Smart Homes and Health Telematics, Designing a Better Future: Urban Assisted Living

Older people with dementia often depend on caregivers to manage their medications. The complexity of medication regimens in this population can impede medication adherence (i.e., taking medications as prescribed), which may compromise the effectiveness of treatment and increase the cost and burden of illness. Different technological devices have been used to improve medication adherence, however, these devices are often not evidence-based or designed with end-user involvement, thereby affecting their acceptability by people living with dementia and their caregivers. This in turn, can influence the effectiveness and uptake of such devices. This study aims to explore the challenges of medication adherence for both older people with dementia and their caregivers to guide the development of future technological solutions that can be effective, practical and sustainable.

Internet Of Things (IoT) is increasingly used throughout the world in different fields. But it does not have a standardized definition [28]. Several definition can be proposed. IoT corresponds to “objects with virtual identity and personality, working in a smart environment and using smart interfaces to connect and communicate in some various context” [3]. IoT is a sum of entities that are used to exchange information in different contexts. This is a network of connected objects communicating between them to extend their functionalities [17]. The IoT is larger than just a system: it is a system of system. Each one can be divided in sub-system and assimilated to a specific technology [5]. The IoT is “a dynamic infrastructure of a global network. This global network has auto-configuration capacities based on standards and communication protocols interoperable. In this network, physical and virtual objects have identities, physical attributes, virtual personalities and smart interfaces and they are integrated to the network in a transparent way” [31].

Helping older people to remain in their homes and to be more autonomous and less isolated, escaping from the potential related depression, is a global challenge. To support people ‘age in place’, the paper proposes a specific data collection to establish the possible requirements of a novel Product Service Platform for wellbeing and health of older people. The study of a community of older people over 75 who live in their homes has allowed acquiring the knowledge of their main needs and characteristics. Two focus groups with experts dealing with the ageing population were then set up to define: (a) how to design an IT artifact that meets end-users needs and (b) the services that a Product Service Platform should provide.

We present three subsequent case studies to design for heart-failure patients at home. The process resulted in the design of Ativo—a tool to help heart-failure patients with their energy management. The research was done using a Jawbone Move activity tracker to obtain data from two heart-failure patients for three weeks each. During the three weeks period, a cultural probe was conducted twice in combination with patient interviews to collect information and data on their daily activities. Another probe was used to test the viability of the concepts. The data obtained captured the critical events that may have gone unnoticed, which helped us to make a design rationale. A conceptual prototype was created and validated with a heart-failure patient using the cognitive walkthrough method. We received positive responses showing that the patient liked to have alternative ways of tracking her energy level throughout the day. After a month, the patient reported continuous benefits from the awareness derived from using the prototype.

Aging process is related to serious decline in physical and cognitive functions. Thus, early detection of these health changes is important to improve classical assessments that are mainly based on interviews, and are insufficient to early diagnose all possible health changes. Therefore, we propose a technological approach that analyzes elderly people behavior on a daily basis, employs unobtrusive monitoring technologies, and applies statistical techniques to identify continuous changes in monitored behavior. We detect significant long-term changes that are highly related to physical and cognitive problems. We also present a real validation through data collected from 3-year deployments in nursing-home rooms.

The growing number of older adults worldwide places high pressure on identifying dementia at its earliest stages so that early management and intervention strategies could be planned. In this study, we proposed a machine learning based method for automatic identification of behavioral patterns of people with mild cognitive impairment (MCI) and Alzheimer’s disease (AD) through the analysis of data related to their activities of daily living (ADL) collected in two smart home environments. Our method employs first a feature selection technique to extract relevant features for classification and reduce the dimensionality of the data. Then, the output of the feature selection is fed into a random forest classifier for classification. We recruited three groups of participants in our study: healthy older adults, older adults with mild cognitive impairment and older adults with Alzheimer’s disease. We conducted extensive experiments to validate our proposed method. We experimentally showed that our method outperforms state-of-the-art machine learning algorithms.

