Developing Ambient Intelligence Applications for the Assisted Living of the Elderly

Transcription

1 Developing Ambient Intelligence Applications for the Assisted Living of the Elderly Edgardo Avilés-López, J. Antonio García-Macías, and Ismael Villanueva-Miranda CICESE Research Center, Mexico {avilesl, jagm, ABSTRACT Ambient Assisted Living is a research area which has emerged to assist individuals in performing their everyday activities with the help of ambient intelligence technology. To accomplish this, technological aspects such as context acquisition, device integration, networking, and social aspects such as accessibility, usability, privacy, and others, play an important role. These aspects become crucial when assisting the elderly, because they present very specific and demanding requirements. In this paper, we present work in some application scenarios conducted within our research group, focused on supporting the elderly. The implementation of these scenarios is possible through the use of our proposed technological infrastructure consisting of two main parts: (1) a physical platform constituted by sensors, actuators, RFID tags, and other devices, and (2) a software platform providing Web services with basic blocks such as voice recognition, indoor localization, and others, that can be composed to construct more sophisticated services. Categories and Subject Descriptors D.2.6 [Software Engineering]: Programming Environments; D.2.11 [Software Engineering]: Software Architectures; J.3 [Computer Applications]: Life and Medical Sciences Keywords ambient assisted living, sentient visors, ubiquitous computing, smart home, mobility assistance, audio sensor networks, pervasive health, ubiquitous mashups 1. INTRODUCTION The ubiquitous computing vision [22] describes an augmented world full of intelligent devices that comprises a fine grained distributed network. Ambient intelligence (AmI) goes further by studying how to allow environments to be sensitive, adaptive, and responsive to the presence of people, in order to support them in their day to day experiences [2]. Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. To copy otherwise, to republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. ANT 2010 Paris, France Copyright 20XX ACM X-XXXXX-XX-X/XX/XX...$ We are interested in ambient assisted living (AAL) systems with a special focus on supporting the elderly support (also known as Home Care Systems [6]). The physical and mental declination that comes with the natural aging process is one of the reasons why ambient intelligence aims to come up with new alternatives and innovative tools to improve their lifestyle by helping them to maintain certain degree of independence. The rest of the paper is organized as follows. In section 2 we talk about the motivation of our work and explain why the support for the elders is a good case study for ambient intelligence. Next, in section 3 we discuss some of the related work. In section 4, we present our technological infrastructure, which comprises both a physical and a software platform to build services on top of it. Then, in section 5, we discuss the cases of study developed with our contributions and talk about how they were used to successfully accomplish the specific requirements of each case. In section 6, we talk about the lessons learned and finally, we conclude with some final remarks and outline the future work. 2. MOTIVATION Augmented spaces are particularly helpful for the elders, and, as average life expectancy increases worldwide with an aging population constantly growing [20], we can expect a greater demand for services and applications oriented toward assisting them. These demands include providing services for those who suffer from various illnesses (both mental and physical) such as: diabetes, arthritis, senile dementia, alzheimer, heart-related diseases among many others. The emergence of new types of mobile and embedded computing devices, developments in wireless networking and communications, smart sensors, and others, gives us the tools and methods to come up with innovative services and applications to better assist users, and therefore, improve their lifestyle. Examples of those can be seen in related areas such as tele-homecare [11], pervasive health (or ubi-health) [15], and mobile tele-monitorization [13]. We believe that support for the elderly through AAL infrastructures is the most naturally appropriate. Not just because of its evident social impact, but because of the characteristics of its special requirements. We summarize this by analysing the characteristics shown by a traditional ambient intelligence system, according to Oppermann et al. [16]: Invisible. Since there is the need to track and automatically identify the users of an augmented space, they are required to wear a digital tag that can take the form of a watch, a purse, glasses, be embedded in

