Aging Friendly Technology for Health and Independence

This paper describes the development of Automatic Door Device as a part of intelligent environment. This device, Robo-Door, can release home robots from door opening/closing task and serve handicapped humans as well. The characteristics of the device are (a) easy installation via wheel actuation and (b) compatibility of automatic motion and human manual handling by clutch mechanism.

Service-Oriented Architecture is widely used to program pervasive spaces such as Smart Homes because of its capabilities to handle dynamic and heterogeneous environments. It is often the case that the services required are designed and implemented using different SOAs, such as OSGi and Web Services. Most of the current composition frameworks take a two-tier approach: those services following the same SOA can take advantage of service composition and runtime substitutions, while interactions between services of different SOAs require hardcoded service invocations that do not really provide full advantage of SOA. Some SOAs do not support features such as on-the-fly compositions or a searchable service directory. In this paper, we present a framework to compose and orchestrate services from different SOA implementations and provide the missing functionalities to support composition of heterogeneous SOAs. We present a case study and the performance analysis of the study to demonstrate the feasibility of our framework.

Ubiquitous and pervasive technologies contribute significantly to the quality of life of dependent people by providing personalized services in context aware environments. The deployment of these services within indoor and outdoor environments still require security, privacy and trust issues for dependent persons. Considering the strong links between these three issues, our challenging task was to integrate them in a common and flexible framework using contextual information. In this paper, we propose a security framework that integrates context awareness to perform authentication and access control in a very flexible and scalable model while ensuring both privacy and trust. The framework focuses on the authentication of users who request access to the resources of smart environment system through static devices (i.e. smart card, RFID, etc.), or dynamic devices (i.e. PDA, mobile phones, etc.).

Security, privacy and dependability are crucial issues if one wants to build a real smart home. First, in addition to established home security requirements, smart home adoption requires to solve brand-new security vulnerabilities deriving from the automated facets of smart homes. Thereafter, pervasive computing and ambient intelligence allow to collect a lot of information, to analyze it to derive new facts, and make them explicit. Finally, systems that are usually safe and dependable can fail when their behavior is becoming controlled as the result of complex interactions between many intertwined information systems. Unfortunately, application developers in smart home environments are usually neither security experts, nor familiar with ethical and legal requirements related to privacy. Security patterns can help to anticipate, overcome, and document systematically these difficult issues in building pervasive information systems in smart homes for cognitively impaired people. In this paper, we illustrate how security patterns can be extended and applied to Smart Home to foster autonomy of elderly or cognitively impaired people, then, we sketch the structure of the catalog which will be populated with a few patterns.

This paper presents taxonomical classification of pervasive computing system that allows characterizing the system and helps to identify most defining performance parameters for evaluation. Tremendous efforts have been put in the related research, but there is no standard or commonly accepted model to benchmark systems and to identify direction for future research. We survey various systems published in the literature and identify their distinctive features to construct a classification scheme, and the outcome is the taxonomy of pervasive computing systems that allows us to devise strategy on how to evaluate a wide variety of these systems.

Central to smart home security is the need for adequate surrounding awareness. Security systems have been designed for remote exploration and control, however, these still lack the simplicity needed by elderly and disabled. The majority of elderly people find the control of such systems laborious. This highlights the need for usable designs that take into consideration the cognitive limitations of this category of people. This paper contributes towards this problem through the introduction of a novel vehicular Remote Exploration Surveillance Robot (RESBot), capable of monitoring in real time the environment in response to events. The interaction with the system is achieved through natural language commands and hence, provides improved usability over traditional approaches. Results from the experimental usability evaluation of the RESBot system revealed considerable improvement over conventional home security systems.

Although the idea of the smart home has been around for over three decades the smart technology that enables it has yet to reach the mass market. Spending on smart technology is expected to rise, but it is still negligible when compared to overall spending on consumer electronics. This paper examines the benefits of the smart home, peoples attitude towards them and smart technologies and the possible reasons for lack of interest and adoption of such technologies.

