulty are more common among older people. A reduced sleep quality due to sleep deprivation or fragmentation may cause reduced vigilance, attention and information processing ability, which ultimately may result in trips and falls. In general, the lack of sleep quality has negative impacts on energy, balance and health.
Several devices referred to as ‘actigraph units’ are currently available to monitor human rest and activity cycles. Sleep actigraphs are generally worn on the wrist and, by capturing periods of activity and inactivity based on the wrist movement, they are able to determine sleep-wake patterns and circadian rhythms. More specifically, they can estimate sleep latency, total sleep time, number and frequency of awakenings and sleep efficiency.
The purpose of this research is to develop a system able to analyse sleep patterns and nocturnal activity autonomously based on information acquired from the smartphone (e.g. movement, noise, brightness) and external sensors (e.g., accelerometer, gyroscope, temperature, oximetry) attached to a dedicated position of the body. Sleep efficiency must be considered towards an analysis of risk, in order to predict the occurrence of falls. Moreover, the system must be able to collect and analyse data continuously, during several nights, in order to detect fluctuations/changes on the normal sleep-wake patterns, which may be indicative of problems, such as physical disability, depression or inadequate medication. The system must also be able to detect every time a person gets up at night.
External sensors will be connected to the smartphone and will continually record the movement someone undergoes (at night), as well as other vital signs considered relevant for sleep stages evaluation. The history of each night will be recorded in order to provide a longitudinal analysis of data, including the evaluation of insomnia, circadian-rhythm disorders and excessive sleepiness. The smartphone will warn the person every time an increased risk of falls is detected.
Author: Pedro Ribeiro
Type: MSc thesis
Partner: Faculdade de Engenharia da Universidade do Porto
Year: 2014