2 clothes, and others. In some nursing homes (like the one we applied our cases of study in), residents are required to wear an identification purse, allowing us to replace it by a digitally augmented version. Mobile. As users move around their homes, or nursing rooms, they need to carry with them some of the computation or sensing needed to support their activities. This becomes crucial when dealing with an application that helps the user to take medications, or one in which factors as blood pressure, sugar levels, an others, must be constantly monitored and controlled. Spontaneous communication. In a scenario in which constant connectivity is required and the number of networked elements is high, an ad hoc network infrastructure is needed, in order to guarantee connectivity in spite of node failures. Heterogeneous an hierarchical Augmenting a space usually involves the integration and coordination of several different kind of system nodes and devices. A hierarchical organization of them can help in building a richer encapsulated functionality. For example, a sensor node can provide raw sensorial data, a sensor network on the other hand, can constitute a sort of macroscope we can use to identify composite activities, while hiding us the individual nodes coordination. Context-aware. Three steps are involved: first, raw context data such as temperature, identity, localization, and others, is acquired; second, context is modeled, communicated through the system, and then interpreted; third, context-inferred data is used to perform an action or cast a change in the system. This requirement becomes really important for the elder because some systems usually rely on personal context such as blood pressure, sugar levels, and others. Context in such situations should be communicated in fast, reliable and opportune ways. Anticipatory. The system must take actions on behalf of the user displaying proactive behaviour. For example, if the elder user has suffered a fall, the system must alert the nursing home personnel. Natural communication with users. This requirement is specially important with the elderly. This kind of user presents interaction problems with traditional mechanisms such as mouse, keyboard, text on screens, etc. A new approach must be taken when displaying data, selecting between options, and requesting input data. Possible approaches could be the use of voice commands and visual components. This is a topic of active research (for instance, see [12]). Also, additional research is needed to accomplish proper usability. Natural interaction with users by means of devices they are used to. Users of ambient intelligent systems should consider the use of everyday items as ways of interaction with the users. Adaptive. Systems must be designed to be able to resolve abnormal or exceptional situations autonomously (if possible), and be prepared to support other scenarios the user could need to incorporate or change after time. Also, as technology rapidly evolves, we must design system architectures in such way that new devices and communication technologies can be exploited (as a research instance, see [10]). Along with the above listed characteristics, there are other features: Elder users, and specially, elders hosted in a nursing home are used to stay in well known spaces, for instance, their bedrooms, a game area, a TV room, and so on. Augmentation of their spaces can, therefore, be carefully planned. Detractors of ambient assisted living usually mention privacy as a major concern on supporting scenarios. The elderly, in cases where they are being hosted in homes for their care taking, are constantly being monitored. Their activities are recorded (usually video taped), their localisation tracked, and so on. Also, as the augmented spaces are basically confined spaces, privacy can be relaxed to some extent and not take primary importance on research designs for the elders. 3. RELATED WORK AlarmNET is an AAL system designed to provide assistance through a smart healthcare environment. It specifically targets assisted-living residents and others whom may benefit from continuous remote healthcare monitoring [21]. AlarmNET s network manages an audit trail and continuous medical history while preserving resident s autonomy, comfort and privacy, thus improving security and quality of life. The AlarmNET system [24] is mainly based on a wireless sensor network that provides readings of temperature, light, pulse and blood oxygenation. It also features a circadian activity rhythm analysis program. Similar to AlarmNET, our platform offers a number of different services to support the elder, while we also offer a sensorial infrastructure, we provide other services and tools such as physical actuators, an augmented reality framework, and others, that allow the implementation of many different application scenarios. CenceMe, is a personal sensing system that enables users to share their activities through the Web, particularly through the use of social networks [7]. The CenceMe system can identify the status of a user in terms of his activity (sitting, walking, etc.), disposition (happy, sad, etc.), habits (at work, at he gym, etc.), and surroundings (environmental conditions). While our infrastructure also includes a behavioral analysis service that can be used to infer if a user is seated, walking, or if he has fallen, we are taking this further by offering a complete solution for ambient assisted living applications that use that information to enable further support. EMI 2 lets [8] is a platform that facilitates the development and deployment of AmI scenarios. Users of the platform interact with smart objects in the environment through the use of mobile devices. The platform helps on discovering locally available services, deploying new software representatives of everyday objects, and creating software controllers to be run on mobile devices. Our contributions also consider the interaction with augmented objects through the use of the sentient visor toolkit, which is not just focused on the interaction with the object controllers, but on providing a natural way for the user to interact with them. Or focus is also more general, to provide a platform for the description,