Existing “photoframes” are single application closed proprietary systems. In this paper, we will outline the possibilities that emerge when we expose the control API of the digital “photoframe” to the local network. The “photoframe” is connected to an execution environment that aggregates intelligence in the smart space. We will describe briefly the Execution environment functionalities and then focus on the new interaction with the “photoframe” this enables. We will report our experience to proof that usage of a “photoframe” in this fashion creates real added value for elderly users in an assisted living environment.

Quality of sleep is an important attribute of an elder’s health state and its assessment is still a huge issue. The sleep posture is a significant feature to evaluate the quality of sleep, and how to detect elder’s sleep posture is a key challenge in elder-care community. This paper proposes an unobtrusive sleep postures detection solution and introduces pressure sensor matrix to monitor the elder’s sleep posture in bed. Based on the proposed sleep detection system, the processing methods of experimental data and the classification approaches for sleep posture detection are also discussed.

Keeping a healthy and balanced diet has long been a critical issue for a person wanting to stay fit and energetic in her/his daily life. We can always turn to a dietitian (or a nutritionist) for professional diet suggestions if necessary. However, we cannot have a dietitian staying with us all the time, which renders daily nutrition control very challenging. Therefore, it is desirable for each individual to receive handy and informative diet suggestions whenever necessary. In this work, we propose a Context-aware Personal Diet Suggestion System (CPDSS) which tries to maximize an aggregated health utility function and provides useful diet suggestions according to some contextual information. In order to increase the practicality of the pro- posed system, we have integrated the CPDSS with an everyday appliance–a smart refrigerator–so that we can readily access the suggestions about one’s diet, receive instant context-aware reminders while preparing foods, and keep long-term diet history to extract more useful pat- terns to caregivers to provide suggestions for health improvement.

Long term eldercare is often labor intensive. This paper addresses a multimodal sensing approach to situation awareness for elderly care using video and force sensitive resistor (FSR) sensor map. For elderly people, especially those with limited mobility, it is useful to keep care givers or family members known of their situations that may lead to abnormal patterns such as repeated action (get up and sit down) or hazardous result such as a falling from bed. By using multimodal sensing with video camera and FSR sensor, the situation awareness algorithm is proposed to detect and track human activities. Experiments have shown the effectiveness of the detection of primary situations for elderly care.

In this paper, we propose a personal diabetes monitoring system which integrates wearable sensors, 3G mobile phone, smart home technologies and Google Health to facilitate the management of chronic disease - diabetes. Our system utilizes wearable sensors and 3G cellular phone to automatically collect physical signs, such as blood glucose level and blood pressure. It allows users, especially seniors with diabetes, to conveniently record daily test results and track long term health condition changes regardless of their locations. It does so without having to ask users to manually input them into the system. Our system also utilizes Google Health to manage Personal Health Records (PHRs), which not only bridges the gaps between patients and different health care providers but enabling accesses to patients’ PHRs anywhere and anytime by taking advantage of the universal accessibility of Google Health.

In this manuscript, a case study is conducted on bio-signals of timevarying spectral content with the purpose of developing a quality of life engineering product. The study deals with noise reduction of electrocardiogram (ECG) for detecting abnormality of the heart system during daily life. Instantaneous bandwidth (IB) of ECG is estimated and is used adaptively as IB of variable bandwidth filter (VBF) for suppressing noise whose Fourier spectrum overlaps with that of ECG and estimating more accurately parameters such as onsets, ends, rates, intervals and durations on the six principal waves of ECG measured during daily life. The proposed method based on the VBF improves the SNR on the P, Q and T waves without damaging the QRS complex, different from, the methods based on the Fourier spectral analysis.

Aims: To determine the degree of change in investment in ICT (Information and Communication Technologies) in residential and community aged care services in regional Queensland.

