Aged-related symptom, such as dementia has increased the demands on healthcare facilities globally, resulting in further cost due to staying longer in aged care homes. In worldwide terms, the entire estimated expenditures of dementia were US $815 billion in 2015  . There are more than 46.8 million people suffering from dementia today, and that number is predicted to increase to 74.7 million in 2030 and 131.5 million by 2050  . Traditional healthcare services for elders or age-care homes are generally expensive; that adds high costs for seniors’ families and their local governments. It is essential that governments and healthcare providers worldwide find efficient solutions as an alternative to the traditional healthcare systems  .
The smart homes concept is formally defined as places of residence that are outfitted with computers and technological devices. They aim to provide not only the comfort, convenience, and safe environment, but also the improvement of life quality, and assistance to occupants on a daily basis as well as connecting them to the world beyond  . Research in smart homes focuses on building technologically advanced systems. Smart environments include applications that monitor the elderly unobtrusively via connection sensors, and warn them or their healthcare providers about abnormal conditions  .
Smart homes have been increasingly considered as a feasible option for healthcare monitoring and services for the elderly as well as for disabled people who prefer to stay comfortable in their own homes. Ambient assisted living Radio Frequency based technologies help to recognise the daily life activities, and they also monitor the elderly’s behavioural movements by measuring a set of daily living specified activities, such as standing, sitting, lying, walking, and interaction with furniture or objects. The technologies can potentially assist impaired individuals, such as people suffering from Dementia, in their residential living  .
Location based-systems in smart homes healthcare are one of the new areas on which Internet of Things (IOT) is focusing  . The advancement in pervasive healthcare has changed the perception of healthcare services. Pervasive computing healthcare technologies aim to assist elderly and impaired individuals in their living, particularly easing their daily activities and performing domestic tasks conveniently. Researchers in the pervasive computing field have been investigating several indoor localisation techniques and technologies to improve the accuracy of the locations of target individuals.
This survey paper summarises the state-of-the-art researches in smart homes for healthcare. It also reviews the current challenges for smart homes and RFID for healthcare systems as well as Activity of Daily Living (ADL).
2. The Radio Frequency Identification
RFID is a new and promising technology, which is adapted in many life applications. It has interested several researchers in the field of indoor localisation due to its desirable characteristics such as identification, tracking, detects multiple objects at same time and ability to read multiple Smart homes users at the same time. Numerous studies in Smart homes have exploited the RFID-based technology for finding auspicious indoor positioning solutions for healthcare facilities     .
RFID technology enables tracking individuals and objects in an indoor environment automatically and independently; based on the communication model and via radio waves (between readers and tags). It works by sending and receiving a unique identity of persons and objects wirelessly by using radio waves. The RFID system consists of readers, tags and data collection modules. The readers can be static or mobile. There are two methods for tracking. In the first method, the reader can be installed in a static location inside the household (such as wall, table or kitchen) to sense the movement of RFID tags. Then the reader searches for the tags which are either attached to objects or carried by the person. In the second method, the portable reader detects the static tags in certain positions while the RFID reader can be carried by individuals   .
There are three main categories of RFID tags including active, passive and semi. Active RFID tags have an internal battery to power themselves continuously. They have the greatest range of all three of the types  . However, active tag lifetimes are limited, and they rely on how much energy is stored in the internal batteries. The maintenance and intrusiveness in active tags is much bigger than their passive counterparts. Further, it contributes to radio, and it is sensitive in harsh environments. The price of active tags and the maintenance cost are relatively higher than other types. Semi RFID tags (battery-assisted passive BAP), also have an internal battery to power the internal circuity  . It does not add radio noise and has alonger reading range with a memory to store more data. Nevertheless, because it has a battery which is a larger size, quite expensive, limited battery life.
Passive RFID tags have no internal battery. They are smaller in size and are much cheaper than active or semi-active tags. Notably, passive RFID tags are powered by the radio waves that are emitted by the antennas, and so they do not have internal sources of power and it does not add radio noise with a good resistance performance in harsh environments. The tags are widely adapted in many applications such as when applied to objects (cups, a kettle or furniture) in Smart homes  . The drawbacks about passive RFID tags that they require higher power interrogators, small memory with a limited amount of data to be stored and low reading ranges. Table 1 provides a technical performance comparison between the three main RFID tags type.
