Band 24, Heft 3 - Special Issue: Ambient Assisted Living / Guest editor: Philippe Le Parc

This article describes the UniversAAL platform, an open platform intended to facilitate the development, distribution, and deployment of technological solutions for Ambient assisted living (AAL). The platform is intended to benefit end users (i.e., assisted persons, their families, and caregivers), authorities with responsibility for AAL, and organizations involved in the development and deployment of AAL services. It consists of an extensive set of resources (some are software and some are models/architectures) aimed at these different groups. The resources are classified into three main groups: runtime support, development support, and community support. The article presents the benefits that can be expected from the widespread adoption of the platform. The article also describes progress on prototype implementations of some of the software resources, and the results of initial evaluations of the platform. The work is partially based on results from earlier European Union-funded research projects in the area.

Ambient assisted living systems are based on sensors and actuators, with a diversity of network protocols and vendors. This commonly leads to the introduction of gateways or middlewares into the technical infrastructure in order to address interoperability issues. The xAAL framework presented in this paper aims to provide interoperability and to redesign such “gateways” into well-defined functional entities communicating with each other via a lightweight message bus over IP. Each entity may have multiple instances, may be shared between several boxes, and may be physically located in any box. Thanks to the distributed architecture of the system, each home automation vendor may peacefully provide its own xAAL box without revealing details of its technology. Also, several applications may be plugged together on the xAAL bus without getting bored with underlying heterogeneity. Moreover, the management of the dynamicity allows sensors or applications to enter and leave the system at any time.

The average lifetime of people in advanced countries is significantly increased in the XXI century. The number of old and dependent people is rising due many innovations in health care: new technologies, medicine, and a lot of innovative devices that allow people to monitor their health and consult with a doctor in case of problems. In the last years, a number of information systems have been developed in the health-care area to assist people in living. Modern systems increase their mobility by using personal mobile devices that allows them to interact with the system at any point of time. Smart space is a technology that allows developing such systems. It is an aggregation of devices that can share their resources (information and services) and cooperate with each other. Sharing personal information between different devices requires ensuring privacy support. For these purposes, a dynamic access control support for information that is shared by devices is needed. In particular, a new access control model for accessing resources is needed. The model should describe the current situation via a context. This paper proposes a model of the context-aware access control for smart systems based on smart space technology.

In 2014, the worldwide context is that the population is increasingly both expanding and aging in industrial countries. In contrast, the personal health levels of individuals could decrease. Although retirement homes and health-care centers assume most of the demand, they will most probably overflow in the next few years. One of the current solutions is e-Health, which involves biomedical monitoring but also home automation functions to compensate for disabilities that tend to increase with age. In this context, several domains have to be merged while respecting the entire ecosystem: the users, their needs and environment, but also all the various actors/experts involved in this process. The issue, however, is that enormous effort is required to combine the multiple expert domains because these can be antinomic. Hence, this paper proposes a collaborative workflow that brings together these different actors and generates the control/command application. Applying model-driven engineering, this workflow makes a clear distinction between people’s health requirements, the home automation functions, and the user interface points of view. Thus, it allows experts in each field to adapt their system in terms of the user’s needs, disability, and health state.

The use of sensors has had an enormous increment in the last years, becoming a valuable tool in many different areas. In this kind of scenario, the quality of data becomes an extremely important issue; however, not much attention has been paid to this specific topic, with only a few existing works that focus on it. In this paper, we present a proposal for managing data streams from sensors that are installed in patients’ homes in order to monitor their health. It focuses on processing the sensors’ data streams, taking into account data quality. In order to achieve this, a data quality model for this kind of data streams and an architecture for the monitoring system are proposed. Moreover, our work introduces a mechanism for avoiding false alarms generated by data quality problems.

The supervisor of the activities of a system user should benefit from the knowledge contained in the event logs of the user. They allow the monitoring of the sequential and parallel user activities. To make event logs more accessible to the supervisor, we suggest a process mining approach, including first the design of an understanding model of the activities of a system user. The model design is based on the relationships between the event logs and the activities of a system user. An intervention model completes the understanding model to assist the supervisor. The intervention model enables an action of the supervisor on the critical activities, and the detection of anomalies. The models are automatically designed with a model-driven engineering approach. An experiment on a smart home system illustrates this tooled design, where the supervisor is a medical or paramedical staff member.