Ambient Intelligence Systems Research Articles

Configuring a Context-Aware Middleware for Wireless Sensor Networks

In the Future Internet, applications based on Wireless Sensor Networks will have to support reconfiguration with minimum human intervention, depending on dynamic context changes in their environment. These situations create a need for building these applications as adaptive software and including techniques that allow the context acquisition and decisions about adaptation. However, contexts use to be made up of complex information acquired from heterogeneous devices and user characteristics, making them difficult to manage. So, instead of building context-aware applications from scratch, we propose to use FamiWare, a family of middleware for Ambient Intelligence specifically designed to be aware of contexts in sensor and smartphone devices. It provides both, several monitoring services to acquire contexts from devices and users, and a context-awareness service to analyze and detect context changes. However, the current version of FamiWare does not allow the automatic incorporation related to the management of new contexts into the FamiWare family. To overcome this shortcoming, in this work, we first present how to model the context using a metamodel to define the contexts that must to be taken into account in an instantiation of FamiWare for a certain Ambient Intelligence system. Then, to configure a new context-aware version of FamiWare and to generate code ready-to-install within heterogeneous devices, we define a mapping that automatically transforms metamodel elements defining contexts into elements of the FamiWare family, and we also use the FamiWare configuration process to customize the new context-aware variant. Finally, we evaluate the benefits of our process, and we analyze both that the new version of the middleware works as expected and that it manages the contexts in an efficient way.

Wireless sensor networks and human comfort index

Conventional wireless home automation networks (WHANs) incorporate embedded wireless sensors and actuators that monitors and control home living environment. WHAN's primary goal is to maintain user comfort and efficient home management. Conventional WHAN lacks "intelligence" in terms of managing compound human comfort, and it deals with multitude of human comfort factors individually instead of collectively. This paper presents wireless sensor networks-based Human Comfort Ambient Intelligence system. A fuzzy-rule-based system for the measurement of human comfort index in a living space is presented. The system is evaluated and tested with simulated and empirical data. It explores the complex relationship between multiple comfort factors. The comfort factors considered here include thermal comfort, visual comfort, indoor air comfort and acoustical comfort.

Combining the real world with simulations for a robust testing of Ambient Intelligence services

This paper proposes a general architecture for testing, validating and verifying Ambient Intelligence (AmI) environments: AmISim. The development of AmI is a very complex task because this technology must often adapt to contextual information as well as unpredictable behaviours and environmental features. The architecture presented deals with AmI applications in order to cover the different components of these kinds of systems: environment, users, context and adaptation. This architecture is the first one that is able to cover all these features, which are needed in a full AmI system. The paper shows that AmISim is able to cover a complete AmI system and to provide a framework which can test scenarios that would be impossible to test in real environments or even with previous simulation approaches. Simulated and real elements coexist in AmISim for a robust testing, validation and verification of the AmI systems, which provide an easier and less costly deployment.

