Ubiquitous Health (U-Health) smart homes are intelligent spaces capable of observing and correctly recognizing the activities and health statuses of their inhabitants (context) to provide the appropriate support to achieve an overall sense of health and well-being in their inhabitants’ daily lives. With the intrinsic heterogeneity and large number of sources of context information, aggregating and reasoning on low-quality raw sensed data may result in conflicting and erroneous evaluations of situations, affecting directly the reliability of the U-Health systems. In this environment, the evaluation and verification of Quality of Context (QoC) information plays a central role in improving the consistency and correctness of context-aware U-Health applications. Therefore, the objective of this chapter is to highlight the impact of QoC on the correct behavior of U-Health systems, and introduce and analyze the existing approaches of modeling, evaluating, and using QoC to improve its context-aware decision-making support.
TopIntroduction
Two main factors are pushing towards the development and deployment of U-Health smart homes: 1) the worldwide increase of people that require for daily care (e.g., elders, people with chronic diseases or disabilities) that comes with an increase need for human costly services to assist them; 2) health providers and government’s willingness to reduce the high costs for assisting them in specialized hospitals and institutions. In the specific case of world population ageing, recent studies1 show that the growth rate of older population (1.9%) is significantly higher than that of the total population (1.2%). For instance, the older U.S. population is numbered in 39.6 million (2009)2, about one in every eight Americans (12.9%), and it will be about 72.1 million in 2030.
The development of U-Health and Ambient Assisted Living (AAL) systems (Belbachir, et al., 2010) is an important action to enable people requiring continuous care to live independently in their own homes (Kim, et al., 2010). See in Orwat (2010) a survey with a large number of U-Health solutions. Recent advances in wireless technologies (e.g., Bluetooth, RFID, ZigBee, 3G, 4G), in sensors/actuators (Dengler, et al., 2007; Matthews, et al., 2007) (e.g., unobtrusive physiological sensors), and the convergence of home broadband access with the Digital TV (DTV) (Oliveira, et al., 2010) expand the usage span of U-health systems in real scenarios. Unobtrusive physiological sensors (Adami, et al., 2003; Hagler, et al., 2010; Matthews, et al., 2007) and mobile technologies can be integrated to monitor human biological conditions for remote diagnostic of diseases (Dongsoo, et al., 2009), detect falls (Sixsmith, 2004), to treat life-threatening situations (Bottazzi, et al., 2006; Fry, 2005), to improve quality of life and to lower health care costs (Wang, et al., 2010). For instance, a elderly can be continuously monitored by a sensor-rich jacket3 (e.g., blood pressure, heart rate, SpO24, CO5, breath rate) that communicates with a smartphone (e.g., via Bluetooth, Wifi) to send the collected data to a remote monitoring system using a 3G connection. This physiological information can yet be combined with data sensed from the environment (e.g., motion sensor, location sensor, thermometer) and in-home objects that interact with inhabitants (e.g., home appliances, sensor-rich chairs6 and mattress7) in order to recognize their activities, providing accurate remote medical assistance (e.g., verifying if the patient is following correctly the medical advices and detecting abnormal behaviors). Indeed, U-Health systems can actively contribute to identify and prevent life-threatening situations, reducing the number of chronic disease deaths (Orwat, et al., 2008). Another possible application scenario of U-Health system is the health monitoring of communities for emergency preparedness and governance decision-making support, such as the control of outbreaks and epidemics (Oliveira, et al., 2010).