Patel et al. Journal of NeuroEngineering and Rehabilitation 2012, 9:21
`http://www.jneuroengrehab.com/content/9/1/21
`
`J N E R JOURNAL OF NEUROENGINEERING
`
`AND REHABILITATION
`
`R EV I E W
`Open Access
`A review of wearable sensors and systems with
`application in rehabilitation
`Shyamal Patel1,2, Hyung Park3, Paolo Bonato1,4, Leighton Chan3 and Mary Rodgers5,6*
`
`Abstract
`The aim of this review paper is to summarize recent developments in the field of wearable sensors and systems
`that are relevant to the field of rehabilitation. The growing body of work focused on the application of wearable
`technology to monitor older adults and subjects with chronic conditions in the home and community settings
`justifies the emphasis of this review paper on summarizing clinical applications of wearable technology currently
`undergoing assessment rather than describing the development of new wearable sensors and systems. A short
`description of key enabling technologies (i.e. sensor technology, communication technology, and data analysis
`techniques) that have allowed researchers to implement wearable systems is followed by a detailed description of
`major areas of application of wearable technology. Applications described in this review paper include those that
`focus on health and wellness, safety, home rehabilitation, assessment of treatment efficacy, and early detection of
`disorders. The integration of wearable and ambient sensors is discussed in the context of achieving home
`monitoring of older adults and subjects with chronic conditions. Future work required to advance the field toward
`clinical deployment of wearable sensors and systems is discussed.
`Keywords: Wearable sensors and systems, Home monitoring, Telemedicine, Smart home
`
`Introduction
`The US health care system faces daunting challenges.
`With the improvements in health care in the last few dec-
`ades, residents of industrialized countries are now living
`longer, but with multiple, often complex, health conditions
`[1-3]. Survival from acute trauma has also improved, but
`this is associated with an increase in the number of indivi-
`duals with severe disabilities [4]. From an epidemiological
`standpoint, the cohort of “baby boomers” in the US is now
`reaching an age at which they will begin to severely stress
`the Medicare system. Finally, recent health care reform
`efforts may add 32 million newly insured patients to the
`health care system in the next few years [5].
`These altered demographics raise some fundamental
`questions
`(cid:129) How do we care for an increasing number of indivi-
`duals with complex medical conditions?
`(cid:129) How do we provide quality care to those in areas
`with reduced access to providers?
`
`* Correspondence: MRodgers@som.umaryland.edu
`5Department of Physical Therapy and Rehabilitation Science, University of
`Maryland School of Medicine, Baltimore, MD, USA
`Full list of author information is available at the end of the article
`
`(cid:129) How do we maximize the independence and partici-
`pation of an increasing number of individuals with
`disabilities?
`Cleary, answers to these questions will be complex and
`will require changes into how we organize and pay for
`health care. However, part of the solution may lie in how
`and to what extent we take advantage of recent advances
`in information technology and related fields. Currently,
`there exist technologies that hold great promise to expand
`the capabilities of the health care system, extending its
`range into the community, improving diagnostics and
`monitoring, and maximizing the independence and parti-
`cipation of individuals. This paper will discuss these tech-
`nologies in depth, with a focus on remote monitoring
`systems based on wearable technology. We chose to focus
`on these technologies because recent developments in
`wearable sensor systems have led to a number of exciting
`clinical applications.
`Wearable sensors have diagnostic, as well as monitoring
`applications. Their current capabilities include physiologi-
`cal and biochemical sensing, as well as motion sensing
`[6,7]. It is hard to overstate the magnitude of the problems
`that these technologies might help solve. Physiological
`
`© 2012 Patel et al; licensee BioMed Central Ltd. This is an Open Access article distributed under the terms of the Creative Commons
`Attribution License (http://creativecommons.org/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction in
`any medium, provided the original work is properly cited.
`
`Petitioner Apple Inc. – Ex. 1021, p. 1
`
`