Methodology: a convenience sample using structured telephone interviews of senior executives or managers of service providers

Findings: Aged care providers were found to have made significant recent investment in ICT. A major driver was to improve patient care. There were investments in clinical systems and systems for administration.

Summary: Aged care is not generally seen to be a sector that has taken advantage of ICT; that appears to be changing and there is now significant investment in clinical systems and other systems to assist staff in providing care.

Technological advances in telehealth systems are primarily focused on sensing, monitoring and analysis. Intervention, behavior alternation and in general affecting change could use additional research and technology development. Many people, especially the elderly, are resistant to change. Such resistance diminishes the impact factor of telehealth systems. Persuasion technology and mechanisms are urgently needed to counter this resistance to change and promote healthy lifestyle. In this paper, we propose an action- based behavior model to enable persuasion. We also review existing technologies we believe are most suitable for enabling persuasive telehealth. We present our ongoing work in the domain of behavior alteration for obese and diabetic individuals.

Acupuncture is known to be effective in ischemia treatment, and glutamate excitotoxicity is an important factor in neuronal cell death. We observed the effect of acupuncture on cerebral blood flow and Δglutamate in the ischemic stroke rat model of hyperglycemia. A global ischemia was induced using the eleven vessel occlusion method in ten Sprague-Dawley rats: the control group and the acupuncture-treatment group. Extracellular Δglutamate was assessed using an intra-cerebral biosensor system measuring 256-Hz sampling frequency, simultaneously with cerebral blood flow and electroencephalogram. Acupuncture stimulation was applied to acupuncture points, Yang Tomb Spring (GB34) and Suspended Bell (GB39) during the ischemic period. 23 diagnostic parameters were proposed first for a detailed analysis of changes in cerebral blood flow and glutamate release during ischemia and reperfusion. Acupuncture rats showed a significant decrease in ischemic (

p

< 0.05) and reperfusion cerebral blood flows (

p

< 0.0001) than control rats, and a significantly larger decrease in ischemic Δglutamate (

p

< 0.05) and peak level of reperfusion Δglutamate (

p

< 0.005) than control rats. From these results, we suggest that acupuncture stimulation is responsible for the potential protection of neurons through suppression of %cerebral blood flow response in the increased plasma osmolality and extracellular Δglutamate in diabetic rats under ischemic conditions.

This paper presents and discusses the Teleherence system that uses web and phone technology to optimize care plans. It uses text-to-speech and speech recognition along with landline, cell, smart, SMS (text messaging), and VOIP phone technology. Teleherence delivers surveys that can inform, remind, suggest, persuade, encourage/motivate, teach, reward, query and branches, and query and alert. Specific uses and considerations for use of Teleherence with the elderly will be discussed. Preliminary findings will be discussed at ICOST 2010.

While people have many ideas about how a smart home should react to particular behaviours from their inhabitant, there seems to have been relatively little attempt to organise this systematically. In this paper, we attempt to rectify this in consideration of context awareness and novelty detection for a smart home that monitors its inhabitant for illness and unexpected behaviour. We do this through the concept of the Use Case, which is used in software engineering to specify the behaviour of a system. We describe a set of scenarios and the possible outputs that the smart home could give and introduce the SHMUC Repository of Smart Home Use Cases. Based on this, we can consider how probabilistic and logic-based reasoning systems would produce different capabilities.

During mealtime, a feeding robot allows a person with upper limbs disability to enjoy chosen food with desired time intervals. Although many feeding machines are developed and commercialized over the world, Korean consumers are still hard to find a feeding robot that can handle the Korean food with boiled rice. In order to handle those kinds of food, we design a novel feeding robotic system that consists of two robotic arms: one is a food grasping robotic arm, and the other is a food transferring robotic arm. We expect that the proposed feeding robot could provide easy handling the Korean food with general bowls. In addition, when one caregiver supports the multiple persons, one part of feeding robots, i.e., a transferring robot, could be effectively applied in facilities or hospitals.