3. Smart Homes
3.1. What Is Smart Homes
The term Smart home was officially coined in the 1980s by the American Asso-
Table 1. Comparison between the three main RFID tags type.
ciation of House Builders, even though the concept of wired homes was founded in the 1960s  . Smart homes are equipped with computing and information communication technologies to respond to the needs of occupants to stay safe, comfortable, secure, independent and healthy, This is achieved through the management of the advancement in technologies and to connect homes to the beyond the world  . Smart homes also monitor elderly individuals in real time for their daily life activities. The system works by utilising sensors and tracking technologies to locate and track objects as well as individuals in the indoor environment  . Smart home environments are designed to provide interactive and sensing technologies to facilitate the living support and health monitoring for elders inside residential homes so that they can live independently  .
3.2. Smart Homes in Healthcare Domain
Smart homes for healthcare aim to provide autonomous support for: 1) people living at their residence, 2) elderly and impaired individuals who live independently and require constant health care, and 3) people who suffering from numerous pathologies and handicaps such as chronic diseases that require them to stay at hospital or at a placement in a caregiver’s home  . The technology could potentially improve living quality for elders and disable individuals. Healthcare Smart homes are also defined as a specialised area of smart environments by integrating sensors and actuators to allow communication with inhabitants and localise the subjects intelligently that can support the daily life activity  .
Since the 1990s, ubiquitous homes have been studied by several researchers who have proposed promising contributions in healthcare and in supporting impaired individuals. Chan et al.  reviewed other relevant aspects in Smart homes such as human activity recognition and the efficiency of implemented sensor systems. The authors argued that smart homes are one of the favourable, cost-effective solutions for home care for the elderly and people with disabilities.
3.3. Healthcare Challenges in Smart Homes
Smart homes are built to facilitate assist in the daily lives of impaired individuals. Nevertheless, researchers are facing challenges to deliver an integrated solution. Smart homes have become a feasible and cost-effective aid to assist impaired individuals and to live independently. Nevertheless, there are major issues with Smart homes which are outlined below.
Although researchers have introduced cheap Smart homes health systems that could potentially reduce the cost of health care, affordability in Smart homes is still a hard task to achieve. Smart homes should be designed to minimise the installation cost of components and to Smart homes allowing the reuse of the smarty space components and objects and consequently reducing the final cost  . Smart home devices, such as sensors, system components and system tools, and applications should also reduce the computational time as well as minimising the cost of implementing the system  .
Reliability and usability are important issues to determine whether or not a solution is applicable for healthcare in Smart homes. Demiris revealed that there were significant reliability and user-friendly concerns when using Smart homes technologies in residential homes. The devices and technologies need to be user-friendly so that elderly people can use them on a daily basis without hassle. Adequate training is crucial for elderly users, and the systems should not obstruct user’s movements or daily activities. Smart environments will also help patients and older residents in emergency situations, analyze their daily life patterns, physical movements and reliably monitor physiological parameters such as blood pressure  .
Finding a means to address accuracy and the robustness of activity recognition is a current pressing issue in the Smart home field. At this stage, the infrastructure of a smart home must be designed to perform well to face several sources of data or distinguish between different sources. If the proposed approach ignored the accuracy factor and robustness in activities recognition problem that could contain similar activities, and also perform in various ways as well as account for different users, then unaccountable activities would show up as noise in the data. In most cases, this noise in the data will lower the accuracy and robustness of the system to recognise the activity.
3.3.4. Ethical and Legal Challenges
Privacy is a crucial element when building or adopting Smart homes. Technologies such as sensors and cameras could lead to privacy issues due to the constant surveillance and monitoring required. Consequently, these technologies are less likely to be a feasible solution. Unfortunately, there is still limited regulation on the patients’ rights to protect them from malpractice related issues   .