`

`Patel et al. Journal of NeuroEngineering and Rehabilitation 2012, 9:21
`http://www.jneuroengrehab.com/content/9/1/21
`
`Page 2 of 17
`
`monitoring could help in both diagnosis and ongoing
`treatment of a vast number of individuals with neurologi-
`cal, cardiovascular and pulmonary diseases such as sei-
`zures, hypertension, dysrthymias, and asthma. Home
`based motion sensing might assist in falls prevention and
`help maximize an individual’s independence and commu-
`nity participation.
`Remote monitoring systems have the potential to miti-
`gate problematic patient access issues. Nearly 20% of those
`in the US live in rural areas, but only 9% of physicians
`work in rural areas [8]. Access may get worse over time as
`many organizations are predicting a shortfall in primary
`care providers as health care reform provides insurance to
`millions of new patients [9]. There is a large body of litera-
`ture that describes the disparities in care faced by rural
`residents [8]. Compared to those in urban areas, those in
`rural areas travel 2 to 3 times farther to see a physician,
`see fewer specialists, and have worse outcomes for such
`common conditions as diabetes, and heart attack [9,10].
`Wearable sensors and remote monitoring systems have
`the potential to extend the reach of specialists in urban
`areas to rural areas and decrease these disparities.
`A conceptual representation of a system for remote
`monitoring is shown in Figure 1. Wearable sensors are
`used to gather physiological and movement data thus
`enabling patient’s status monitoring. Sensors are deployed
`according to the clinical application of interest. Sensors to
`monitor vital signs (e.g. heart rate and respiratory rate)
`would be deployed, for instance, when monitoring patients
`with congestive heart failure or patients with chronic
`
`obstructive pulmonary disease undergoing clinical inter-
`vention. Sensors for movement data capturing would be
`deployed, for instance, in applications such as monitoring
`the effectiveness of home-based rehabilitation interventions
`in stroke survivors or the use of mobility assistive devices
`in older adults. Wireless communication is relied upon to
`transmit patient’s data to a mobile phone or an access
`point and relay the information to a remote center via the
`Internet. Emergency situations (e.g. falls) are detected via
`data processing implemented throughout the system and
`an alarm message is sent to an emergency service center to
`provide immediate assistance to patients. Family members
`and caregivers are alerted in case of an emergency but
`could also be notified in other situations when the patient
`requires assistance with, for instance, taking his/her medi-
`cations. Clinical personnel can remotely monitor patient’s
`status and be alerted in case a medical decision has to be
`made.
`Despite the potential advantages of a remote monitoring
`system relying on wearable sensors like the one described
`above, there are significant challenges ahead before such a
`system can be utilized on a large scale. These challenges
`include technological barriers such as limitations of cur-
`rently available battery technology as well cultural barriers
`such as the association of a stigma with the use of medical
`devices for home-based clinical monitoring. In the follow-
`ing section, we discuss key technologies enabling the
`development and deployment of wearable technologies
`and remote monitoring systems. The next section
`describes wearable and ambient sensor technologies that
`
`Figure 1 Illustration of a remote health monitoring system based on wearable sensors. Health related information is gathered via body-
`worn wireless sensors and transmitted to the caregiver via an information gateway such as a mobile phone. Caregivers can use this information
`to implement interventions as needed.
`
`Petitioner Apple Inc. – Ex. 1021, p. 2
`
`