Healthcare has become a major field of scientific research and is beginning to merge with new technologies to become connected. Measurement of motor activity provides physicians with indicators in order to improve patient follow up. One important health parameter is weight variation. Measuring these variations is not obvious when a person is walking. This paper highlights the difficulty of providing reliable weight variation values with good accuracy. To reach this objective, the paper presents ways to classify the activity of walking, in order to propose a method to measure weight variation at the right time and in a good position. Many methods were studied and compared, using Matlab. We propose a classification tree that uses the standard deviation of acceleration magnitude to define normal walking. The algorithm was embedded in an insole equipped with two force-sensing resistors and tested in laboratory.

The context itself has multiple meanings may vary according to the domain of application. This contextual flexibility was behind the emergence of so such huge number of context definitions. Nevertheless, all the proposed definitions do not provide solid ground for systems developers’ expectations, especially in healthcare domain [1]. This issue prompted researchers to divide the context into a set of concepts that would facilitate organizing of contextual knowledge. The conventional taxonomies of context are always too complex, and we need to fight to make them useful in the intended application area. In this paper, we propose a new context classification which covers almost all the context aspects that we may need to develop a tele-monitoring system for chronic disease management.

The quantified self-movement has gained a lot of traction, recently. In this regard, research in personalized wellness support systems has increased. Most of the recommender systems focus on either calorie-burn or calorie-in take objectives. The achievement of calorie-burn objective is through physical activity recommendations while diet recommendations geared towards calorie-in take objectives. A very limited research is performed which track and optimize objectives for both calorie-burn and calorie-in-take, simultaneously based on well-known wellness support guidelines. In this regard, we propose a hybrid recommendation framework, which provides recommendations for physical activity as well as diet recommendation in order to support wellness requirements of a user in a comprehensive manner.

Many e-health services are available to users today, but they often suffer from lack of personalization. In this paper, we present a system to generate personalized health recommendations from various providers, based on classification of health related calendar events on the user’s smartphone. Due to privacy constraints, such personal data often cannot be uploaded to external servers, hence the classification and personalization has to run on the client device. We use a server to train our model to classify calendar events using SVM and fastText, while the prediction is run on the client device using the trained model. The class labels from the classified calendar events, weighted in order of recency, are used to build a vector, which we treat as a representation of user interest while personalizing the recommendations. This vector is used to re-rank health related recommendations obtained from third party providers based on relevance. We describe the implementation details of our system and some tests on its accuracy and relevance to provide relevant health related recommendations. While we used the calendar app to classify events, our system can also be extended for other apps such as messaging.

This study aims to investigate factors influencing adoption and continued use of PCEHR system among consumers (individual users) in Australia. The data collected via online questionnaire survey were analysed via a Structural Equation Modelling (SEM) approach. The results indicate that: (1) “External Factors & Influences” and “Individual Differences” are significant factors that influence “Perceived Benefits” of the PCEHR system, which in turn influence adoption of the PCEHR system; (2) “External Factors & Influences”, “Individual Differences”, and “PCEHR System Characteristics” are significant factors that influence “Perceived User Friendliness” of the PCEHR system, which in turn influence adoption of PCEHR system; (3) “Facilitating Factors” are significant factors that influence both “Realized Benefits” and “Realized User Friendliness”, which in turn influence continued use of PCEHR system; and (4) “Voluntariness of Adoption” and “Voluntariness of Continued Use” are significant factors that influence both adoption and continued use of the PCEHR system respectively.

Technologies necessary for the development of pervasive health apps with intensive and seamless interactions with their environments are now widely available. Research studies and experimentations have demonstrated the real ability for health apps to interact with their environment. However, designing, testing and ensuring the maintenance and evolution of pervasive health apps remains very complex. In particular, there is a lack of tools to enable developers to design apps that can adapt to increasingly complex and changing environments (sensors added or removed, failures, mobility etc.). This paper reflects our vision to reduce this complexity and is based on our current research work on smart environment and personalized health monitoring apps. It uses SAM, a smart asthma monitoring app as an illustration to highlight the need for a comprehensive set of new interactions to help health app developers interact with the users’ environment, and more specifically get a smarter access to the data. Some requirements can be on the minimum quality level of the data and the way to adapt to the diversity of the sources (data fusion/aggregation), on the network mechanisms used to collect the data (network/link level) and on the collection of the raw data (sensors). It discusses possible solutions to address these needs.