3.4. Smart Homes Projects in Healthcare
A number of later research projects have utilised Smart homes solutions to benefit impaired individuals, the elderly and patients who require continuous health care support. These projects are summarised in Table 2.
Researchers at the University of Missouri, USA developed a cost effective project called “Aging in place” to assist seniors when living independently at home  . The CASAS  project at the University of Washington aimed to detect activity patterns using data mining techniques. It also created an automation of policies that helped understand the change in activity patterns. The University of Texas at Arlington introduced the Mav Home smart home project that acted as a rational agent to maximise an inhabitant’s living conditions and minimize operational costs  . The Smart Condo at the University of Alberta,
Table 2. Smart homes for healthcare projects.
Canada  developed a simulated Smart home that integrated intelligent technologies such as wireless sensors to assist in remote monitoring, improving the quality of living for chronically ill patients and reducing the time spent in the hospital.
Several smart home projects have been introduced in ambient assisted living situations in Europe. Gloucester’s Smart House  , a community contribution project, targeted the increase of the demographic changes of the elderly through- out the Telecare system, which is based on life style monitoring. SPHERE  by the University of Bristol in the UK aims to help people suffering from chronic health conditions by predicting falls, strokes and to detect periods of depression or anxiety using computer-based therapy as well as analyzing human eating behaviour. Another project named, TREVA  is a smart home station that monitors long-term physiological and psychosocial variables. It helps study the well-being of the individuals, including the slow development and deterioration and their vital signs such as; beat-to-beat RR intervals, activity level, and blood pressure. PROSAFE  aimed to target long-term care and was used as a multi- sensor to monitor elderly people continuously. The system monitors the mobility changes and signals of activities, and it sent alarms in case of emergencies.
Other notable works in Europe are presented at    . Enable project  aimed to provide assistive technologies that were designed to increase the independent living for people suffering from dementia. Devices were easily installed to assist the patients without technical supporters. PAMAP  was an Information Communication Technology (ICT) based system that targeted the physical activity of elderly individual’s in clinical environments and on a daily basis. Similar projects such as (HMFM, HOPE and HERA  ) were innovative ICT service systems focused on ambient assisted living (AAL) and cost-effective solutions.
In Asia, many smart home projects have been carried out by researchers. In Japan, the Ministry of International Trade and Industry developed a series of 13 research examples for one project called “Welfare Techno Houses”  . This project aimed to monitor human behaviour on a daily basis in terms of improving the quality of life for both mental and physical health using a combination of infrared and magnetic positioning sensors. Ubiquitous Home  is a home context-aware service oriented which was designed to support seniors in real life to help them to live independently in their homes. It integrated devices and sensors with existing data network infrastructure. Intelligent Sweet Home was introduced to provide an easy living environment for the inhabitants by giving the subjects the freedom of movement using hand gesture recognition  .
In Australia, Celler et al.  proposed a system that showed the interaction between participants and environments while it examined the health status of elderly participants by monitoring their activity remotely in a smart environment. Researchers also introduced a smart home model that helps the elderly in their life and support their needs based on simple approaches using a hidden semi-Markov  .
3.5. RFID Technology in Healthcare
RFID technology enables tracking individuals and objects in an indoor environment automatically and independently, based on the communication model and via radio waves (between readers and tags). It works by sending and receiving a unique identity of persons and objects wirelessly by using radio waves. The RFID system consists of readers, tags and data collection modules. The readers can be static or mobile. There are two methods for tracking. In the first method, the reader can be installed in a static location inside the household (such as wall, table or kitchen) to sense the movement of RFID tags. Then the reader searches for the tags which are either attached to objects or carried by the person. In the second method, the portable reader detects the static tags in certain positions while the RFID reader can be carried by individuals   .
