Information, Storage & Access Nick Ipe Mathew

Cyber-Physical Systems for Assisted Living at Home

1. Introduction

The demand for healthcare is growing together with a population that is

growing older. To meet the demand for more healthcare, people are starting to
look for new healthcare constructions that provide better healthcare to more
people without a huge increase in cost.

The foundations of these new constructions are going to be information

technology and especially the newest version of information technology labeled
pervasive or ubiquitous computing. That is information technology that is not
trapped in a desktop computer, but is distributed in the environment, in our
clothes and maybe even inside our bodies.

One way this new technology will restructure the health industry is by
keeping people out of residential homes and hospitals and in their own home
continuing their daily routines. This will help detect signs of illnesses before it
gets serious, allowing medical consultation between the home and the hospital,
and help in continuous monitoring of a patient’s condition by medical
professionals while the patient stays in their own home.

The devices and the network for a Home-Health System which can monitor
the health and activity of the use in a secure and private manner and issue alerts
to the user, care givers or emergency services as necessary to provide additional
safety and security to the user. This system integrates a set of smart sensors
which are designed to provide health and security to the elder citizen living at
home. The system facilitates privacy by performing local computation, it supports
heterogeneous devices and it provide a platform and initial architecture for
exploring the use of sensors with elderly people.

2. Related Technologies & Applications

In recent years there has been increasing interest in the areas of

distributed medical monitoring and diagnostics (which divides responsibility
between the patient and the doctor), at-home health monitoring and wearable or
environmentally embedded (ubiquitous) technology to help patients monitor their
health. Within these efforts, there exists a fairly large body of work aimed not
only at improving biosensor technology, but also at packaging the sensors into
integrated systems that provide automated healthcare delivery in various
environments. Finally, there is a growing body of work in the areas of data mining
and presentation of health-related information.

2.1. Sports Monitoring

1
Information, Storage & Access Nick Ipe Mathew

Using wearable sensors to monitor and analyze physiological data while

exercising seems to be a popular, attractive, and profitable domain. There are
today sophisticated watches, helmets and mobile phone applications that assist
users in their exercise routine and goals.

2.2. Wearable Health Monitoring

Wearable physiological sensor systems have also been used for more
general health monitoring. Most of the systems allow users to monitor various
physiological signals while at home. They typically send the data wirelessly to a
local or remote base station for processing and display. In addition, a small
number of more sophisticated systems perform real-time analysis of the signals.

2.3. At-Home Health Monitoring

The concept of a smart home, i.e. a home instrumented with sensors that
are able to constantly monitor the daily activities of its inhabitants, has received
particular attention and research interest in recent years.

However, there exists a notable gap in work aimed at developing a unified

platform on which such technologies can operate. In most work to date,
researchers have developed fairly closed systems, making it difficult to integrate
new sensors, or more importantly to achieve interoperability of heterogeneous
medical and environmental sensors. The platform proposed in this paper aims at
filling this gap by addressing challenging issues such as sensor transparency and
interoperability, energy consumption and power harvesting, user interfaces and
data visualization, signal processing, communications, and privacy.

3. Intelligent, Monitoring CPS

A unified platform for sensing environmental and physiological signals
continuously is proposed. The intelligent, monitoring CPS manages, stores, and
analyzes the sensed data, and presents it to the user or forwards it to a health-
care professional. Figure 1 depicts an example of how the CPS would facilitate
implementing end-to-end sensor-based biofeedback applications.

2
Information, Storage & Access Nick Ipe Mathew

4. Components

The components of the intelligent monitoring CPS and how they integrate
with each other are described here.

A. Privacy
A critical aspect about sensing data about people’s health and activity is
privacy.

The sensor devices themselves contain embedded processors and software

such that they will not transmit information about the user except to provide
notification of an event of concern, or if specifically requested to do so by an
authorized and authenticated user. While encryption can protect this data, it is
much more secure to reduce the amount of data transmitted to a very low level.
This also reduces the bandwidth requirement of the system. When data is
streamed, for example when remote monitoring is authorized such that a care
provider can check in on the user, then the signal will be encrypted for privacy.

This Home Health System is by default a personal and closed system. The
person using the system can grant other people or services access to part of the
data collected by the system. For example, the user of the system can grant (in
advance) an emergency service access to cameras installed in the home and
sensors worn by the user in the event that a fall is detected by the system, or the
user can allow a doctor to access a user’s medical data during an online
appointment. By letting the user explicitly decide who has access to the health
and activity data, what data they have access to and in what kind of

3
Information, Storage & Access Nick Ipe Mathew

circumstances we begin to address the privacy issues.

