Database Reference
In-Depth Information
medical domains, the advancement of this natural concept to more pro-
active applications such as round-the-clock monitoring has only been a
recent development.
A method called
LiveNet
is proposed in [150], in which a flexible dis-
tributed mobile platform that can be deployed for a variety of proactive
healthcare applications that can sense one's immediate context and pro-
vide feedback. This system is based on standard PDA hardware with
customized sensors and a data acquisition hub, which provides the ability
for local sensing, real-time processing, and distributed data streaming.
This integrated monitoring system can also leverage off-body resources
for wireless infrastructure, long-term data logging and storage, visual-
ization/display, complex sensing, and computation-intensive processing.
The
LiveNet
system also allows people to receive real-time feedback from
their continuously monitored and analyzed health state. The system can
also communicate health information to caregivers and other members
of an individual's social network for support and interaction. One of the
attractive features of this system is that it can combine general-purpose
commodity hardware with specialized health/context sensing within a
networked environment. This creates a multi-functional mobile health-
care device that is at the same time a personal real-time health monitor,
which provides both feedback to the patient, the patient's social network,
and health-care provider.
We note that a significant number of predictions can also be made
without collecting data which is clinical in nature. In particular, the
daily activities of an individual can provide key insights into their health.
Smartphones have now become sophisticated enough that the data from
the different sensors can be fused in order to infer the daily activities of
an individual [65]. For example, the presence of illness and stress can af-
fect individuals in terms of their total communication, interactions with
respect to the time of day, the diversity and entropy of face-to-face com-
munications and their movement. In order to achieve this goal, the work
in [121] uses mobile phone based co-location and communication sensing
to measure different attributes about the daily activity of an individual.
It has been shown in [121], that the collection of even simple day-to-day
information has a powerful effect on the ability to make an accurate
diagnosis. Methods have also been proposed for finding sequential pat-
terns from human activity streams, in order to determine the key activity
trends over time. Furthermore, such activity monitoring cane be used
to model the influence of different individuals on each other in terms of
their daily activities. The work in [122] used a mobile phone platform
to examine how individuals are influenced by face-to-face interactions
in terms of their obesity, exercise and eating habits. It was shown that