In the healthcare domain, RFID technology has been adapted by caregivers to reduce the gap for health care progression and improve patients care. RFID systems have tremendous benefits in smart home healthcare particularly, 1) RFID tags are fairly small and easy to attach to objects (Drugs container, medical supplies, wheelchair, kittle cups, furniture, etc.) and 2) they are light and practical enough to be worn by individuals. Smart home healthcare can provide facilities and real-time tracking for elders and patients through the use of RFID. RFID chips can provide a highly accurate location of patients, and they also collect information for health care professionals. RFID technologies are potentially applicable for the indoor object and subject localisation and recognition of activity and user interaction with household objects. It works by categorising the information from RFID sensors to define the nature of daily life activities on a daily basis.
Smart homes health based monitoring system with RFID consists of several components that are combined in one context-aware system (see Figure 1). The architecture includes three main layers as shown in Figure 2.
3.5.1. Sensing Layer
This layer consists of RFID physical components which sense the movement and targeted objects (e.g. Medical equipment). Furthermore, it captures the data from the individuals and detects their health status for further processing. The layer collects the information from RFID devices in the test bed from either environmental (e.g. RFID sensors) or wearable sensors (e.g. RFID and accelerometer). RFID Static Environmental Sensors are commercially available with various
Figure 1. Components of RFID system in smart homes healthcare applications.
Figure 2. RFID-based perception of smart homes for health.
functionalities. RFID Wearable Sensors can be worn by the participants to measure a person’s interactions with home objects and track body movement or to detect a fall, etc.
3.5.2. Middleware Layer
The raw data from the physical layer is now translated to the context using inference engines that describe the condition of the individuals. The classifiers filter and categorize the data to a particular context such as position and movement of the person  . Data reduction and data analysis are also processed in this layer. The software in this layer may combine multiple sensors to analyze a data stream intelligibly  . The inference engines are considered as a knowledge representation in the middleware layer as the main component of the RFID systems  .
3.5.3. Service Layer
RFID Health information systems in the service layer store the information about an individual’s health and physical condition (e.g. Health database server) which will be accessible by medical staff and caregivers in queries  throughout real time monitoring servers. The context-aware reasoning module assists the end users of their health care needs in various ways such as a notification or warning in case of risks. It also notifies the caregivers of the health of individuals through monitoring and assessment consoles  . These consoles help the health care researchers and practitioners to monitor the patients and to provide the patients’ health status and medical information. The service layer allows the caregivers to interact remotely with the patients and assist them when dealing with abnormal health conditions.
Context-aware for healthcare has significantly enhanced the quality of healthcare services and facilitated services delivering in healthcare smart home. It is apparent in RFID-based solutions and researches which are improving the advancement in the field. Table 3 summarizes early contribution of RFID smart home projects in healthcare and wellbeing.
4. Activity in Daily Living in Smart Homes for Healthcare
The concept of Activity in Daily Living (ADL) refers to the things that we do in our daily life and daily self-care activities such as feeding, bathing, dressing, grooming, work, homemaking and leisure  . These activities define the ability to live in residential homes independently. ADLs are categorized into two main groups, basic ADLs (BADLs) and instrumental ADLs (IADLs). BADLs are the
Table 3. Comparison between various RFID-based solutions in healthcare.
basic domestic and necessary human activities for individuals’ daily routines including mobility, eating, drinking, sleeping, dressing, bathing and going to the bathroom, etc. IADLs are other tasks that are not crucial for life. However, IADLs comfort the elderly and impaired individuals such as housework, preparing food, medication, exercising, shopping, ironing, sweeping and telephoning.
The recognition of human activities in indoor environments is a difficult task to achieve  . ADL focuses on addressing the challenges and finding solutions for understanding human activity in smart environments. Ubiquitous environments like Smart homes have facilitated the daily activities detection, assisted participants with housekeeping tasks as well as helped the impaired individuals and elderly to live comfortably and independently. Various environmental sensors such as RFID, wearable sensors, and vital signs sensors have been deployed in SH solutions to collect data such as location, movement patterns and patient status. The data is then translated to descriptions of activities using models and algorithms within context-aware systems and computerized applications.
4.1. Sensors for Activity in Daily Living
There are three main groups of sensors for human activity recognition including wearable based, physical environment based and other sensors as following.