`

`Patel et al. Journal of NeuroEngineering and Rehabilitation 2012, 9:21
`http://www.jneuroengrehab.com/content/9/1/21
`
`Page 3 of 17
`
`are essential components of systems to monitor patients in
`the home and community settings. Examples of applica-
`tions of these technologies largely taken from a National
`Science Foundation initiated study of European projects
`focused on rehabilitation technology [11] are then pre-
`sented. Conclusions and future developments that we
`foresee in the field of remote monitoring of patients’ status
`via wearable technology are discussed in the final section.
`
`Key enabling technologies
`Wearable systems for patients’ remote monitoring consist
`of three main building blocks: 1) the sensing and data
`collection hardware to collect physiological and move-
`ment data, 2) the communication hardware and software
`to relay data to a remote center, and 3) the data analysis
`techniques to extract clinically-relevant information from
`physiological and movement data. Recent advances in
`sensor technology, microelectronics, telecommunication,
`and data analysis techniques have enabled the develop-
`ment and deployment of wearable systems for patients’
`remote monitoring. Researchers have relied upon
`advances in the above-mentioned fields to address short-
`comings of ambulatory technologies (e.g. Holter moni-
`tors) that had previously prevented long-term monitoring
`of patients’ status in the home and community settings.
`The miniaturization of sensors and electronic circuits
`based on the use of microelectronics has played a key role
`in the development of wearable systems. One of the major
`hurdles to the adoption of sensing technology, especially
`for wearable applications, has been the size of the sensors
`and front-end electronics that, in the past, made the hard-
`ware to gather physiological and movement data too
`obtrusive to be suitable for long-term monitoring applica-
`tions. Recent developments in the field of microelectronics
`have allowed researchers to develop miniature circuits
`entailing sensing capability, front-end amplification,
`microcontroller functions, and radio transmission. The
`flexible circuit shown in Figure 2 is an example of such
`technology and allows one to gather physiological data as
`well as transmit the data wirelessly to a data logger using a
`low-power radio. Particularly relevant to applications in
`the field of rehabilitation are advances in technology to
`manufacture microelectromechanical systems (MEMS).
`MEMS technology has enabled the development of minia-
`turized inertial sensors that have been used in motor activ-
`ity and other health status monitoring systems. By using
`batch fabrication techniques, significant reduction in the
`size and cost of sensors has been achieved. Microelectro-
`nics has also been relied upon to integrate other compo-
`nents, such as microprocessors and radio communication
`circuits, into a single integrated circuit thus resulting in
`System-on-Chip implementations [12].
`Advances in material science have enabled the develop-
`ment of e-textile based systems. These are systems that
`
`Figure 2 Flexible wireless ECG sensor with a fully functional
`microcontroller by IMEC. Developments in the field of flexible
`electronics are expected to lead to the advent of smaller, lighter
`and more comfortable wearable systems. (Courtesy of IMEC, The
`Netherlands).
`
`integrate sensing capability into garments. The example
`shown in Figure 3 demonstrates how sensors can be
`embedded in a garment to collect, for instance, electro-
`cardiographic and electromyographic data by weaving
`electrodes into the fabric and to gather movement data
`by printing conductive elastomer-based components on
`the fabric and then sensing changes in their resistance
`associated with stretching of the garment due to subject’s
`movements. Rapid advances in this field promise to deli-
`ver technology that will soon allow one to print a full cir-
`cuit board on fabric.
`Health monitoring applications of wearable systems
`most often employ multiple sensors that are typically
`integrated into a sensor network either limited to body-
`worn sensors or integrating body-worn sensors and
`ambient sensors. In the early days of body-worn sensor
`networks (often referred to as “body sensor networks”),
`the integration of wearable sensors was achieved by run-
`ning “wires” in pockets created in garments for this pur-
`pose to connect body-worn sensors. An example of this
`technology is the MIThril system [13]. Such systems by
`design were not suitable for long-term health monitoring.
`Recently developed wearable systems integrate individual
`sensors into the sensor network by relying on modern
`wireless communication technology. During the last dec-
`ade, we have witnessed tremendous progress in this field
`and the development of numerous communication stan-
`dards for low-power wireless communication. These
`standards have been developed keeping in mind three
`main requirements: 1) low cost, 2) small size of the trans-
`mitters and receivers, and 3) low power consumption.
`With the development of IEEE 802.15.4/ZigBee [14] and
`Bluetooth, tethered systems have become obsolete. The
`recently developed IEEE 802.15.4a standard based on
`
`Petitioner Apple Inc. – Ex. 1021, p. 3
`
`