Medical and general health-related measurements can increasingly be performed via IoT components and protocols, whilst inexpensive sensors allow the capturing of a wider range of parameters in clinical, care, and general health monitoring domains. Measurements must typically be combined to allow e.g. differential diagnosis, and in many cases it is highly desirable to track progression over time or to detect anomalies in care and general monitoring contexts. However, the sensitive nature of such data requires safeguarding, particularly where data is retained by different third parties such as medical device manufacturers for extended periods. This appears to be very challenging especially when standards-based interoperability (i.e using IoT standards like HyperCAT or Web of Things-WoT) is to be achieved. This is because open meta-data of those standards can facilitate inference and source linkage if compiled or analysed by adversaries. Therefore, we propose an architecture of pseudonimyised distributed storage including a dynamic query analyser to protect the privacy of information being released.

Brazil presents a complex scenario in cancer treatment. The occurrences have been growing around 600.000 new cases every year. The development of telemedicine has been a priority to INCA and its importance to the delivery of healthcare services in Brazil is huge. The PACS’ deployment allied with the creation of a national network of cancer care institutions were the priorities of INCA’s telemedicine project. This environment can remove communication barriers and ensure better collaboration among physicians across the country. The purpose of this article was to study the telemedicine adoption by physicians. The implementation of telemedicine can be considered as a type of disruptive innovation which changes radically the doctor-patient relationship.

The overall objectives of this research were to assess the functionality of iris scanning technology in a community setting and to evaluate the acceptability to shelter clients of using iris scanning as a form of identification. In order to assess the feasibility of implementing iris scanners in a shelter setting, the research team documented the number of people who agreed to be scanned, the number of people who declined, and the number of successful scans completed. The research team collected 200 scans over the course of 3 visits. A second iris scan was requested of 50 individuals to allow the research team to assess whether the technology accurately identifies someone over a period of time. The results indicate that most people found the technology acceptable, and that the number identifier was consistent over repeated scans.

Clinical Decision Support System (CDSS) plays an indispensable role in decision making and solving complex problems in the medical domain. However, CDSS expects complete information to deliver an appropriate recommendation. In real scenarios, the user may not be able to provide complete information while interacting with CDSS. Therefore, the CDSS may fail to deliver accurate recommendations. The system needs to predict and complete missing information for generating appropriate recommendations. In this research, we extended Ripple Down Rules (RDR) methodology that identifies the missing information in terms of key facts by analyzing similar previous patient cases. Based on identified similar cases, the system requests the user about the existence of missing facts. According to the user’s response, the system resumes current case and infers the most appropriate recommendation. Alternatively, the system generates an initial recommendation based on provided partial information.

The efforts to computerize the medical record of a patient began in 1990. In the documents of this record, the healthcare professional practices the annotation activity. Most medical annotation systems are made to perform a specific task. As a result, we have dozens of medical annotation system that we sneak a fragmented image in the absence of generic classification for these. In this article, we try to present a unified image by classifying 30 medical annotation systems based on 5 generic criteria and the features offered by them. From these two classifications, we present our observation and the limits of these systems.

The concept of smart home is a promising and efficient way of maintaining good health, providing comfort and safety thus helps in enhancing the quality of life. Acceptability of smart homes relies on the users’ perceptions towards its benefits and their concerns related to monitoring and data sharing. Within this study, an online survey with 234 participants has been conducted to understand the attitudes and perceptions of future smart home users, followed by detailed analysis of their responses. In general, the users agree that the smart home technology would improve the quality of life to a greater extent and enhance the safety and security of residents. On the contrary, they raise several concerns such as the increased dependence on technology and the monitoring of private activities, which may be seen as perceived drawbacks. The obtained results show that the older adults (ages from 36 to 70 years) are more open to monitoring and sharing data especially if it useful for their doctors and caregivers while the young adults (ages up to 35 years) are somewhat reluctant to share information.