3 discovery, and integration of services that produce compositions to facilitate the development of AmI applications, independently of aspects such as the targeted platform, the programming language, or the scenario where the final application is deployed. 4. TECHNOLOGICAL INFRASTRUCTURE Before presenting and discussing the different scenarios we have explored to support the elders, we have to talk about our technological infrastructure. We have designed and implemented a platform featuring basic services and tools to allow the easy composition of hardware and software functionality. In the following subsections we introduce and detail each of these services and tools. 4.1 Services A service in our platform consists of a RESTful [9] Web service which exposes its functionality by describing what common interfaces it implements, and that notifies its availability within the environment by using the discovery mechanism provided by the platform. We have designed a number of common interfaces for those services, including contextacquisition, behaviour analysis, indoor localization, metadata management, and others. Once the services are registered in the platform, a developer can create compositions by defining which services are involved and the application flow between them. The composition files are sent to one of the execution engines available in the environment, which are in charge of handling the requests and data involved on the execution of the described functionality. The developer can alternatively use our platform framework to directly interact with the discovery and description mechanisms to handle its own composition implementation. Some services in our platform have to notify data as it happens, i.e., they follow an event-based communication. To support this, we have included the publish/subscribe model. For instance, if you want to be notified about new tag readings of an RFID service, you must first subscribe to it and specify the parameters of how and when you will be alerted. As the components of our platform are mostly RESTful Web services, a notification of data usually consists of a POST request to a target subscribed URI. The notification can be configured with aggregation operators. We have implemented a working prototype of our platform that includes server, desktop, and mobile versions of the execution engine. To conduct our cases of study, we also implemented the next basic services: Indoor Localization This service estimates the user s position based on the signal s intensity of surrounding Wi-Fi access points. This approach has been widely used in other work that requires knowledge of user/object location in an indoor environment [14]. The service has to be trained before the location can be estimated. Training is done by measuring Wi-Fi signal strengths at different points of the area to be covered and associating the measured signal strength with a specific location. This process is also associated to the platform being used, additional training is required for each of the different platforms to be used. When an estimation request is issued, the service looks into the measurements stored during training and estimates a position by using a custom heuristic based on the similitude of signal strengths. During experimental tests and using between 3 and 10 access points, we managed to get an average error of 4 meters, which is enough to support the localization needed in our cases of study (as explained in Section 5). Wireless Sensor Networks This service provides a high level abstraction to different wireless sensor platforms, allowing the easy acquisition of raw context. The type of context being acquired depends on the sensorial capability of the nodes in the network. Our setup consisted of 8 MicaZ motes and 10 Telos B motes (both from Crossbow, Inc.) which provided us with environmental (light, temperature, humidity, noise) and user (audio capture, accelerometer) context. In some special cases we attached a sensor node to a user to monitor his behaviour by tracking the changes of the accelerometer data. The current implementation of this service is based on a previous work [3]. This service also offers asynchronous notifications following the publish/subscribe model. An entity should first subscribe itself by describing the desired sensor type, the sensing area of interest, the time window, and the aggregation operator to be applied to sensor readings between that window (e.g., the hourly average temperature of a room). RFID Readers This service provides notifications of RFID tag readings. The intention of this service is to serve as a way for automatic identification of objects and users. We use this service in the taking medications application scenario (see subsection 5.1) where the medicine bottles should be identified. Video Feeds The current implementation of this service takes the form of a Web widget, a visual component that can be easily embedded in other Web pages or systems. However, the design of the service specifies the delivering of a video stream that can be used in conjunction with image processing techniques to offer richer behavioral analysis. Voice Commands Voice commands are a very natural way of interaction where user effort is minimized. With this service, we enable voice commands on an environment by provisioning it with a wireless sensor network where nodes are equipped with a constantly open microphone. The reliability of the voice recognition network is extremely important, as the sensor nodes are highly prone to failures. We have deployed nodes redundantly, often overlapping coverage areas, in this way, if a node fails, another one can perform its functions without disrupting overall system functionality. The main functionality that this service exposes is the notification of a new command identified by the network. To detect a command, the sensor nodes first capture sound, and if it is within the human voice range then they forward it to a base station, where the sound is analyzed to determine if it is a command. The base station is the service provider as well (please refer to [17] for in-depth details). Speech Synthesis Each instance of a provider for this service is directly associated with a speaker. On a request,