We discuss an integrated approach towards building systems for monitoring and assisting people with mild dementia in their homes. Our approach differs from existing approaches in three ways. First we improve context acquisition and understanding with the concept of micro-context that takes us beyond existing notions of location and temporal context; second, we incorporate plasticity concept into the human computer interface, in order to provide a natural interaction way and accommodative interface to the user; third we target robust and reliable systems that are easy to scale and deploy in diverse end-user settings, through the use of formal model building tools to specify and verify systems at key stages from requirements generation all the way to deployment and user statistics gathering. In order to address real-life end user requirements we are working closely with geriatric doctors and their staff, so as to get inputs as to precise challenges in caring for mild dementia patients, and how systems targeted at holistic, personalized assistance and care-giving can be built with a view towards scaled up deployment in diverse settings. The main contribution of this paper is an approach for system building that incorporates activity monitoring, user interface plasticity and scenario verification targeting people with cognitive decline in regards to a Singapore initiative called A-Star Home 2015 Phase II. We expect our work to lead to a methodology for systematic development of monitoring and assistive systems for cognitive interventions for mild dementia patients at home. Although the integrated framework is still not completely realized, the three areas mentioned above have each yielded significant results on their own, and these are mentioned in the paper.

With undergoing a stunning demographic transformation, a growing problem is how to support the elderly population who want to continue living independently as opposed to moving to an institutional care setting. Globally, the increasing number and proportion of frail and elderly adults with limitations in mobility, dexterity and mental capacity who are living in their own homes or desiring to live independently is a well- recognized social fact, which has provided clues to the needs and values for seniors to live in aging-friendly digital homes. The purpose of this study is to ascertain the needs of older adults in terms of the items of digital home applications supporting their daily living activities through a web-based questionnaire survey. It also empowers end users to make informed choices as they see their concerns and suggestions being addressed through the web-based survey.

This article presents a service robotic system for people loosing their autonomy developed at CEA LIST. In the past on SAM robot, we have developed a method for automatic manipulation and object grasping using visual servoing. This method is too stereotyped to correctly grasp objects with complex geometry or to assign particular use to the manipulated object. In this article, we present a new study to adapt the grasping and the usage of an object designed by the user. Our method uses vision object recognition (CBIR) and an ontology for robotic manipulation. This recognition is implemented as a Web Service. It relies on passive vision and does not use a geometric model for grasping. The implementation of this method enables us to automatically search objects in the surrounding areas and to play cognitive and physical stimulation games with the user.

Since the dramatic demographic change makes it inevitable that rapid aging of the population is an unprecedented phenomenon in Taiwan. A growing social problem is supporting older adults who want to live independently in their own homes. It needs a health assistance system to make them independent living up to a higher age. Recently, technological advancements have spurred various ideas and innovations to assist the elders living independently. In this paper, we proposed a homecare sensory system that uses RFID-based sensor networks to collect elder’s daily activities and conducts the data into Hidden Markov model (HMM) and Support Vector Machines (SVMs) to estimate whether the elder’s behavior is abnormal or not. Through detecting and distinguishing the abnormal behaviors of elder’s daily activities, the system provides assistance on elder’s independent living and improvement of aged quality of life.

Population over aging is at present a widely discussed and researched challenge that society will have to face in the future. Research on ambient assisted living (AAL) yields promising solutions to master those challenges and the IT industry meanwhile has identified AAL as an important future market. However, AAL solutions which are adequate for large portions of the population are still missing. When considering that population over aging will be a mass phenomenon, solutions have to be provided which are applicable for a majority of the population living in different environments and having different income levels and, most importantly, consider a broad range of usability and psychological aspects which influence the acceptance and usage of technology. In this paper we identify and discuss shortcomings of existing research activities and technological developments and present approaches overcoming these shortcomings on the basis of the concept of user experience.

