No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Software Reference Architecture for Smart Environments: Perception
... H1c. Supporting cognitive and organizational tasks Irizzarry et al. [27]; Martin et al. [28]; Sanchez-Pi et al. [29]; Vales-Alonso et al. [30];Pimenta et al. [31]; Bogdan et al. [32] H1d. Enhancing workers' comfort and wellbeing while working Fernández-Montes et al. [33]; Muñoz et al. [34]; Naqi et al. [35]; Baedeker et al. [36]; Sun et al. [37]; Zhao et al. [38] With the sole exception of (H1b), the criteria were consistently distributed (six papers for H1a, H1c, and H1d). Bajo et al. [26] was the only selected paper dedicated to supporting workers affected by a disability in performing their job (H1b); in particular, the article presented a solution to ease interactions between musicians with vision-related impairments and orchestra conductors. ...
... Bajo et al. [26] Coughlin et al. [20] Osunmakinde [21] Fernández-Montes et al. [33] Irizzarry et al. [27] Martin et al. [28] Pancardo et al. [22] Sanchez-Pi et al. [29] Vales-Alonso et al. [30] Pimenta et al. [31] Muñoz et al. [34] Bhatia & Sood [23] Jo et al. [24] Naqi et al. [35] Baedeker et al. [36] Sun et al. [37] Bogdan et al. [32] Zhao et al. [38] Singh et al. [25] The possibility of monitoring environmental metrics in indoor workplaces was investigated in almost all of the papers analysed. Conversely, only 10 papers adopted technologies to monitor workers' physiological parameters as input for the AmI systems described. ...
... Osunmakinde [21] and Fernández-Montes et al.'s [33] focuses were mostly on the environment. In the first case, the aim of the AmI solution proposed was to enhance miners' safety by identifying dangerous gases within the environment, while in the second article, a prototypical smart office aimed at gathering workers' habits regarding indoor comfort metrics for energy-saving purposes was presented. ...
The increase in older workers in industrialized countries has become evident in the past two decades. The need to support the ageing workforce to effectively perform their tasks has resulted in Ambient Assisted Working (AAW), consisting of developing “smart” systems that can adapt themselves to workers’ needs by exploiting ambient intelligence (AmI) solutions. In AAW, AmI provides flexible workplace adaptations for a wide range of older workers (including persons characterized by chronic conditions and disabilities), while ensuring the ageing workforce’s safety and comfort within the workplace. This work proposes a systematic literature review with the aim of identifying trends among existing AAW solutions specifically designed for older workers. The review adopted the PRISMA methodology, focusing on journal articles and surveying more than 1500 works. The review underlined an absence of articles completely devoted to this research question. Nonetheless, by extending the research question to existing AmI solutions for workers that could potentially be able to support older workers in performing their working activities, it was possible to draw some considerations on the adoption of AmI for the ageing workforce. Among them, the review identified the different types of supporting AmI solutions provided to AAW, which technologies were adopted, and which workplaces were investigated the most. Finally, this work leveraged the findings of the review process to sketch some future research directions for AAW as a discipline.
... Various studies on architecture and digital signage [10][11][12] for configuring and managing smart environments have been performed. Additional research on the configuration of smart environments is currently underway, but many of the studies being conducted are dependent on specific domains, such as smart homes and cities [1][2][3][4]13]. ...
... Fernández-Montes et al. [11] presented a reference architecture for coordinating various resources in a smart environment. e first task that is necessary in a smart environment is to recognize environmental conditions (temperature changes, user detection, etc.). ...
Smart environments, such as smart cities and streets, contain various heterogeneous devices and content that provide information to users and interact with each other. In a smart environment, appropriate content should be provided based on the situations of users. Additionally, when a user is in motion, it is necessary to provide content in a seamless manner without interruption. A method for systematically controlling the delivery of such content is required. Therefore, we propose a content service platform to meet the needs discussed above. The content service platform supports the delivery of content and events between different devices, as well as the control of content. Context-aware technology can also be applied to support customized content. In this paper, we present an architectural model, a contextual reasoning process, and case study on applying content service platform to a smart street environment. The proposed content service platform applied as a base model to support the provision of user-specific content in smart environments.
... In fact, in the ROS 2 documentation website, there is only one guide that covers how to migrate to ROS 2 a basic example of a publish-subscribe ROS 1 package. 8 Yet unofficially, there are valuable collections of example code for various ROS 2 applications that help users mastering and transitioning to ROS 2 (e.g., see (Ferguson 2024)). ...