`

`Patel et al. Journal of NeuroEngineering and Rehabilitation 2012, 9:21
`http://www.jneuroengrehab.com/content/9/1/21
`
`Page 4 of 17
`
`Figure 3 Example of e-textile system for remote, continuous monitoring of physiological and movement data. Embedded sensors
`provide one with the capability of recording electrocardiographic data (ECG) using different electrode configurations as well as
`electromyographic (EMG) data. Additional sensors allow one to record thoracic and abdominal signals associated with respiration and movement
`data related to stretching of the garment with shoulder movements. (Courtesy of Smartex, Italy).
`
`Ultra-wide-band (UWB) impulse radio opens the door
`for low-power, low-cost but high data rate sensor net-
`work applications with the possibility of highly accurate
`location estimation [15].
`Most monitoring applications require that data gath-
`ered using sensor networks be transmitted to a remote
`site such as a hospital server for clinical analysis. This
`can be achieved by transmitting data from the sensor net-
`work to an information gateway such as a mobile phone
`or personal computer. By now most developed countries
`have achieved almost universal broadband connectivity.
`For in-home monitoring, sensor data can be aggregated
`using a personal computer and transmitted to the remote
`site over the Internet. Also, the availability of mobile tele-
`communication standards such as 4 G means that perva-
`sive continuous health monitoring is possible when the
`patient is outside the home environment.
`Mobile phone technology has had a major impact on
`the development of remote monitoring systems based on
`wearable sensors. Monitoring applications relying on
`mobile phones such as the one shown in Figure 4 are
`becoming commonplace. Smart phones are broadly avail-
`able. The global smart phone market is growing at an
`annual rate of 35% with an estimated 220 million units
`shipped in 2010 [16]. Smart phones are preferable to tra-
`ditional data loggers because they provide a virtually
`“ready to use” platform to log data as well as to transmit
`
`data to a remote site. Besides being used as information
`gateways, mobile devices can also function as information
`processing units. The availability of significant computing
`power [17] in pocket-sized devices makes it possible to
`envision ubiquitous health monitoring and intervention
`applications.
`In addition, most mobile devices now include an inte-
`grated GPS tracking system thus making it possible to
`locate patients in case of an emergency. Also, as storage
`and computation becomes more and more cloud based,
`health monitoring systems can become low-cost, plat-
`form-independent, rapidly deployable and universally
`accessible [18,19]. Monitoring devices can become sim-
`pler and cheaper as the computation is pushed to the
`cloud. This enables users to buy off-the-shelf devices and
`access customized monitoring applications via cloud-
`based services [20]. Cloud-based systems can prove espe-
`cially useful for bringing health care services to rural
`areas [21]. In addition, monitoring applications deployed
`via the cloud can be easily updated without requiring
`that the patient installs any software on his/her personal
`monitoring device, thus making system maintenance
`quick and cost effective.
`Finally, the massive amount of data that one can gather
`using wearable systems for patient’s status monitoring
`has to be managed and processed to derive clinically-
`relevant information. Data analysis techniques such as
`
`Petitioner Apple Inc. – Ex. 1021, p. 4
`
`

`

`Patel et al. Journal of NeuroEngineering and Rehabilitation 2012, 9:21
`http://www.jneuroengrehab.com/content/9/1/21
`
`Page 5 of 17
`
`Figure 4 Smart phone based ECG monitoring system by IMEC. The Android based mobile application allows low power ECG sensors to
`communicate wirelessly with the phone. With increasing computational and storage capacity and ubiquitous connectivity, smart phones are
`expected to truly enable continuous health monitoring. (Courtesy of IMEC, The Netherlands).
`
`signal processing, pattern recognition, data mining and
`other artificial intelligence-based methodologies have
`enabled remote monitoring applications that would have
`been otherwise impossible. Although a discussion of the
`various techniques used to process and analyze wearable
`sensor data is outside the scope of this review paper, one
`cannot emphasize enough the fact that data processing
`and analysis techniques are an integral part of the design
`and development of remote monitoring systems based on
`wearable technology.
`
`Sensing technology
`In this section, we provide information concerning the
`sensors used in remote monitoring systems. Information
`gathered using body-worn (i.e. wearable) sensors is col-
`lected ubiquitously thanks to the technologies mentioned
`in the previous section of this review paper. Wearable
`sensors are often combined with ambient sensors when
`subjects are monitored in the home environment as sche-
`matically shown in Figure 5. The combination of wear-
`able and ambient sensors is of great interest in several
`applications in the field of rehabilitation. For instance,
`when monitoring older adults while deploying interven-
`tions to improve balance control and reduce falls, one
`would be interested in using wearable sensors to track
`motion and vital signs. Specifically-designed data analysis
`
`procedures would then be used to detect falls via proces-
`sing of motion and vital sign data. In this context, ambi-
`ent sensors could be used in conjunction with wearable
`sensors to improve the accuracy of falls detection and,
`most importantly, to enable the detection of falls even at
`times when subjects do not wear the sensors. This
`
`Figure 5 Ambient sensors can unobtrusively monitor
`individuals in the home environment. Ambient sensors can
`monitor activity patterns, sleep quality, bathroom visits etc. and
`provide alerts to caregivers when abnormal patterns are observed.
`Such sensors are expected to make the home of the future smarter
`and safer for patients living with chronic conditions.
`
`Petitioner Apple Inc. – Ex. 1021, p. 5
`
`