New developments in pervasive and ambient information systems

This special issue contains selected papers from the 2nd International Conference on Ambient Systems, Networks and Technologies (ANT 2011), which was held at Niagara Falls, Ontario, Canada, September 19–21, 2011. The conference attracted a large number of scientific papers that contributed to the state-of-the-art in the areas to the theme of the conference. All the papers selected for this special issue were subjected to a two rounds of rigorous review process. Based on the reviewers’ feedback, a total of seven papers were selected for publication from ten invited papers. The accepted papers cover interesting works on new developments in pervasive and ambient systems such as smart environments, environmental monitoring, information search and processing, and the practical use of smart devices in industrial applications. A brief summary is as follows. Identifying and recognizing objects in (indoor) smart environment is one of the challenging research areas in pervasive and ambient systems. The paper by Menon et al. proposes a novel model for identifying and tracking objects in smart environments. This work integrates recognition and spatio-temporal reasoning in order to achieve improved precision in smart environments. The proposed approach is evaluated through experimentation in terms of face recognition, which shows improved performance, precision, and recall. Wireless sensor network (WSN) augmented with ambient intelligence has interesting applications in home living. Rawi et al. in their paper develop WSN-based Human Comfort Ambient Intelligence system, which exploits fuzzy rules in order to measure human comfort index in a living space. It explores complex relationship among multiple comfort factors such as thermal, visual, and indoor air comfort factors. Further, the system is developed in a way such that it provides flexibility in terms of adding or removing comfort factors as well as sensor nodes. Trust is another important issue in providing truly smart environments in living spaces. El Husseini et al. propose a trust model that takes into account user’s past and present behavior. The proposed model utilizes a lightweight authentication key agreement protocol in order to ensure trust and to provide mutual authentication between communicating entities. The model is developed such that it optimizes the communication and processing of resource scare devices in smart environments. Al-Turjman et al. explore the utilization of WSN in environmental monitoring applications such as forestry. The large number of failures complicates the process of environmental monitoring as WSNs often suffer from physical damages and network partition. This paper proposes 3D grid-based deployment for relay nodes and is based on a minimum spanning tree construction. It is used in re-connecting the disjointed WSN sectors and has the potential to optimize various factors including: average relay node count and distribution, the scalability of the federated WSNs in large-scale applications, and the robustness of the topologies. Effective processing of queries in mobile ad hoc network is crucial in order to optimize performance, reduce energy consumption, and avoid failures. Nghiem et al. E. Shakshuki (&) Jodrey School of Computer Science, Acadia University, Wolfville, NS, Canada e-mail: elhadi.shakshuki@acadiau.ca

Activity Inference for Ambient Intelligence Through Handling Artifacts in a Healthcare Environment

Human activity inference is not a simple process due to distinct ways of performing it. Our proposal presents the SCAN framework for activity inference. SCAN is divided into three modules: (1) artifact recognition, (2) activity inference, and (3) activity representation, integrating three important elements of Ambient Intelligence (AmI) (artifact-behavior modeling, event interpretation and context extraction). The framework extends the roaming beat (RB) concept by obtaining the representation using three kinds of technologies for activity inference. The RB is based on both analysis and recognition from artifact behavior for activity inference. A practical case is shown in a nursing home where a system affording 91.35% effectiveness was implemented in situ. Three examples are shown using RB representation for activity representation. Framework description, RB description and CALog system overcome distinct problems such as the feasibility to implement AmI systems, and to show the feasibility for accomplishing the challenges related to activity recognition based on artifact recognition. We discuss how the use of RBs might positively impact the problems faced by designers and developers for recovering information in an easier manner and thus they can develop tools focused on the user.

An ecosystem of products and systems for ambient intelligence - the AAL4ALL users perspective.

Developed societies are currently facing severe demographic changes: the world is getting older at an unprecedented rate. In 2000, about 420 million people, or approximately 7 percent of the world population, were aged 65 or older. By 2050, that number will be nearly 1.5 billion people, about 16 percent of the world population. This demographic trend will be also followed by an increase of people with physical limitations. The traditional health care systems, not only in Portugal, but also in all other European states, will be faced with new challenges. There is an urgent need to find solutions that allow extending the time people can live in their preferred environment by increasing their autonomy, self-confidence and mobility. AAL4ALL presents an idea for an answer through the development of an ecosystem of products and services for Ambient Assisted Living (AAL) associated to a business model and validated through large scale trial. This paper presents the results of the first survey developed within the AAL4ALL project: the users' survey targeted at the Portuguese seniors and pre-seniors. In this way, this paper addresses the lives of the Portuguese population aged 50 and over.

A Rule-Based Approach to Automatic Service Composition

The incapability to foresee or react to all the events that take place in a specific environment supposes an important handicap for Ambient Intelligence systems, expected to be self-managed, proactive, and goal-driven. Endowing such systems with capabilities to understand and reason about context seems like a promising solution to overcome this hitch. Supported on the service-oriented paradigm, composing rather than combining services provides a reasonable mean to implement versatile systems. This paper describes how systems for Ambient Intelligence can be improved by combining automatic service composition and reasoning capabilities upon a distributed middleware framework.