This paper presents two algorithms that enables the MemoryLane system to support persons with mild dementia through creation of digital life stories. The MemoryLane system consists of a Logging Kit that captures context and image data, and a Review Client that recognizes activities and enables review of the captured data. The image filtering algorithm is based on image characteristics such as brightness, blurriness and similarity, and is a central component of the Logging Kit. The activity recognition algorithm is based on the captured contextual data together with concepts of persons and places. The initial results indicate that the MemoryLane system is technically feasible and that activity-based creation of digital life stories for persons with mild dementia is possible.

Formants are useful components to be used in order to recognize some meaningful contents from any sound. By using formants, vowel sounds in a speech can be recorded and categorized as a reference in a speech training system for the hearing impaired. The recorded sound then can be analyzed and the sound’s formant values can be obtained. By using PRAAT system, the vowel speech is recorded and up-to three values of formants were gained. These formant values from five vowels (A, E, I, O, U) from three subjects were analyzed and characterized as a reference for a speech training system. The results shows that pronounced vowels’ characteristics can be distinguished but may defer a little from a person to another.

The deployment, replication and adaptation of sensor environments at various scales and for various purposes is one of the challenges academia as well as industry are faced with today. Individual user requirements, the heterogeneity of devices, the often non-standardized communication protocols in addition to proprietary-related aspects are just some of the problems, which must be addressed in order to establish flexible, efficient and maybe most importantly, cost-effective smart environments that are capable to facilitate Ambient Assisted Living (AAL). This paper discusses some of the requirements for the design and deployment of activity recognition systems and also addresses some of the problems that arose during the replication and adaptation of such a system along with a reflection on the lessons learnt.

This paper is proposed by 3D facial avatar modeling using stereo camera. We use the adaboost algorithm for facial detection to get 3D facial data. We make the 3D facial modeling to match extractive 3D data with justified 3D facial avatar. We use ICP algorithm for matching 3D data and control the number of vertex and feature point for efficiency and accuracy. Feature point is selected within outline points using canny edge method. We propose to make personal 3D facial avatar for reducing expense and time.

This paper describes construction of a system for measurement of human position from laser range finders (LRFs) deployed in real home environment. The system gathers and stores scan data from LRF modules equipped with room corners at different hip heights by network. We also develop a tracking method based on a particle filter framework. In the filter, after scan data is subtracted with background data and noise data is eliminated with grid map that represents room layout, the position is estimated based on detected scan points with the filtering framework. This method realizes robust tracking of the occupant in real cluttered environment. We demonstrated the system can measure human position accurately in real home environment.

Health management is fundamental to enabling elderly people to ‘age in place’ in their homes, and health care services can help elderly people to manage their health. The number of elderly people who require such care services is increasing rapidly, causing a parallel rise in the need for expert care providers. One of the solutions to this demand for expert care is an automatic health care system that may be integrated into a residence, but installing and operating such systems can be prohibitively expensive. To solve this issue, a cost-effective activity monitoring based health care system is proposed in this study. The system uses the infrastructure of a smart grid and a home network system in order to reduce the costs of installation and operation.

We present a development of a gesture-based interface for the elderly and people with mobility impairment in a smart house environment. To reduce a burden of memorizing a variety of gesture commands, we introduce baby signs which are natural and easy-to-remember body signs without special education. The baby signs can be applied not only to communicate with others but also to interact with a computer for people with low level of proficiency in conventional peripherals. To achieve this purpose, we have attempted to create a real application working under illumination change and real-time requirement. The system observes the user’s sign by a monitor-mounted camera and color gloves. Introducing a robust hand segmentation method against illumination change and adopting HMMs, our initial result shows 94.33% success rate for 6 sign words.