4 the message received is synthesized to an audible form and played on the service s speaker. The synthesized speech is another very natural way of interaction with the users, as we don t require them to look a display to acknowledge information. Context Acquisition Automatic Object Identification Augmented Reality Scenario Virtual Object Representation Actuators This kind of services allows the developers to perform a physical reaction in the environment. This reaction can take the form of lights, motors, sounds, and other actuators. We have implemented services to trigger single servo-motors that can be used to open doors or windows. We designed these services in a generic way so the developers can easily adapt them to their own application scenarios. Physical Object Additional Services Input Devices We have implemented services to allow simple input, such as buttons, sliders, touch events, rotators, and others using Phidget hardware [1]. As stated before, one of the common characteristics of an AmI system is to provide natural interaction with the users by means they are used to. We designed the input device services with a general focus, so they can be easily extended to include other types of devices, for example, infrared sensors, electric scales, and others. This type of services are event-based, any entity interested on receiving the event of a new user input must first subscribe. Other Services There are other services implemented to allow specialized actions. One example of these services is the context-processor which receives sensor reading sent by a wireless sensor service and then, after applying a certain logic (through scripts), generates new events. We have used the context-processor service in the intelligent care monitoring application scenario. More services can easily be added to the platform. The necessary steps are: first, develop it on any programming language (as long as it exposes its functionality through the RESTful approach), second, describe which platform interfaces are being implemented by the service in a service description file, and third, to register it on the service discovery mechanism (by using one of the many different provided tools). 4.2 Tools Along with the design and implementation of the services in the platform, we have a couple of tools built on top of our infrastructure to better support the development of AAL applications for the elderly. The most important one is a sentient visor toolkit that can be used to develop applications that allow the interaction of users with augmented objects in a very natural way Sentient Visors User interaction on augmented assisted living environments is intended to be the most natural possible, ideally not requiring the use of traditional means such as displays, keyboards, and so on. When designing interaction of elder users with augmented environments, we must think on new approaches that offer users of advanced age with alternatives that require no previous knowledge nor training to use. Elders need a clear and simple human-interaction model that Figure 1: The application scenario of a sentient visor. presents them filtered, condensed, and summarized information based on their personal profile and preferences. Following the idea introduced by the ambient devices concept [23] we have been working on what we call sentient visors [5]. A sentient visor is a device carried by the user that basically presents three characteristics: a screen, a back-facing camera (pointing to the back of the screen), and some sensing capabilities. A tablet computer or a modern smartphone can be currently used as sentient visors [25]. The scenario of use for a sentient visor is as follows (see Fig. 1). To start the interaction, the user points the camera (and the device) to the augmented object of interest or to an area in the environment according to what the application scenario involves. The device then automatically identifies what is being focused, captures whatever additional context is required by the application, and then sends a request for an augmented reality scenario to a service in our platform to be shown on the device. The augmented reality scenario could include some sort of basic interaction such as touching one of the objects on the screen. The device then sends as many additional requests to the data providers as the application flow needs. The final scenario is that the user sees an augmented version of the physical reality and in this way, he is able to interact with the objects he uses in his everyday life just by pointing the sentient device to it. We use this tool on the taking medications scenario (see subsection 5.1) Other Development Tools We have developed other tools aimed to better assisting the developers of ambient intelligence systems by providing higher abstraction layers on top of our platform. For instance, while the services are already designed to facilitate the development, the Mashup Editor (see [4] for more details) allows the development of applications just by dragging graphical representations of the services to form compositions to be run on the execution engines, which is also handled by the editor. Other tools provide Web widgets to present and manage information, they are also ready to be updated as new notifications arrive, automatically handling the low level communication. 5. APPLICATION SCENARIOS We now present some scenarios that we came across during our work with ambient-assisted living technologies to