Simulation of human behaviours for the validation of Ambient Intelligence services: A methodological approach

An Ambient Intelligence (AmI) system is a pervasive system in which services have some intelligence in order to smoothly interact with users immersed in the environment. Users are the main entity in AmI systems. Thus, the services are user-centred with an adaptive interaction that provides users with more personalized facilities in a non-intrusive way. The deployment of AmI services is a hard task, especially when the system includes complex users' behaviours or complex deployments in terms of the devices and software participating at the system. Since one of the intrinsic requirements in these services is smooth interaction with users, the user, or at least a model of the user, should be incorporated in the development process. This makes the process of verification and validation of such services quite difficult. This paper proposes the use of Agent Based Social Simulation for a quick and feasible validation of AmI systems. Simulation in the first stages enables easy validation of the services before real environment deployment. The main challenge in this approach is how to simulate humans with realistic behaviours. In this paper, Social Simulation (SS) is used to tackle this problem. Specifically, this paper presents a methodology for the validation of AmI systems by SS. The realistic modelling of users and its validation are key elements of this process and involve challenges that the techniques proposed here are able to deal with. A real application example which shows the level of reality reached in the users' models and the benefits of the methodology is presented in this paper.

Analysis of daily-living dynamics

Analysis of daily-living behavior is an important approach to assess the wellbeing of an elderly person that lives at home alone. This paper presents an approach to monitoring an individual in the home environment by an ambient-intelligence system in order to detect anomalies in daily-living patterns. The proposed method is based on transforming the sequence of posture and spatial information using a novel matrix presentation to extract spatial-activity features. Then, an outlier-detection method is used for a classification of the individual's usual and unusual daily patterns regardless, of the cause of the problem, be it physical or mental. Experiments indicate that the proposed algorithm successfully discriminates between the daily behavior patterns of a healthy person and those with health problems.

Robotic Ecologies for Deep Space Outposts

Abstract Robotics systems are a recognised part of the human exploration and colonisation of space. Advances in sensor and robotic networks, ambient intelligence and multi-agent systems offer approaches to modelling, implementing and operating robotic ecologies, comprising heterogeneous sets of mobile and embedded robotic devices and sensors, to support space applications, particularly in constructing and maintaining human habitats prior and subsequent to human arrival. This paper proposes a framework for integrating these technologies and techniques. The framework comprises application-level and infrastructure-level components, the former emphasising a model-driven approach supporting cognitive awareness and the latter an autonomic computing approach to self management. The paper provides a first draft of the framework, motivated by a deep space human outpost mission scenario.

Bringing together commercial and academic perspectives for the development of intelligent AmI interfaces

The users of Ambient Intelligence systems expect an intelligent behavior from their environment, receiving adapted and easily accessible services and functionality. This can only be possible if the communication between the user and the system is carried out through an interface that is simple (i.e. which does not have a steep learning curve), fluid (i.e. the communication takes place rapidly and effectively), and robust (i.e. the system understands the user correctly). Natural language interfaces such as dialog systems combine the previous three requisites, as they are based on a spoken conversation between the user and the system that resembles human communication. The current industrial development of commercial dialog systems deploys robust interfaces in strictly defined application domains. However, commercial systems have not yet adopted the new perspective proposed in the academic settings, which would allow straightforward adaptation of these interfaces to various application domains. This would be highly beneficial for their use in AmI settings as the same interface could be used in varying environments. In this paper, we propose a new approach to bridge the gap between the academic and industrial perspectives in order to develop dialog systems using an academic paradigm while employing the industrial standards, which makes it possible to obtain new generation interfaces without the need for changing the already existing commercial infrastructures. Our proposal has been evaluated with the successful development of a real dialog system that follows our proposed approach to manage dialog and generates code compliant with the industry-wide standard VoiceXML.