The robot operating system (ROS) is a well-established and popular open-source robotics middleware used for rapid prototyping of robotic applications. However, ROS has several known weaknesses, such as lack of support for real-time systems and limitations in fully distributed deployments with multiple robots. To address these weaknesses, ROS underwent a major update and the first version of ROS 2 was released back in 2015, being lingeringly adopted by the community in recent years. Yet, long-term support for ROS 1 will come to an end on May 2025. As such, it is more important than ever to analyze and explore the features of ROS 2, and understand its technological readiness. This work focuses on the state of adoption of ROS 2. Specifically, the article presents a user experience questionnaire targeting the ROS community to understand the more eminent needs with respect to ROS 2, determine the current levels of adoption, and identify what is holding the community back from migrating their ROS 1 applications to ROS 2. Results with more than 100 participants from around the world show that the community is aware of ROS 2 and the middleware is addressing most user expectations. We unveil the main reasons given for not migrating to ROS 2, further understand the community’s views on ROS 2, and identify what is missing to anticipate ROS 1 users migrating to ROS 2 and make ROS 2 widely adopted. Moreover, we gather important impressions on the appropriateness of ROS 2 for multi-robot system use cases.
... As highlighted in [40], further research in evaluating the economic viability of adopting RAs is strongly needed. Also, we are witnessing a shortage of models to precisely evaluate the benefits of RAs [41]; this is needed in practice to make informed decisions about their adoption. ...
Reference architectures (RAs) are successfully used to represent families of concrete software architectures in several domains such as automotive, banking, and the Internet of Things. RAs inspire architects when designing concrete architectures, and they help to guarantee compliance with architectural decisions, regulatory requirements, as well as architectural qualities. Despite their importance, reference architectures still suffer from a number of open technical issues, including (i) the lack of a common interpretation, a precise notation for their representation and documentation, and (ii) the lack of conformance mechanisms for checking the compliance of concrete architectures to their related reference architecture, architectural decisions, regulatory requirements, etc. This paper addresses these two issues by introducing a model-driven approach that leverages (i) a domain-independent metamodel for the representation of reference architectures and (ii) the combination of model transformation and weaving techniques for the automatic conformance checking of concrete architectures. We evaluate the applicability, effectiveness, and generalizability of our approach using illustrative examples from the web browsers and automotive domains, including an assessment from an independent practitioner.
... In contrast to the existing approaches, provided by Fernandez-Montes et al. in [10] and by Strohbach et al. in [11], which are based on fixed programs and notations, our model is platform-independent and is focused on the components, which are important to define the behavior of the smart space. ...
The heterogeneity of interconnected devices and communication technologies in the Internet of Things (IoT) domain courses the problem of impossibility to synchronize several different objects in one scheme of the smart space effectively and automatically. Such diversity of technologies results in the need to have special skills in order to reach once created behavior for the smart space. In addition, there are many platforms, which allows to interconnect different devices, but only if they fulfill their protocols. All these lead to the idea, that a new, unified approach to the smart devices representation is needed, which allows to represent objects in a compact form by a platform-independent way. In this article we propose an object-oriented model for representation of the smart devices and demonstrate its efficiency by the simple case of smart space scenes adaptation.
... The increasing number of smart objects has highlighted the need of modeling these devices to be able to synergize their behaviors, to control them through a single framework and to define a standard process to design new ones. In 11 , authors propose a model focused on the objects' (sensing) capabilities, using UML class diagrams to describe the sensors. In 12 , the internal components and processes of a smart object are modeled to propose a manner to 'smartify' any device and to provide communication among various objects. ...
Nowadays, the heterogeneity of interconnected things and communication technologies creates several small worlds composed of a single object and a smartphone. For each object, the user needs to download a specific application, search and connect the device. The result is a waste of valuable resources: several objects are able to communicate with the smartphone, but they cannot directly interact among them. In this paper, we propose a model that can be used to define a set of standard interfaces suitable for every smart object. Devices that adhere to the same model can be easily controlled and placed in relation among them, creating multi-object behaviors for a smart space. The smartphone is still a control center, but with a single application it is possible to control and personalize spaces in a holistic way, instead of using the traditional one-to-one approach. Moreover, personalization should be portable: it is desirable that a behavior works in as many smart spaces as possible, at least in a similar way as it does in the environment in which it was configured, freeing the user from the tedious task of adapting it manually every time s/he goes to another space. A portable personalization extends the bring your own device paradigm to a new “bring your own space” paradigm. The model is inspired in the object-oriented programming, reinterpreting features such as inheritance and polymorphism to the real world, so it is possible to provide a software system able to adapt existing behaviors to new spaces. The use of the model is exemplified in the paper with two examples of smart spaces.