With the increase in presence of smart devices in our daily life, it is an important problem for these devices to be more intelligent. The most sought after problems in this area are activity recommendation and prediction. Researchers have proposed solutions for this problem, however, most of them are based on single-user home space. In this paper, we propose an unsupervised approach to separate the logs of multi-user home space into buckets equal to the number of users. With a minimal set of assumptions, the aim of the method is to transform the multi-user problem to a single-user problem. It is achieved by estimating the layout of the house and then tracking the users at room-level. We achieved empirically-determined high precision in estimating the layout and 74% accuracy in separating the multi-user stream.

Indoor positioning and navigation have recently gained a significant increase in interest in academia due to the proliferation of smart phones, mobile devices and network services in buildings. Various techniques were introduced to achieve high performance of indoor positioning and navigation. In addition, the inventions of creative location-based service applications for mobile and Internet of Things devices for business purpose have helped push the demand for indoor positioning and navigation system to an unprecedented level. However, currently, unlike outdoor positioning system which commonly uses GPS, there is no de facto standard for indoor positioning technique and technology. Furthermore, even though there are already a number of various location-based service applications, a few of them target visually impaired users who would gain significant benefits from this technology. We propose our indoor navigation system based on RSS lateration and RF Fingerprint using Wi-Fi and Bluetooth Low Energy. The user interface is tailor-made to be suitable to the visually impaired.

Ambient Assisted Living (AAL) represents one of the most promising Internet of Things applications due to its influence on the quality of life and health of the elderly people. However, the interoperability is one of the major issues that needs to be addressed to promote the adoption of AAL solutions in real environments, and to find a way of common exchange between the available connected tools to share the data exchanged. This article will present software buses needs and specify an API based on a MQTT software bus treelike architecture. An example is given to illustrate the efficiency of the API developed in a smart home.

Many people who are suffering from a chronic pain face periods of acute pain and resulting problems during their illness and adequate reporting of symptoms is necessary for treatment. Some patients have difficulties in adequately alerting caregivers to their pain or describing the intensity which can impact on effective treatment. Pain and its intensity can be noticeable in ones face. Movements in facial muscles can depict ones current emotional state. Machine learning algorithms can detect pain intensity from facial expressions. The algorithm can extract and classify facial expression of pain among patients. In this paper, we propose a new deep learning model for detection of pain intensity from facial expressions. This automatic pain detection system may help clinicians to detect pain and its intensity in patients and by doing this healthcare organizations may have access to more complete and more regular information of patients regarding their pain.

As the popularity of Deep Learning grows in the Science field, it is hard to avoid experiencing and discovering the scope of this powerful tool and all it has to offer. This work explores the possibility of using Deep Learning methodologies in the Medicine framework, oriented specifically to the study of vital signs from critical patients in the ER. Using a public domain dataset taken from Massachusetts General Hospital as well as the learning modules from Python, the objective is to use Deep Learning to calculate a patient’s chances of survival based on his vital signs.

In this article, the analysis of pure movements of the lower limb of the human being applied to the design of exoskeletons is explained, in order to be able to obtain bases for the selection of which meet the appropriate torque requirements that can move the robot and help perform continuous trajectories. These values are based on the trajectories that are obtained by measuring the orientation of the lower limb while the patient performs pure rehabilitation movements.Having these movements fully developed, a communication can be applied by Bluetooth protocol, in such a way that signals are sent between the two parts of the exoskeleton of the lower limb to generate a successive walk clearly necessary in the rehabilitation.