The ambient intelligence for the sake of accessibility in residential projects: a proper study to the Brazilian scene

The concept of Ambient Intelligence consists of intuitive interfaces embedded in everyday objects that interact with the user and function in an integrated and discrete generating and transmitting information. This article has as objective to present applications that when focused on accessibility criteria, can contribute to the work of architects during the design of residential projects. In Brazil, pioneering projects are already being developed and the use of Ambient Intelligence systems are already widespread, both by private and public, however much care technologies developed in other countries.

An ambient agent model for monitoring and analysing dynamics of complex human behaviour

In ambient intelligent systems, monitoring of a human could consist of more complex tasks than merely identifying whether a certain value of a sensor is above a certain threshold. Instead, such tas...

DoMAIns: Domain-based modeling for Ambient Intelligence

Ambient Intelligence and Smart Home Automation systems are currently emerging as feasible and ready to exploit solutions to support more intelligent features inside future and current homes. Thanks to increased availability of off-the-shelf components and to relatively easy to implement solutions we are experiencing a steady evolution of households, causing an ever-increasing users’ awareness of the capabilities of such innovative environments. To foster effective adoption of Smart Home Automation technologies in our home environments, traditional architectural and plant design must be complemented by sound design methodologies and tools, supporting the whole environment design cycle, including for example modeling, simulation and emulation, as well as, when feasible, formal model-checking and verification. Several research efforts have already addressed the design of expressive modeling tools, mostly based on Semantic Web technologies, as well as of suitable platforms for adding interoperation and rule-based intelligence to home environments. This paper proposes a new modeling methodology designed to fit the different phases of Intelligent Environments design, with a particular focus on validation and verification of the whole system. Carefully designed separation of modeled entities permits to exploit the DoMAIns framework during all phases of the environment design, from early abstract conception to the final in-field deployment. The DoMAIns design methodology is applied to a sample use case that involves comprehensive modeling and simulation of a Bank Security Booth, including the environment, the control algorithms, the automation devices and the user. Results show that the approach is feasible and that can easily handle different types of environment modeling, required in the different design phases, and for each of them it may support simulation, emulation, or other verification techniques.

DEAL

Authorization is an open problem in Ambient Intelligence environments. The difficulty of implementing authorization policies lies in the open and dynamic nature of such environments. The information is distributed among various heterogeneous devices that collect, process, change, and share it. Previous work presented a fully distributed approach for reasoning with conflicts in ambient intelligence systems. This paper extends previous results to address authorization issues in distributed environments. First, the authors present the formal high-level authorization language DEAL to specify access control policies in open and dynamic distributed systems. DEAL has rich expressive power by supporting negative authorization, rule priorities, hierarchical category authorization, and nonmonotonic reasoning. The authors then define the language semantics through Defeasible Logic. Finally, they demonstrate the capabilities of DEAL in a use case Ambient Intelligence scenario regarding a hospital facility.

A new spatial IP assignment method for IP-based wireless sensor networks

Wireless sensor networks (WSNs), one of the commercial wireless mesh networks (WMNs), are envisioned to provide an effective solution for sensor-based AmI (Ambient Intelligence) systems and applications. To enable the communications between AmI sensor networks and the most popular TCP/IP networks seamlessly, the best solution model is to run TCP/IP directly on WSNs (Mulligan et al. 2009; Hui and Culler 2008; Han and Mam 2007; Kim et al. 2007; Xiaohua et al. 2004; Dunkels et al. 2004; Dunkels et al. 2004; Dunkels 2001; Dunkels et al. 2004). In this case, an IP assignment method is required to assign each sensor node a unique IP address. SIPA (Dunkels et al. 2004) is the best known IP assignment method that uses spatial relations and locations of sensor nodes to assign their IP addresses. It has been applied in Contiki (Dunkels et al. 2004), a famous WSN operating system, to support the 6LowPAN protocol. In Chang et al. (2009), we proposed the SLIPA (Scan-Line IP Assignment) algorithm to improve the assignment success rate (ASR) obtained by SIPA. SLIPA can achieve a good ASR when sensor nodes are uniformly distributed. However, if sensor nodes are deployed by other distributions, the improvements would be limited. This paper proposes a new spatial IP assignment method, called SLIPA-Q (SLIPA with equal-quantity partition), to improve SLIPA. Experiments show that, by testing the proposed method 1,000 times with 1,000 randomly deployed sensor nodes, the average ASR obtained by SLIPA-Q is over two times of that obtained by SLIPA. Under the same 88% ASR, the average numbers of sensor nodes those can be successfully assigned by SLIPA-Q, SLIPA, and SIPA are 950, 850, and 135, respectively. Comparing to previous spatial IP assignment methods, SLIPA-Q can achieve dramatic improvements in ASR for assigning IP addresses to a large set of sensor nodes.