... Such architectures address well-known characteristics of the pervasive computing paradigm and provide frameworks for facilitating cooperation among application developers. A recent work focuses on an architecture for the development of smart applications and their deployment in SE [4]. The authors propose a reference architecture that operates in a three-stage pipeline, namely perception, reasoning and acting. ...
This paper introduces an architecture as a proof-of-concept for emotion detection and regulation in smart health environments. The aim of the proposal is to detect the patient’s emotional state by analysing his/her physiological signals, facial expression and behaviour. Then, the system provides the best-tailored actions in the environment to regulate these emotions towards a positive mood when possible. The current state-of-the-art in emotion regulation through music and colour/light is implemented with the final goal of enhancing the quality of life and care of the subject. The paper describes the three main parts of the architecture, namely “Emotion Detection”, “Emotion Regulation” and “Emotion Feedback Control”. “Emotion Detection” works with the data captured from the patient, whereas “Emotion Regulation” offers him/her different musical pieces and colour/light settings. “Emotion Feedback Control” performs as a feedback control loop to assess the effect of emotion regulation over emotion detection. We are currently testing the overall architecture and the intervention in real environments to achieve our final goal.
... Many cloud and semantic based architectures and frameworks for smart home have been proposed so far [1][2][3][4]. There are still lots of issues to deal with such as multiple scales, multiple system, and resource management. ...
Recently, various types of wireless sensor network systems have been developed. Their price has also been reduced, and we can easily use such systems to monitor human states and behaviors in a house. Furthermore, such kind of information is useful for elderly care and nursing care by robot partners. However, we have to integrate different types of data measured by each sensor node to estimate human states and behaviors. If the measurement data are organized and structured, the monitoring system can do flexible monitoring and share the information. Therefore, we have proposed the concept of Informationally Structured Space (ISS). This paper proposes a methodology for human behavior estimation by wireless sensor networks in ISS. Next, we propose a monitoring system for sensor state and human behavior using ISS. Finally, we show several experimental results and discuss the effectiveness of the proposed method.
... In works related to ambient intelligence Montes, Ortega, Venzala, and Abril (2014) built smart environment based on software reference architecture. The smart environment is used to conduct the perception process in a standard office. ...
In this chapter, we investigate smart maintenance for human capacity management through a wider exposome lens. We describe the general knowledge of exposome in Sect. 12.1. Then, in order to demonstrate how smart maintenance strategy can be better implemented in such hybrid asset management, in particular, exposome aspect, two representative research avenues are introduced in Sects. 12.2 and 12.3, respectively. Section 12.4 summarises this chapter.
The main objective of Ambient Assisted Living
(AAL
) is to offer high performance and easier ways of personalized services, such as health monitoring, mobility training devices, and socially assistive technologies
(ATs). Nowadays, the ageing population, the high costs for the individual treatment in nursing homes, and the importance that the individuals increasingly necessary to be self-supporting all motivate development of intelligent hardware (i.e. ATs) for safe and independent living. However, AAL related to ambient intelligence (AmI
), together with the wide spectrum of ATs, is too heterogeneous and hence difficult to handle. In this context, managing the adaptable embedded software development has become more important, which provides guidance for the organization of a software system including the set of significant decisions, the selection of the structural elements, their relationships to each other, and composition of these elements into progressively larger subsystems, etc. In this chapter, we centre our attention from the perspective of computer science, particularly, we focus on the proposal of software reference architecture (SRA
) for the development, standardization, and evolution of system architectures of AAL. The main aim of this work tends to justify that how embedded software development can be better managed via the proposed approach. The ultimate goal would be trans-domain applicability of the adaptable embedded software system.
A smart environment system should automatically control the devices according to the sensing information and users' requirements so as to keep the environmental elements (e.g., temperature, light) within the desired range. System control with minimum power is one key issue in such a system. In this paper, we propose a multi-dimension model for system control. In this model, each environmental element is abstracted into a dimension, such that a service with conditions and targets can be formulated as a multi-dimensional service space, and a smart environment with many services may map to a comprehensive multi-dimensional service space through space computation. Based on this model, we propose a minimum power adjustment algorithm for energy-efficient scheduling in smart environment, which transforms the optimal control problem into the problem of the shortest weighted distance of point-to-polygonal in multi-dimensional space. Theoretical analysis and experimental results show that the proposed model is effective and efficient in energy-efficient system control. It is important to point out that the proposed algorithms are scalable when the number of dimensions or services increases.