5 Figure 2: The taking medications application showing the two possible results. promote safer and healthier lifestyles for elders. These scenarios have also been very useful for highlighting the benefits of our proposed platform for developing AmI applications. 5.1 Taking Medications Mr. Smith is a senior of advanced age who needs to take many different medications on a daily basis. Sometimes he forgets to take the medications, and maybe worse, he takes the same dosis of pills twice or thrice because he just wants to be sure he took it. This situation can lead to adverse, sometimes very serious consequences and it is known to cause many problems worldwide [18]. Mr. Smith is physically impaired, so it is impossible for him to visit his physician except on certain special occasions. Without frequent visits, the medical examinations are conducted via phone calls and sometimes his physician changes the doses by altering the number of pills to be taken or by setting a different intaking schedule, which makes the problem even worse because Mr. Smith must remember the proper doses of each of the many bottles of pills he takes during the day. To support this scenario, we first identified which objects in Mr. Smith s daily life we could augment to allow him to use the system the way he is used to. We decided to use the bottles of pills. We attached an RFID tag to each of the bottles to be able to individually identify them. Later, we analyzed which services were already available in our platform so we could use them. They were the RFID reader (for bottle identification) and the speech synthesis services (to alert the user). Then, we identified what custom services were needed to complete the functionality for this scenario. Two services were specially implemented: a service that provides a Web page to input the doses specifications to be used by the physician, and a service that keeps record of the doses and that sends the alerts to the user when the schedule of a doses is met. Finally, to wrap all the services and implement the final application, we used the sentient visor tool to create an augmented reality scenario that shows if the doses from a bottle should be taken or if the user should wait until the next doses. The new scenario with the support of our contributions is as follows: Mr. Smith takes many different medications Figure 3: Desktop version of the intelligent video monitoring application. during the day. When he wants to be sure he is on schedule with the doses, he takes his mobile device (e.g., smartphone) and points it to each of the bottles of pills. In the screen, a green or red glow appears around the bottle indicating whether he needs to take or to wait for a doses; if he needs to take it, the number of pills also appears on the screen, if he must wait, an animated countdown appears telling him how many minutes he should wait until the next doses (see Fig. 2). When he must take the doses, a button appears, to be pushed after he takes it. When Mr. Smith hasn t used the smartphone and the schedule is not met, the alert service notifies the voice synthesis service to send an user notification telling him the number of pills he must immediately take. Sometimes, Mr. Smith s physician logs in into the doses specification Web page to change the schedule or to check the progress of his patient, but this is all transparent to Mr. Smith, as the system takes care of updates and other details in the background. 5.2 Intelligent Care Monitoring Mrs. Jones is a caregiver at a nursing facility. As part of her activities, she must regularly check the residents to look if they require assistance. To avoid her to walk around the many different rooms, they installed a closed circuit camera system for her. Now, when she is in the office she can keep an eye on the residents by watching a monitor that shows all the camera feeds in the building. Sometimes, one of the residents falls, if she is not careful with the inspection, the elder could spent a long time until she realized of the accident. Given the fact that during the aging process there is a considerable decline in motor capabilities, older adults become more prone to falls. While Mrs. Jones is not the only caregiver, they have many other activities, and after some time, the camera feeds are no longer being used for monitoring, but for having a record of what happens inside the building. To implement this scenario, we provided each of the residents with wearable sensor nodes, in this way, we are aware of their location by using the perceived Wi-Fi signal strengths and infer their behaviour by analyzing the readings of an embedded accelerometer. We get the locations of the users thanks to the indoor localization service which we had to