This paper describes an environment based on rich interactive diagrams, allowing the geriatricians and caregivers to access, analyze and precisely annotate or label specific granular cases of interest in a variety of heterogeneous data collected, to identify “behaviour changes” through Smart City IoT and Open Data infrastructures. The overall goal is to detect and contextualize, as early and precisely as possible, negative changes that may lead to onset of MCI/frailty in the elderly population. The environment is being developed and piloted within the City4Age project, partially funded by the EU.

In this paper, we discuss the Affective Respiration Device, its rationale and elaborate a few lessons learned from our attempt to embed this technology in the flow of everyday life. The device captures the respiratory behaviour of its viewer and provides bio-feedback and feedforward that enables people to come to terms with their breathing and activity in an engaging manner. After briefly discussing the theory, related work, and the system design we provide a use-scenario to highlight the experiential consequences of using the affective device. We further reflect on few learning points derived from a walk-through. This work aims to inspire design-thinking for patient’s home monitoring to shift from the cognitive approach towards an embodied bio-feedback.

This research explores enablers for and obstacles to the acceptance and use of the Australian Government Personally Controlled Electronic Health Record (PCEHR) system and provides recommendations drawn from surveys from existing and potential individual users of the system. The results of the study indicate that the participants’ major concerns are data security and information privacy. Participants value the importance of governance. They expect more benefits from the PCEHR system than traditional health records. They also expect a quality system that operates normally, a simple system that they can register and learn, and a usable system that they can use easily. The system needs efforts from stakeholders including individuals, health care providers, the Australian Government, legal professionals and system developers to satisfy individuals’ expectations, and resolve the issues of the concerns.

This study explores the understanding of and the current status of adoption and use of the personally controlled electronic health record (PCEHR) system among Australian consumers and aims to identify concerns/issues associated with the PCEHR system and factors influencing their decision regarding adoption and use of the PCEHR system. A qualitative field study was undertaken, in which 30 individuals/consumers were interviewed. The outcomes of this study have both theoretical and practical implications to the Australian Government’s ongoing implementation of the PCEHR system.

These days adoption of healthy behavior can be quantified through Ubiquitous computing and smart gadgets. This digital technology has revolutionized the self-quantification to monitor activities for improving lifestyle. Context based lifelog monitoring is among the processes of tracking individual’s lifestyle in an effective manner. We have proposed a methodology for context-based monitoring of an individual’s prolonged sedentary physical activity and unhealthy dietary behavior in the domain of wellness and give just-in-time intervention to adapt healthy behavior. It detects multiple unhealthy activities of its users and verifies the context for intervention generation. The results depict that the average response of the context-based just-in-time interventions is about 75%.

The ageing population is leading to a significant impact on current society and it is introducing new challenges to find innovative solutions to help older adults to improve their quality of life, stay healthier, and live independently. In this context, the present paper provides a usability assessment of a Smart Kitchen developed to support people with the early-stage dementia in cooking activities. The smart system is managed through an adaptable user interface, which provides information on the meal preparation and allows to configure and manage all household appliances in a simple and intuitive way. Although this preliminary evaluation only included a small number of participants, the results showed that the system could be useful to help and guide people to remain independent in their own home environment for daily kitchen activities.

The aim of this work is to discuss abnormality detection and explanation challenges motivated by Medical Internet of Things. First, any feature is a measurement taken by a sensor at a time moment, so abnormality detection also becomes a sequential process. Second, an anomaly detection process could not rely on having a large collection of data records, but instead there is a knowledge provided by the experts.

In order to build a user profile using data from various connected IoT smart sensors and devices, determination of the current context of the user is vital. We assume a hierarchy of contexts (such as party, trip, exercise) based on common daily activities of users. Knowing the context can inform about the actual activity being performed by the user and predict what the user might be interested in at a given moment. This can then be used to suggest appropriate services to the user. In this paper, we propose a system to infer the user context from input data from various devices. Our system includes an app classifier, a Points of Interest (POI) classifier and a motion classifier to make sense of the input sensor data. We describe the implementation details of a system and some results on real world data to measure our model performance.