B. Sensors
The project relies on the existence of ubiquitous and reliable sensors that
are able to collect information about the wellbeing of the user of the system and
their environment. Fixed wireless sensors are employed to monitor the
environment and provide for an IEEE 802.11.4 (Zigbee) ad hoc wireless network
(see section III-E below). This is done with Telos Rev B Mote devices [6] which
provide built-in temperature, humidity and light sensors that allow for basic
environmental sensing, and expansion for other sensing functionality. Wearable
sensors are also included which measure and analyze the user’s health and
activity such as motion and, in the near future, heart rate.

C. Gateways
SensorNet has two types of gateways: a mobile gateway that is portable
and which the sensors worn by the user can send data to, and a fixed gateway
used to connect sensors in the Home Health System.

D. Sensor Fusion and Network

Alert notifications are sent from the sensors to the gateways which fuse the
information and determine an appropriate response. For example, a belt-worn fall
detection sensor might send an alert at which point the gateway might query a
motion sensor in the appropriate room, and/or a pulse monitor to determine if an
accident has occurred. If normal behavior is detected by the latter devices, then
the event might just be recorded as an incident of interest, or the user might be
prompted to ask if they are alright. If on the other hand no motion is detected
then the gateway might immediately query the user and send an emergency
signal if there is no response within a certain (short) period of time. With the
emergency signal, access would be granted to the remote care provider who
could log in and via the live camera data.

5. Key Properties

The intelligent, monitoring CPS exhibit the following properties:

1. Near-Transparency. Physiological sensors are typically distinguished by
various degrees of intrusiveness, where intrusion may involve using body
tissue to diagnose a particular physiological state or condition. However, so
called non-intrusive sensors are typically obtrusive and cumbersome. The
CPS sensors are transparent or near transparent, i.e., they would
continuously obtain biofeedback from the user’s body, with little or no
additional action taken by the users compared to their usual daily routine.
To achieve real pervasiveness, sensors are integrated near-transparently
with the users routines and living environment, including their garment,
shoes, accessories, cars, furniture, etc.

4
Information, Storage & Access Nick Ipe Mathew

2. Favorable Accuracy and Reliability vs. Cost of Operation. The CPS

would obtain high accuracy and reliability data using relatively inexpensive
sensors. Although most labs-on-chip are on-par with precise laboratory
tests, it still should not be expected from this system to provide
professional-grade accurate, reliable, and timely results. The emphasis is
on monitoring, not on diagnosing, with a similar liability model than that of
companies manufacturing non-medical physiological sensing devices.
3. Secure Communication. Users are allowed to choose their desired level
of privacy in parts of or in all collected data with respect to access by
relatives and friends, health insurance providers, and health-care
professionals. The system would include standards that enable and handle
privacy far more efficiently than separate systems.
4. Analysis. The system analyzes the sensed data with different levels of
abstraction and detail, in order to present it to a health-care professional in
a compact format. The primary role of the CPS analysis tools in the medical
community would be as a provider of a continuum of data beyond the
sporadic data point a doctor normally obtains today, and as a research tool.
5. 4As. This concept, borrowed from the ubiquitous computing research
community, relates to “anywhere, anytime, anyone, any device.” In the
context of the intelligent, monitoring CPS, the system should make the
recorded data and its analysis available to the user or health-care
professional in a 4A-style, according to user-specified privacy scenarios.

6. Conclusion

Fueled by advances in technologies and societal needs, we now have the

unprecedented potential to provide continuous physiological-monitoring to
individuals as they go about their everyday lives. The middleware platform
described enables multi-device sensing, and transparent monitoring, analysis,
storage and presentation of a number of physiological signals. The objective is to
provide safety & security so that elder citizens who might have to leave their own
homes for a group care facility will be able to extend their ability to remain at
home longer. This will in most cases provide them with better quality of life and
better health in a cost effective manner.

References:
1. J. M. Eklund, T R Hansen, J. Sprinkle, S. S. Sastry. "Information Technology
for Assisted Living at Home: Building a Wireless Infrastructure for Assisted
Living". 27th Annual International Conference of the IEEE Engineering In
Medicine and Biology Society (EMBS), 3931-3934, September, 2005.
2. A. Sixsmith and N. Johnson, “Smart sensor to detect the falls of the elderly,” IEEE Pervasive
Computing, vol. 3, no. 2, pp. 42–47, April-June 2004.
3. Kirovski, D., Oliver, N., Sinclair, M., and Tan, D. 2007. Health-OS:: a position paper. In
Proceedings of the 1st ACM SIGMOBILE international Workshop on Systems and Networking

5
Information, Storage & Access Nick Ipe Mathew

Support For Healthcare and Assisted Living Environments (San Juan, Puerto Rico, June 11 - 11,
2007). HealthNet '07. ACM, New York, NY, 76-78.