6 Wi-Fi Access Points Wireless Sensor Network Door Controller User Controller and Localization Badge Figure 4: Infrastructure implemented for the voiceenabled assistance scenario. train before using it. We took readings in 2,500 positions, in each location we took 10 signal strength readings. We equipped the nursing home with 5 Wi-Fi extra access points to enhance the location estimation. Each of the nodes interacts directly with the indoor localization service to estimate their individual position and then reports it to a centralized service. The behaviour analysis is provided by accelerometer readings, each sensor reports segments of data each 10 seconds to a centralized service, data is analyzed there to conclude if the user is walking, seated, or if he has fallen. The implementation of the centralized service in both cases is a specialization of the context-processor service provided by our platform. We use the video feeds of each camera to provide a way for the caregivers to confirm that the alerts are real events and avoid false positives. Finally we implemented an application, with desktop and mobile versions, that uses the functionality provided by the centralized location and behavior analysis services to support this scenario. The new scenario is as follows: Mrs. Jones must check the residents regularly. When she is in the office, in her desktop computer she can see a map of the building showing the activity and location of each resident. She can click on one of the resident icons and then the system shows the video feed of the nearest camera that has that location on sight. When one of the residents suffers a fall, the desktop system shows her a visual and audible alert highlighting the location and the video feed so she can be sure the alert is not a false positive and then go directly to attend the resident (see Fig. 3). When she and other caregivers are not in the office, they receive a fall alert containing the location and an image captured from the nearest camera. Residents can also use a button in the sensor node to trigger an alert. 5.3 Voice-Enabled Assistance Mr. Brown is a patient who uses an electric-powered wheelchair to move himself around the building. Very often, he requires assistance to open doors or when he needs to go to the bathroom. When nobody is around he usually finds himself waiting until a caregiver or another patient assists him. To support this scenario, we are using the indoor localization, voice commands, input device, and actuators services. We designed a custom input device (and service) that presents two buttons for the use of the elder. The applica- tion (a service composition) is running in the environment, when the user pushes the command button, the application identifies him with its location and waits for the voice command service to detect a command, when it receives the request for an action, it acts accordingly. When the user presses the help button, the system sends a notification to a caregiver in the form of a message containing the location of the patient (see Fig. 4). The voice-powered scenario is as follows: Mr. Brown is an elder who presents physical disadvantages that makes him use a wheelchair. When he needs to open a door, he presses the command button and says open, then the door in front of him opens to let him enter. Once inside, he presses the button again and says close, then the door closes behind him. When Mr. Brown requires assistance from a caregiver, he presses the help button, then a caregiver receives his request containing his location so he can be found rapidly. 6. LESSONS LEARNED Working with assisted living systems for supporting the elderly is a very interesting and challenging task; while the research offers a good degree of complexity, the results have an important and quick social impact. When designing the application scenarios, we found many issues that required very well planed privacy management, for instance, the intelligent care monitoring scenario, where the activities of the residents of a nursing house are always being tracked. We think that, as long as the application is managed locally, privacy of users in such cases is not so crucial. On the other hand, there are scenarios which are more oriented towards healthcare, where the processing and transmission of confidential patient data requires important security and privacy considerations [19]. We faced another problem when dealing with the precision of the indoor localization service. We needed a mechanism to get localization at the lowest cost possible (in terms of computation, infrastructure, and price) which led us to base it on Wi-Fi signal strength readings. Wi-Fi based techniques manage to get estimations within an approximate error of 20 meters, we needed a better one and considered a 5 meters error window. The precision we finally got was satisfactorily enough but this resulted particularly difficult on the voice-enabled assistance scenario, where the user activates the doors in front of him. Luckily, doors in the nursing room in which we conducted the experimentation were spread in far longer distances than our error window. 7. CONCLUSIONS AND FUTURE WORK In this article, we approached the use of ambient intelligence systems in the context of ambient assisted living for supporting the elder. This is a topic that has been pursued recently and it has gained greater importance because of the worldwide increase in average life expectancy [20]. We also presented our hardware and software infrastructure to support this kind of applications and discussed the implementation of a number of scenarios conducted in our research group. We believe our proposals will contribute in improving the lifestyle of the elderly by allowing the rapid construction of prototypes for usability, and application-driven research. As stated before, the elder users have quite specific requirements, and their relationship with augmented objects