4.1.1. Physical Environment Based Sensors
Types of sensors such as RFID, Proximity, Pressure, Zigbee, and Wifi can be used to detect the interaction between the human and the environment around them  . Environmental variable based sensors use the raw data from sensed objects to assume the nature of activity undertaken by the individuals  . The distributed sensors detect the activity by entities and their interaction with objects. The data is collected by the ubiquitous sensors and is then sent to a local server for further processing.
4.1.2. Wearable Based Sensors
Wearable sensors such as inertial sensors, accelerometers, electromechanical switches, goniometers and pedometers gyroscopes are body-attached sensors and are considered one of the most common sensors for human activity recognition. They are used to recognise the motions of a human body and to support the human recognition movements as well as falls detection using wireless monitoring systems  . The devices are designed to continuously measure physiological data (vital signs of thehuman body) and biomechanical data. Analysing such data will help to identify human activities in daily living and translate them into a meaningful form using pattern recognition  .
4.1.3. Other Activity Recognition Sensors
Camera based sensors, which are widely used for human activity recognition within a finite sensing coverage are those sensors which rely on the cameras recording and video sequences to recognise the human activity using computer vision algorithms  . Video sensors such RGB video  , RGB-D video  and depth images sensors  are common types of visual sensors and broadly accepted in human activity recognition with good recognition rates. However, they are costly, have high energy consumption and also require frequent maintenance and are subjected to privacy related concerns.
4.2. Problems Related to Activity of Daily Living in Healthcare
4.2.1. Activity Misclassification
This problem happens when the method cannot distinguish the types of ADLs, i.e. BADLs or IADLs  .
4.2.2. Specifics Activities
Some of the BADL activities such as making a sandwich and making toast are usually classified as the same. However, they are different activities and need to be identified differently in the discriminated model  .
4.2.3. Ambiguous Activities
These occur when activities that are not predefined previously in the training model appear. These also happen when several sensors and objects are activated at the same time so that the system reports the same activity from different sensors. For example, most of the systems classify the sleeping activity as sleeping while we cannot justify whether a person is sleeping or reading a book or watching TV   .
Some of the current issues    related to ADLs in Smart homes are summarized in Table 4.
Table 4. Issues related to ADLs in smart homes.
4.3. Research Challenges in ADL
ADL detection is still a hard task to achieve in Smart homes in regards to the healthcare requirements. Many approaches have been introduced towards solving ADL recognition problems; however, there are still limitations. Table 5, summarizes some of current challenges   of ADLs from the literature.
5. Conclusion and Future Outlook
In this paper, we reviewed the current state-of-the-art works in Smart homes in the healthcare domain. We discussed the most popular radio frequency technologies and projects in indoor positioning. Among those RFID systems employed in Smart home environments, we have compared them based on performance criteria such as Affordability, Reliability, and Robustness. There is a trade-off between these metrics. A solution of a more accurate system in terms of detecting and localizing people and their movement will typically increase the cost and complexity.
We also reviewed the challenges that are faced by Smart homes in the healthcare domain. The paper analyzed the activity of daily living and the importance of predicting the nature of the different activity that is performed by individuals for a better understanding of human activity recognition. The study indicated that there were limitations in RFID healthcare solutions in Smart homes and challenges facing ADL recognition in Smart home settings.
The advancement of indoor positioning with Radio Frequency sensing technologies and the development of human activities detection techniques in Smart homes have facilitated the way people live and complete their daily tasks. However, there are still several challenges which need to be addressed by researchers, particularly.
Table 5. Current research challenges in ADLs.
・ Developing new algorithms to enhance the accuracy of tracking individuals and detecting human activities in real time.
・ Using new cost-effective technologies (e.g. RFID) to allow real test scenarios in residential homes within clinical trials or healthcare.
・ The deployment of large-scale tests with real objects enables different scenarios in real life settings for analyzing human behaviour over the long term.
・ Authentication methods should be considered in the deployment of a smart home system with different levels and forms of security.
・ Use of video cameras where the data collected might be misinterpreted or misused. Therefore, there is need for developing non-invasive solutions to address these challenges.