`

`Patel et al. Journal of NeuroEngineering and Rehabilitation 2012, 9:21
`http://www.jneuroengrehab.com/content/9/1/21
`
`Page 6 of 17
`
`section provides a summary of the state of the art in
`wearable sensor technology and the development of
`ambient sensors.
`
`Wearable sensors
`Physiological measures of interest in rehabilitation include
`heart rate, respiratory rate, blood pressure, blood oxygen
`saturation, and muscle activity. Parameters extracted from
`such measures can provide indicators of health status and
`have tremendous diagnostic value. Until recently, continu-
`ous monitoring of physiological parameters was possible
`only in the hospital setting. But today, with developments
`in the field of wearable technology, the possibility of accu-
`rate, continuous, real-time monitoring of physiological
`signals is a reality.
`Integrating physiological monitoring in a wearable sys-
`tem often requires ingenious designs and novel sensor
`locations. For example, Asada et al. [22] presented a ring
`sensor design for measuring blood oxygen saturation
`(SpO2) and heart rate. The ring sensor was completely
`self-contained. Worn on the base of the finger (like a
`ring), it integrated techniques for motion artifact reduc-
`tion, which were designed to improve measurement accu-
`racy. Applications of the ring sensor ranged from the
`diagnosis of hypertension to the management of conges-
`tive heart failure. A self-contained wearable cuff-less
`photoplethysmographic (PPG) based blood pressure moni-
`tor was subsequently developed by the same research
`group [23]. The sensor integrated a novel height sensor
`based on two MEMS accelerometers for measuring the
`hydrostatic pressure offset of the PPG sensor relative to
`the heart. The mean arterial blood pressure was derived
`from the PPG sensor output amplitude by taking into
`account the height of the sensor relative to the heart.
`Another example of ingenious design is the system
`developed by Corbishley et al. [24] to measure respiratory
`rate using a miniaturized wearable acoustic sensor (i.e.
`microphone). The microphone was placed on the neck to
`record acoustic signals associated with breathing, which
`were band-pass filtered to obtain the signal modulation
`envelope. By developing techniques to filter out environ-
`mental noise and other artifacts, the authors managed to
`achieve accuracy greater than 90% in the measurement of
`breathing rate. The authors also presented an algorithm
`for the detection of apneas based on the above-described
`sensing technology.
`In recent years, physiological monitoring has benefited
`significantly from developments in the field of flexible
`circuits and the integration of sensing technology into
`wearable items [25]. An ear-worn, flexible, low-power
`PPG sensor for heart rate monitoring was introduced by
`Patterson et al. [26]. The sensor is suited for long-term
`monitoring due to its location and unobtrusive design.
`Although systems of this type have shown promising
`
`results, additional work appears to be necessary to
`achieve motion artifact reduction [27,28]. Proper attenua-
`tion of motion artifacts is essential to the deployment of
`wearable sensors. Some of the problems due to motion
`artifacts could be minimized by integrating sensors into
`tight fitting garments. A comparative analysis of different
`wearable systems for monitoring respiratory function was
`presented by Lanata et al. [29]. The analysis showed that
`piezoelectric pneumography performs better than spiro-
`metry. Nonetheless, further advances in signal processing
`techniques to mitigate motion artifacts are needed.
`Biochemical sensors have recently gained a great deal
`of interest among researchers in the field of wearable
`technology. These types of sensors can be used to moni-
`tor the bio-chemistry as well as levels of chemical com-
`pounds in the atmosphere (e.g. to facilitate monitoring
`people working in hazardous environments). From a
`design point of view, biochemical sensors are perhaps the
`most complex as they often require collection, analysis
`and disposal of body fluids. Advances in the field of wear-
`able biochemical sensors has been slow, but research has
`recently picked up pace due to the development of micro
`and nano fabrication technologies [12]. For example,
`Dudde et al. [30] developed a minimally-invasive wear-
`able closed-loop quasi-continuous drug infusion system
`that measures blood glucose levels and infuses insulin
`automatically. The glucose monitor consists of a novel
`silicon sensor that continuously measures glucose levels
`using a microperfusion technique and continuous infu-
`sion of insulin is achieved by a modified advanced insulin
`pump. The device has integrated Bluetooth communica-
`tion capability for displaying and logging data and receiv-
`ing commands from a personal digital assistant (PDA)
`device.
`An array of bio-chemical sensors has been developed as
`part of the BIOTEX project, supported by the European
`Commission. Specifically, the BIOTEX project deals with
`the integration of bio-chemical sensors into textiles for
`monitoring body fluids. Within this project, researchers
`have developed a textile based fluid collecting system and
`sensors for in-vitro and in-vivo testing of pH, sodium and
`conductivity from body sweat [31,32]. By in-vitro and in-
`vivo testing of the wearable system, researchers have
`shown that the system can be used for real-time analysis
`of sweat during physical activity. As part of a similar pro-
`ject called ProeTEX, Curone et al. [33] developed a wear-
`able sensorized garment for firefighters, which integrates a
`CO2 sensor with sensors to measure movement, environ-
`mental and body temperature, position, blood oxygen
`saturation, heart rate and respiration rate. The ProeTEX
`system can warn the firefighters of a potentially dangerous
`environment and also provide information about their
`well being to the control center. The systems developed in
`the above-mentioned projects could be relied upon to
`
`Petitioner Apple Inc. – Ex. 1021, p. 6
`
`