Entity Notation: enabling knowledge representations for resource-constrained sensors

The forthcoming ambient systems will contain a large amount of sensors. Representing the data produced by these sensors in a format suitable for ambient intelligence applications would enable a large number of useful services. However, such formats tend to require processing power and communication bandwidth not available in many sensors utilizing ultra low-power microcontrollers and radio chip solutions. This paper presents a lightweight data representation, Entity Notation, to tackle this problem. Sensors with limited computation and communication capabilities can use Entity Notation to describe the data they produce. Entity Notation can be transformed into knowledge representations in a straightforward manner, and hence, the data produced by sensor nodes can be utilized with ease by any ambient intelligence system compatible with the common knowledge representations. This paper presents the design of Entity Notation, its implementations on embedded sensors and the evaluation of its performance.

Context provenance to enhance the dependability of ambient intelligence systems

Ambient intelligence systems would benefit from the possibility of assessing quality and reliability of context information based on its derivation history, named provenance. While various provenance frameworks have been proposed in data management, context data have some peculiar features that claim for a specific support. However, no provenance model specifically targeted to context data has been proposed till the time of writing. In this paper, we report an initial investigation of this challenging research issue by proposing a provenance model for data acquired and processed in ambient intelligence systems. Our model supports representation of complex derivation processes, integrity verification, and a shared ontology to facilitate interoperability. The model also deals with uncertainty and takes into account temporal aspects related to the quality of data. We experimentally show the impact of the provenance model in terms of increased dependability of a sensor-based smart-home infrastructure. We also conducted experiments to evaluate the communication and computational overhead introduced to support our provenance model, using sensors and mobile devices currently available on the market.

Bio-inspired enhancement of reputation systems for intelligent environments

Providing security to the emerging field of ambient intelligence will be difficult if we rely only on existing techniques, given their dynamic and heterogeneous nature. Moreover, security demands of these systems are expected to grow, as many applications will require accurate context modeling. In this work we propose an enhancement to the reputation systems traditionally deployed for securing these systems. Different anomaly detectors are combined using the immunological paradigm to optimize reputation system performance in response to evolving security requirements. As an example, the experiments show how a combination of detectors based on unsupervised techniques (self-organizing maps and genetic algorithms) can help to significantly reduce the global response time of the reputation system. The proposed solution offers many benefits: scalability, fast response to adversarial activities, ability to detect unknown attacks, high adaptability, and high ability in detecting and confining attacks. For these reasons, we believe that our solution is capable of coping with the dynamism of ambient intelligence systems and the growing requirements of security demands.

On Dependability Issues in Ambient Intelligence Systems

Ambient Intelligence (AmI) is the emerging computing paradigm used to build next-generation smart environments. It provides services in a flexible, transparent, and anticipative manner, requiring minimal skills for human-computer interaction. Recently, AmI is being adapted to build smart systems to guide human activities in critical domains, such as, healthcare, ambient assisted living, and disaster recovery. However, the practical application to such domains generally calls for stringent dependability requirements, since the failure of even a single component may cause dangerous loss or hazard to people and machineries. Despite these concerns, there is still little understanding on dependability issues in Ambient Intelligent systems and on possible solutions. This paper provides an analysis of the AmI literature dealing with dependability issues and to propose an innovative architectural solution to such issues, based on the use of runtime verification techniques.