 World Alzheimer Report 2015 (2015) The Global Impact of Dementia.
 Alsinglawi, B., Liu, T., Nguyen, Q., Gunawardana, U., Maeder, A. and Simoff, S. (2016) Passive RFID Localisation Framework in Smart Homes Healthcare Settings. Studies in Health Technology and Informatics, 231, 1.
 Kim, S.-C., Jeong, Y.-S. and Park, S.-O. (2013) RFID-Based Indoor Location Tracking to Ensure the Safety of the Elderly in Smart Home Environments. Personal and Ubiquitous Computing, 17, 1699-1707.
 Wan, J., O’Grady, M.J. and O’Hare, G.M. (2015) Dynamic Sensor Event Segmentation for Real-Time Activity Recognition in a Smart Home Context. Personal and Ubiquitous Computing, 19, 287-301.
 Bouchard, K., Bilodeau, J.-S., Fortin-Simard, D., Gaboury, S., Bouchard, B. and Bouzouane, A. (2014) Human Activity Recognition in Smart Homes Based on Passive RFID Localization. Proceedings of the 7th International Conference on Pervasive Technologies Related to Assistive Environments, Rhodes, Greece, 27-30 May 2014, Article No. 1.
 Alsinglawi, B., Elkhodr, M., Nguyen, Q.V., Gunawardana, U., Maeder, A. and Simoff, S. (2017) RFID Localisation for Internet of Things Smart Homes: A Survey. International Journal of Computer Networks & Communications (IJCNC).
 Cislo, N. (2010) Undernutrition Prevention for Disabled and Elderly People in Smart Home with Bayesian Networks and RFID Sensors. In: Lee, Y., et al., Eds., Aging Friendly Technology for Health and Independence. ICOST 2010. Lecture Notes in Computer Science, Vol. 6159, Springer, Berlin, Heidelberg, 246-249.
 Postolache, G., Girao, P.S., Moura, C.M. and Postolache, O. (2011) Rehabilitative TeleHealthCare for Post-Stroke Outcome Assessment. Proceedings of the 5th International Conference on in Pervasive Computing Technologies for Healthcare, Dublin, 23-26 May 2011, 408-413.
 Gu, H. and Wang, D. (2009) A Content-Aware Fridge Based on RFID in Smart Home for Home-Healthcare. 11th International Conference on Advanced Communication Technology, Phoenix Park, 15-18 February 2009, 987-990.
 Zhang, D., Zhou, J., Guo, M., Cao, J. and Li, T. (2011) TASA: Tag-Free Activity Sensing Using RFID tag Arrays. IEEE Transactions on Parallel and Distributed Systems, 22, 558-570.
 Harper, R. (2003) Inside the Smart Home. Springer Science & Business Media, Berlin, Heidelberg. http://www.springer.com/la/book/9781852336882
 Garlan, D., Siewiorek, D.P., Smailagic, A. and Steenkiste, P. (2002) Project Aura: Toward Distraction-Free Pervasive Computing. IEEE Pervasive Computing, 1, 22-31.
 Noury, N., Virone, G., Barralon, P., Ye, J., Rialle, V. and Demongeot, J. (2003) New Trends in Health Smart Homes. Proceedings of the 5th International Workshop on Enterprise Networking and Computing in Healthcare Industry, 7 June 2003, 118-127.
 Vega-Barbas, M., Pau, I., Martín-Ruiz, M.L. and Seoane, F. (2015) Adaptive Software Architecture Based on Confident HCI for the Deployment of Sensitive Services in Smart Homes. Sensors, 15, 7294-7322.
 Korhonen, I., Parkka, J. and Van Gils, M. (2003) Health Monitoring in the Home of the Future. IEEE Engineering in Medicine and Biology Magazine, 22, 66-73.
 Rashidi, P. and Mihailidis, A. (2013) A Survey on Ambient-Assisted Living Tools for Older Adults. IEEE Journal of Biomedical and Health Informatics, 17, 579-590.