`

`Patel et al. Journal of NeuroEngineering and Rehabilitation 2012, 9:21
`http://www.jneuroengrehab.com/content/9/1/21
`
`Page 7 of 17
`
`design robust e-textile based wearable systems for remote
`health monitoring applications.
`There has been a growing interest in the development of
`self contained lab-on-a-chip systems. Such systems can
`revolutionize point-of-care medical testing and diagnosis
`by making testing and diagnosis fast, cheap and easily
`accessible. Wang et al. [34] developed a system-on-chip
`(SOC), which integrates a pH and temperature sensor, for
`remote monitoring applications. Their SOC includes gen-
`eric sensor interface, ADC, microcontroller, a data enco-
`der and a frequency-shift keying RF transmitter. Similarly,
`Ahn et al. [35] developed a low-cost disposable plastic lab-
`on-a-chip device for biochemical detection of parameters
`such as blood gas concentration and glucose. The biochip
`contains an integrated biosensor array for detecting multi-
`ple parameters and uses a passive microfluidic manipula-
`tion system instead of active microfluidic pumps.
`Finally, applications in rehabilitation of remote monitor-
`ing systems relying on wearable sensors [36] have largely
`relied upon inertial sensors for movement detection and
`tracking. Inertial sensors include accelerometers and gyro-
`scopes. Often, magnetometers are used in conjunction
`with them to improve motion tracking. Today, movement
`sensors are inexpensive, small and require very little
`power, making them highly attractive for patient monitor-
`ing applications.
`
`Ambient sensors
`Examples of instrumented environments include sensors
`and motion detectors on doors that detect opening of,
`for instance, a medicine cabinet, refrigerator, or the
`home front door [37]. This approach has the character-
`istic of being totally unobtrusive and of avoiding the
`problem of misplacing or damaging wearable devices.
`“Smart home” technology that includes ambient and
`environmental sensors has been incorporated in a variety
`of rehabilitation related applications. One such application
`is ambient assisted living (AAL) that refers to intelligent
`systems of health assistance in the individual’s living envir-
`onment [38]. It covers concepts, products and services
`that interlink and improve new technologies and the social
`environment. AAL technologies are embedded (distributed
`throughout the environment or directly integrated into
`appliances or furniture), personalized (tailored to the
`users’ needs), adaptive (responsive to the user and the
`user’s environment) and anticipatory (anticipating users’
`desires as far as possible without conscious mediation).
`Stefanov et al provide a summary of the various types of
`devices that can be installed in smart homes, and the asso-
`ciated target user populations [39].
`Remote monitoring of patient status and self-manage-
`ment of chronic conditions represent the most often
`pursued applications of AAL technologies. The combina-
`tion of wearable and ambient sensors is being explored
`
`and prototypes are being developed. A relevant application
`in the field of rehabilitation relates to the identification of
`a patient’s patterns of activity and on providing sugges-
`tions concerning specific behaviors and exercises for self-
`management of health conditions. In this context, infor-
`mation gathered using wearable sensors is augmented by
`information gathered using ambient sensors. Data col-
`lected using, for instance, body-worn accelerometers could
`be augmented by motion sensors distributed throughout
`the home environment to determine the type and intensity