Successful ubiquitous systems need to integrate several underlying technologies including different operating systems, advanced middleware, several Internet protocols, sensors, actuators, I/O drivers and many others elements. This scenario means that ubiquitous systems software should cope with different kinds of software/hardware components, programming languages, and interaction protocols. In order to easy software development in this heterogeneous context, software architecture elements provide high abstractions that hide the details of specific platforms. However, a clear and common understanding of the elements that compose a ubiquitous system architecture and their relationship is still missing. Reference Architectures have been used to provide a common ground and to give directions for the construction of software architectures for different classes of systems. In this paper, we propose RA-Ubi, a reference architecture for ubiquitous systems that was build based on PROSA-SA, a process for the establishment of new reference architectures. Following PROSA-SA’s steps, RA-Ubi defines the architectural requirements of ubiquitous systems by following the literature about this subject, applying literature systematic review technique. As main results, we present RA-Ubi reference architecture detailing the role of each element and their relationships.
We propose a learning and prediction based paradigm for designing smart home environments. The foundation of this paradigm lies in information theory as it manages uncertainties of the inhabitants' contexts (e.g., locations or activities) in daily lives. The idea is to build compressed dictionaries of context-aware data collected from sensors and devices monitoring and/or controlling the smart environment, efficiently learn from these profiles, and finally predict inhabitant's future contexts. Successful prediction helps automate device control operations and tasks within the environment as well as to identify anomalies. Thus, the learning and prediction based paradigm optimizes such goal functions of smart environments as minimizing maintenance cost, manual interactions and energy utilization. After identifying important features of smart environments, we present an overview of our MavHome architecture and apply the proposed paradigm to the inhabitant's location and activity tracking and prediction, and automated decision-making capability.
In this essay we will present a coherent way to create UbiComp applications. These are considered to consist of tangible objects, which carry the computing and networking technology required. By providing uniform abstractions and a supporting middleware, we treat objects as components of a UbiComp application. The component architecture is made directly visible and accessible via an Editor device that enables end-users to act as programmers. The possibility to reuse devices for several purposes - not all accounted for during their design - opens possibilities for emergent uses of ubiquitous devices, whereby the emergence results from actual use and people's creativity.
Advancements in supporting fields have increased the likelihood that smart-home technologies will become part of our everyday environments. However, many of these technologies are brittle and do not adapt to the user's explicit or implicit wishes. Here, we introduce CASAS, an adaptive smart-home system that utilizes machine learning techniques to discover patterns in resident's daily activities and to generate automation polices that mimic these patterns. Our approach does not make any assumptions about the activity structure or other underlying model parameters but leaves it completely to our algorithms to discover the smart-home resident's patterns. Another important aspect of CASAS is that it can adapt to changes in the discovered patterns based on the resident implicit and explicit feedback and can automatically update its model to reflect the changes. In this paper, we provide a description of the CASAS technologies and the results of experiments performed on both synthetic and real-world data.
In this paper, we present a novel smart home system integrating energy efficiency features. The smart home application is built on top of Hydra, a middleware framework that facilitates the intelligent communication of heterogeneous embedded devices through an overlay P2P network. We interconnect common devices available in private households and integrate wireless power metering plugs to gain access to energy consumption data. These data are used for monitoring and analyzing consumed energy on device level in near real-time. Further, transparent information about the energy usage can be used to efficiently program and control home appliances depending on various factors, e.g. the electricity price. Making more and more data available to end-users, brings with it further challenges in the area of user interfaces. Hence, we complete the smart home system by intuitive user interfaces presenting energy consumption data in meaningful contexts and allowing end users to interact with their environment. We argue, that the combination of both, a technically sophisticated smart home application and at the same time transparent, intuitive user interfaces showing information regarding the energy usage, e.g. energy price, energy source, standby consumption etc., has the potential to bring the vision of the energy efficient smart home within reach.