 Rantz, M.J., Skubic, M., Koopman, R.J., Phillips, L., Alexander, G.L., Miller, S.J., et al. (2011) Using Sensor Networks to Detect Urinary Tract Infections in Older Adults. 13th IEEE International Conference on e-Health Networking Applications and Services, Columbia, MO, 13-15 June 2011, 142-149.
 Rashidi, P. and Cook, D.J. (2009) Keeping the Resident in the Loop: Adapting the Smart Home to the User. IEEE Transactions on Systems, Man, and Cybernetics— Part A: Systems and Humans, 39, 949-959.
 Cook, D.J., Youngblood, M., Heierman III, E.O., Gopalratnam, K., Rao, S., Litvin, A., et al. (2003) MavHome: An Agent-Based Smart Home. Proceedings of the 1st IEEE International Conference on Pervasive Computing and Communications, Fort Worth, TX, 26 March 2003, 521-524.
 Korhonen, I., Lappalainen, R., Tuomisto, T., Koobi, T., Pentikainen, V., Tuomisto, M., et al. (1998) TERVA: Wellness Monitoring System. Proceedings of the 20th Annual International Conference of the IEEE in Engineering in Medicine and Biology Society, 4, 1988-1991.
 Adlam, T., Faulkner, R., Orpwood, R., Jones, K., Macijauskiene, J. and Budraitiene, A. (2004) The Installation and Support of Internationally Distributed Equipment for People with Dementia. IEEE Transactions on Information Technology in Biomedicine, 8, 253-257.
 Barnes, N., Edwards, N., Rose, D. and Garner, P. (1998) Lifestyle Monitoring Technology for Supported Independence. Computing & Control Engineering Journal, 9, 169-174.
 Yamazaki (2005) Ubiquitous Home: Real-Life Testbed for Home Context-Aware Service. 1st International Conference on Testbeds and Research Infrastructures for the Development of Networks and Communities, 23-25 February 2005, 54-59.
 Do, J.-H., Jang, H., Jung, S.H., Jung, J. and Bien, Z. (2005) Soft Remote Control System in the Intelligent Sweet Home. IEEE/RSJ International Conference on Intelligent Robots and Systems, 2-6 August 2005, 3984-3989.
 Yamaguchi, A., Ogawa, M., Tamura, T. and Togawa, T. (1998) Monitoring Behavior in the Home Using Positioning Sensors. Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 4, 1977-1979.
 Zhu, N., Diethe, T., Camplani, M., Tao, L., Burrows, A., Twomey, N., et al. (2015) Bridging e-Health and the Internet of Things: The SPHERE Project. IEEE Intelligent Systems, 30, 39-46.
 University of Alberta (2015, 10/08/2005) Smart Condo Project http://www.hserc.ualberta.ca/Resources/Spaces/SmartCondo.aspx
 Chan, M., Campo, E. and Estève, D. (2005) Assessment of Activity of Elderly People Using a Home Monitoring System. International Journal of Rehabilitation Research, 28, 69-76.
 Reiss, A. and Stricker, D. (2012) Introducing a New Benchmarked Dataset for Activity Monitoring. 16th International Symposium on Wearable Computers (ISWC), Newcastle, 18-22 June 2012, 108-109.
 Ambient Assisted Living (2011). http://www.aal-europe.eu
 Celler, B., Earnshaw, W., Ilsar, E., Betbeder-Matibet, L., Harris, M., Clark, R., et al. (1995) Remote Monitoring of Health Status of the Elderly at Home. A Multidisciplinary Project on Aging at the University of New South Wales. International Journal of Bio-Medical Computing, 40, 147-155.
 Duong, T.V., Phung, D.Q., Bui, H.H. and Venkatesh, S. (2006) Human Behavior Recognition with Generic Exponential Family Duration Modeling in the Hidden Semi-Markov Model. 18th International Conference on Pattern Recognition, Hong Kong, 20-24 August 2006, 202-207.