7 and modern interface technologies have yet to be carefully analyzed. We plan to conduct an extensive evaluation of our contributions from two approaches. First, to evaluate the construction of ambient assisted living applications for the elderly with the use of our platform from the perspective of the developers of such applications. Second, to evaluate the usability and acceptance of technology of the applications from the perspective of the elderly user. We have successfully tested the implemented applications in our laboratory, the next step is to conduct the usability studies by using our prototypes in the nursing home in which we conducted our analysis. 8. ACKNOWLEDGMENTS The work presented in this paper was funded with grants from CONACyT, the Mexican Council for Science and Technology. 9. REFERENCES [1] Phidgets, Inc. [2] E. Aarts, H. Harwig, and M. Schuurmans. The invisible future: the seamless integration of technology into everyday life. McGraw-Hill, Inc., New York, NY, USA, [3] E. Avilés-López and J. A. García-Macías. TinySOA: a service-oriented architecture for wireless sensor networks. Service Oriented Computing and Applications, 3(2):99 108, [4] E. Avilés-López and J. A. García-Macías. UbiSOA Dashboard: Integrating the physical and digital domains through mashups. In Human Interface and the Management of Information. Designing Information Environments, pages Springer-Verlag, Berlin, Heidelberg, [5] E. Avilés-López, I. Villanueva-Miranda, J. A. García-Macías, and L. E. Palafox-Maestre. Taking care of our elders through augmented spaces. In Proceedings of the Latin-American Conference on Human-Computer Interaction (CLIHC 09), Nov [6] R. Bellazzi, S. Montani, A. Riva, and M. Stefanelli. Web-based telemedicine systems for home-care: technical issues and experiences. Computer Methods and Programs in Biomedicine, 64(3): , [7] A. T. Campbell, S. B. Eisenman, K. Fodor, N. D. Lane, H. Lu, E. Miluzzo, M. Musolesi, R. A. Peterson, and X. Zheng. CenceMe: Injecting sensing presence into social network applications using mobile phones. In Proc. of ACM 9th International Symposium on Mobile Ad Hoc Networking and Computing (MobiHoc 08), Hong Kong, May [8] D. L. de Ipiña, J. Vázquez, D. García, J. Fernández, I. García, D. Sainz, and A. Almeida. Emi 2 lets: A reflective framework for enabling AmI. Journal of Universal Computer Science, 12(3): , [9] R. T. Fielding. Architectural styles and the design of network-based software architectures. PhD thesis, University of California, Irvine, [10] L. Fuentes, D. Jiménez, and M. Pinto. Development of ambient intelligence applications using components and aspects. Journal of Universal Computer Science, 12(3): , [11] B. Gonçalves, J. G. P. Filho, R. V. Andreão, and G. Guizzardi. ECG data provisioning for telehomecare monitoring. In SAC 08: Proceedings of the 2008 ACM symposium on Applied computing, pages , New York, NY, USA, ACM. [12] T. Kleinberger, M. Becker, E. Ras, A. Holzinger, and P. Müller. Ambient intelligence in assisted living: Enable elderly people to handle future interfaces. In Universal Access in Human-Computer Interaction. Ambient Interaction, pages [13] I. Korhonen. Health monitoring in the home of the future. IEEE Eng. Med. Biol. Mag., 22(3):66 73, [14] J. Krumm and E. Horvitz. LOCADIO: Inferring motion and location from Wi-Fi signal strengths. Mobile and Ubiquitous Systems, Annual International Conference on, 0:4 13, [15] D. Malan, T. Fulford-Jones, M. Welsh, and S. Moulton. CodeBlue: An ad hoc sensor network infrastructure for emergency medical care. In In International Workshop on Wearable and Implantable Body Sensor Networks, [16] R. Oppermann, R. Rashev, and K. Kinshuk. Adaptability and adaptivity in learning systems. Knowledge Transfer, 2: , [17] L. E. Palafox and J. A. García-Macias. Wireless sensor networks for voice capture in ubiquitous home environments. In ISWPC 09: Proceedings of the 4th international conference on Wireless pervasive computing, pages , Piscataway, NJ, USA, IEEE Press. [18] P. A. Routledge, M. S. O Mahony, and K. W. Woodhouse. Adverse drug reactions in elderly patients. British journal of clinical pharmacology, 57(2): , [19] C. Ruan and S.-S. Yeo. Modeling of an intelligent e-consent system in a healthcare domain. Journal of Universal Computer Science, 15(12): , [20] United Nations. World population prospects the 2008 revisions. publications/wpp2008/wpp2008 highlights.pdf. [21] G. Virone, A. Wood, L. Selavo, Q. Cao, L. Fang, T. Doan, Z. He, R. Stoleru, S. Lin, and J. A. Stankovic. An assisted living oriented information system based on a residential wireless sensor network. In Proc. 1st Transdisciplinary Conference on Distributed Diagnosis and Home Healthcare (D2H2 2006), pages , Arlington, VA, USA, [22] M. Weiser and J. S. Brown. The coming age of calm technology. Beyond Calculation: The Next Fifty Years of Computing, pages 75 85, [23] C. Wisneski, H. Ishii, A. Dahley, M. G. Gorbet, S. Brave, B. Ullmer, and P. Yarin. Ambient displays: Turning architectural space into an interface between people and digital information. In CoBuild 98: Proceedings of the First International Workshop on Cooperative Buildings, Integrating Information, Organization, and Architecture, pages 22 32, London, UK, Springer-Verlag. [24] A. Wood, G. Virone, T. Doan, Q. Cao, L. Selavo, Y. Wu, L. Fang, Z. He, S. Lin, and J. Stankovic. ALARM-NET: Wireless sensor networks for assisted-living and residential monitoring. Technical

8 Report CS , Department of Computer Science, University of Virginia, [25] A. Wright. Get smart. Communications of the ACM, 52(1):15 16, 2009.