Assessing the accessibility using 3D Virtual Reality and telecommunication technology has influenced home adaptation to improve accessibility in homes for individuals with disabilities, especially with Spinal Cord Injury. To provide clients with quantitative ideas on home adaptation with levels of accessibility, we propose a tentative method of measuring accessibility in home. There are a number of assessment protocols to assist rehabilitation professionals and architects in gaining wheelchair accessibility. In this paper, we briefly introduce quantitative assessment method of wheelchair accessibility in home. The feasibility of mathematical expressions of the quantitative accessibility was discussed.

Location awareness is one of the key aspects for pervasive computing environments. It enables location data to be accessed and used anywhere by any application. Major challenges to design effective localization solutions are pervasive deployment and support for heterogeneous technologies. In our efforts to design an effective localization solution, we present a dynamic and efficient infrastructure independent layered architecture. The architecture is highly distributed, integrates inference engine to provide best location estimation for multiple technologies. Our architecture is efficient and comes across challenges in localization process such as computational power, reusability and components dependency.

Undernutrition prevention or detection for disabled or elderly people must be performed rapidly to avoid irremediable consequences. In this paper a classification of uncertainties centered on a meal notion is first proposed. Two of these uncertainties are developed in a smart home and homecare context.

Meal preparation

probability is evaluated by a simulation based on Naïve Bayesian Networks. To determine if a person is at risk of malnutrition or undernutrition, and to supervise prepared

meal quality and quantity

in terms of nutrients, the use of RFID tags is discussed, bringing many open issues for which additional sensors are proposed. This research work was initiated in a collaborative project called CaptHom.

This paper describes an AAL-enabling platform which combines OSGi middleware, interactive TV, RFID and NFC in order to ease the day to day of not only dependant or semi-dependant elderly people (its main focus) but also their care takers and relatives. The end result is an affordable, unobtrusive, evolvable, usable and easily deployable ICT infrastructure which aims to approach the vision of “AAL for All”.

This paper presents a guideline-driven healthcare service platform for smart homes. The clinical guidelines are usually established by medical experts according to the symptoms of diseases. Based on the biological and ambient information detected by sensors, the guideline-driven system makes the appropriate care decisions and then takes actions. In case of emergency, the platform uses the short message system to inform the relevant units immediately. The proposed service platform can therefore reduce the burdens of care and unexpected events in an effective way; therefore it enhances the quality of family care.

Remote medical monitoring services for elderly people is necessary, especially for societies where the population of elderly people are rapidly increasing and healthcare costs are increasing due to lack of human resources. Wearable health-monitoring systems (WHMSs) can provide real-time medical condition monitoring using multiple biosensors attached to the human body. In this paper, virtual multiple input multiple output (MIMO) is proposed as a suitable technique for biosensor networks as it enables higher throughput capacity and less energy consumption than conventional schemes. The performance analysis of the proposed system shows that the lifetime of the virtual MIMO-based system outperforms existing systems.

To offset sedentary lifestyles, physical activity is widely promoted in the workplace. In this paper, we present HealthQuest, a mixed reality system to motivate employees’ physical activity. HealthQuest leverages a company facility’s existing physical infrastructure augmented with distributed kiosks. Users engage in wellness learning quests by walking from kiosk to kiosk in the environment. The system assists in achieving company health promotion goals.

Falls are the primary cause of accidents for elderly people and often result in serious injury and health threats. It is also the main obstacle to independent living for frail and elderly people. A reliable fall detector can reduce the fear of falling and provide the user with the reassurance to maintain an independent lifestyle since the reliable and effective fall detection mechanism will provide urgent medical support and dramatically reduce the cost of medical care. In this work, we propose a fall-detecting system based on a wearable sensor and a real-time fall detection algorithm. We use a waist- mounted tri-axial accelerometer to capture movement data of the human body, and propose a fall detection method that uses the area under a signal magnitude curve to distinguish between falls and daily activities. Experimental results demonstrate the effectiveness of proposed scheme with high reliability and sensitivity on fall detection. The system is not only cost effective but also portable that fulfills the requirements of fall detection.