 Lee, H. and Kwon, J. (2013) The Smart Home Service System Architecture for Healthy and Safe Human Life. ASTL, 25, 13-16. http://onlinepresent.org/proceedings/vol25_2013/4.pdf
 Helal, A., Cook, D.J. and Schmalz, M. (2009) Smart Home-Based Health Platform for Behavioral Monitoring and Alteration of Diabetes Patients. Journal of Diabetes Science and Technology, 3, 141-148.
 Hu, L., Ong, D.M., Zhu, X., Liu, Q. and Song, E. (2015) Enabling RFID Technology for Healthcare: Application, Architecture, and Challenges. Telecommunication Systems, 58, 259-271.
 Neuhaeuser, J., Gaensler, S., Kreutzer, J.F., Reimer, S.M., Lueth, T.C. and D’Angelo, L.T. (2016) Recording Proximity to Everyday Objects with a Radio Frequency Identification Logger while Performing Activities of Daily Living. 2014 IEEE International Conference on Robotics and Biomimetics (ROBIO), Bali, 5-10 December 2014, 1856-1861. http://ieeexplore.ieee.org/document/7090606/
 Hoque, E., Dickerson, R.F. and Stankovic, J.A. (2010) Monitoring Body Positions and Movements during Sleep Using Wisps. Wireless Health, San Diego, CA, 5-7 October 2010, 44-53.
 Zhou, M. and Ranasinghe, D.C. (2014) A Novel Approach for Addressing Wandering off Elderly Using Low Cost Passive RFID Tags. In: Stojmenovic, I., Cheng, Z. and Guo, S., Eds., Mobile and Ubiquitous Systems: Computing, Networking, and Services. MobiQuitous 2013. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, Vol. 131, Springer, Cham, 330-343.
 Parlak, S., Marsic, I. and Burd, R.S. (2011) Activity Recognition for Emergency Care Using RFID. Proceedings of the 6th International Conference on Body Area Networks, Beijing, 7-8 November 2011, 40-46.
 MedicineNet (2012) Definition of ADLs (Activities of Daily Living).
 Abbate, S., Avvenuti, M. and Light, J. (2014) Usability Study of a Wireless Monitoring System among Alzheimer’s Disease Elderly Population. International Journal of Telemedicine and Applications, 2014, Article ID: 617495.
 Ke, S.-R., Thuc, H.L.U., Lee, Y.-J., Hwang, J.-N., Yoo, J.-H. and Choi, K.-H. (2013) A Review on Video-Based Human Activity Recognition. Computers, 2, 88-131.
 Lei, J., Ren, X. and Fox, D. (2012) Fine-Grained Kitchen Activity Recognition Using RGB-D. Proceedings of the 2012 ACM Conference on Ubiquitous Computing, Pittsburgh, 5-8 September 2012, 208-211.
 Shotton, J., Sharp, T., Kipman, A., Fitzgibbon, A., Finocchio, M., Blake, A., et al. (2013) Real-Time Human Pose Recognition in Parts from Single Depth Images. Communications of the ACM, 56, 116-124.
 Wu, J., Osuntogun, A., Choudhury, T., Philipose, M. and Rehg, J.M. (2007) A Scalable Approach to Activity Recognition Based on Object Use. IEEE 11th International Conference on Computer Vision, Rio de Janeiro, 14-21 October 2007, 1-8.
 Wongpatikaseree, K., Ikeda, M., Buranarach, M., Supnithi, T., Lim, A.O. and Tan, Y. (2012) Activity Recognition Using Context-Aware Infrastructure Ontology in Smart Home Domain. 7th International Conference on Knowledge, Information and Creativity Support Systems (KICSS), Melbourne, 8-10 November 2012, 50-57.
 Ni, Q., García Hernando, A.B. and de la Cruz, I.P. (2015) The Elderly’s Independent Living in Smart Homes: A Characterization of Activities and Sensing Infrastructure Survey to Facilitate Services Development. Sensors, 15, 11312-11362.
 Khusainov, R., Azzi, D., Achumba, I.E. and Bersch, S.D. (2013) Real-Time Human Ambulation, Activity, and Physiological Monitoring: Taxonomy of Issues, Techniques, Applications, Challenges and Limitations. Sensors, 13, 12852-12902.