`of the activities performed by an individual. Accordingly,
`an individual undergoing monitoring who suffers from, for
`instance, chronic obtrusive pulmonary disease could
`receive feedback about not overexerting himself/herself
`and the performance of rehabilitation exercises that would
`be prescribed in order to maintain a satisfactory functional
`level.
`Innovative solutions for recognizing emergencies in the
`home can be achieved through a combination of monitor-
`ing vital parameters of the person living at home as well as
`supervising the conditions of domestic appliances [40].
`Personal safety can be improved if vital data measures are
`combined with the monitoring and control of devices in
`the household. Remote monitoring of potential sources of
`danger increases the individual sense of security and can
`make life much easier and more comfortable (e. g. check-
`ing whether the stove or the coffee machine has been
`switched off and to be able to turn them off remotely if
`necessary). Sensors embedded in electrical devices and in
`doors and windows may be integrated into an easy-to-use
`house-control system that also provides improved perso-
`nal safety and security [41]. An intelligent system may
`issue a reminder to switch off devices and/or lights in
`an apartment or not to forget the pill box or the mobile
`terminal needed to inform friends or neighbors when
`necessary.
`Several smart home projects are currently ongoing
`including the Technology Research for Independent Living
`(TRIL) Center in Ireland [42], the TigerPlace [43] in Mis-
`souri, the Oregon Center for Aging and Technology
`(ORCATECH) [44] in Oregon, the University of Rochester
`Center for Future Health [45], The University of Florida
`Gator-Tech Smart House [46], the Georgia Institute of
`Technology Aware Home [47], and the Massachusetts
`Institute of Technology PlaceLab [48]. The main aim of
`such projects is to explore the use of ambient and/or
`wearable sensing technology to monitor the well-being of
`individuals in the home environment.
`
`Applications
`This section provides about a review of applications of
`wearable and ambient sensors and systems that are rele-
`vant to the field of rehabilitation. The material is orga-
`nized in five sub-sections devoted to summarizing
`
`Petitioner Apple Inc. – Ex. 1021, p. 7
`
`

`

`Patel et al. Journal of NeuroEngineering and Rehabilitation 2012, 9:21
`http://www.jneuroengrehab.com/content/9/1/21
`
`Page 8 of 17
`
`applications focused on: 1) health and wellness monitor-
`ing, 2) safety monitoring, 3) home rehabilitation,
`4) assessment of treatment efficacy, and 5) early detec-
`tion of disorders.
`
`Health & wellness monitoring
`As the world population is aging and health care costs
`are increasing, several countries are promoting “aging in
`place” programs which allow older adults and indivi-
`duals with chronic conditions to remain in the home
`environment while they are remotely monitored for
`safety and for the purpose of facilitating the implemen-
`tation of clinical interventions.
`Monitoring activities performed by older adults and
`individuals with chronic conditions participating in “aging
`in place” programs has been considered a matter of para-
`mount importance. Accordingly, extensive research efforts
`have been made to assess the accuracy of wearable sensors
`in classifying activities of daily living (ADL). Mathie et al
`[49] showed the feasibility of using accelerometers to iden-
`tify the performance of ADL by older adults monitored in
`the home environment. Sazonov et al [50] developed an
`in-shoe pressure and ac