We've long heard about the wide functionality that home automation technologies offer for improving our lives and securing our houses. However, price and an unstable domotics market have restricted such systems' deployment. Nowadays, companies offer too technology-dependent solutions that don't cover user demands completely. Meanwhile, research works focus on small innovations on specific parts of home automation systems, which don't consider integration and deployment issues to present practical designs. The system presented in this article considers user requirements, including novel advances, all in an integral home automation solution suitable for many services. The architecture's modular nature allows direct adaptation to specific cases using standard domotic technologies, for managing in-house devices, and a proposal of an IP-based network for connecting the main home automation module with other platform elements. A remote security system has been developed, and managing tasks are enabled via in-home control panels and an advanced 3D application for local and remote homeowner access. The system has been deployed on a prototype house, testing a wide set of domotic services. Moreover, the range of indoor pervasive applications has also been extended to e-health, elderly adaptation, greenhouse automation, and energy efficiency.
A wireless sensor network (WSN) is a group of sensors linked by wireless medium to perform distributed sensing tasks. WSNs have attracted a wide interest from academia and industry alike due to their diversity of applications, including home automation, smart environment, and emergency services, in various buildings. The primary goal of a WSN is to collect data sensed by sensors. These data are characteristic of being heavily noisy, exhibiting temporal and spatial correlation. In order to extract useful information from such data, as this paper will demonstrate, people need to utilise various techniques to analyse the data. Data mining is a process in which a wide spectrum of data analysis methods is used. It is applied in the paper to analyse data collected from WSNs monitoring an indoor environment in a building. A case study is given to demonstrate how data mining can be used to optimise the use of the office space in a building.
In this paper we take a look at the state of the art in smart environments research. The survey is motivated by the recent dramatic increase of activity in the field, and summarizes work in a variety of supporting disciplines. We also discuss the application of smart environments research to health monitoring and assistance, followed by ongoing challenges for continued research.
The goal of the MavHome (Managing An Intelligent Versa- tile Home) project is to create a home that acts as a rational agent. The agent seeks to maximize inhabitant comfort and minimize operation
cost. In order to achieve these goals, the agent must be able to predict the mobility patterns and device usages of the inhabitants.
Because of the size of the problem, controlling a smart environment can be effectively approached as a multi-agent task. Individual
agents can address a portion of the problem but must coordinate their actions to accomplish the overall goals of the system.
In this chapter, we discuss the application of multi-agent systems to the challenge of controlling a smart environment and
describe its implementation in the MavHome project.
Ubiquitous computing environments accrete slowly over time rather than springing into existence all at once. Mechanisms are needed for incremental integration- the problem of how to incrementally add or modify behaviors in existing ubicomp environments. Examples include adding new input modalities and choreographing the behavior of existing independent applications. The iROS event heap, via its publish-subscribe coordination mechanism, provides the foundation for interoperation through event intermediation, but does not directly provide facilities for expressing these intermediations. The patch panel provides a general facility for retargeting event flow. Intermediations can be expressed as simple event translation mappings or as more complex finite-state machines. We describe an implemented prototype of the patch panel, including examples of its use drawn from real life applications in production use in the iRoom ubiquitous computing environment.
Scaling AI algorithms to large problems requires that these algorithms work together to harness their respective strengths. We introduce a method of automatically constructing HHMMs using the output of a sequential data-mining algorithm and sequential prediction algorithm. We present the theory of this technique and demonstrate results using the MavHome intelligent environment.
We are building a home, called the Aware Home, to create a living laboratory for research in ubiquitous computing for everyday activities. This paper introduces the Aware Home project and outlines some of our technology- and human-centered research objectives in creating the Aware Home.
The Context Recognition Network (CRN) Toolbox permits fast implementation of activity and context recognition systems. Using parameterizable and reusable software components, it provides a broad set of online algorithms for multimodal sensor input, signal processing, and pattern recognition. The CRN Toolbox also features mechanisms for distributed processing and support for mobile and wearable devices. Three case studies demonstrate its versatility. In these case studies, the CRN Toolbox supports information flow in hospitals, monitors walking habits to help prevent cardiovascular diseases, and recognizes hand gestures in a car-parking game. This article is part of a special issue on activity-based computing.
Pervasive computing is to enhance the environment by embedding many computers that are gracefully integrated with human users. To achieve this, the key research thrust is to create a smart context-awareness environment which should enclose various users and satisfy different needs of the users. Building such smart environments is still difficult and complex due to lacking a uniform infrastructure that can adapt to diverse smart domains. To address this problem, we propose a context-aware computing infrastructure, called FollowMe. Our infrastructure integrates an ontology based context model and a workflow based application model with the OSGi framework. By plugging different domain contexts and applications, FollowMe can be customized to various domains.
VisualRDK is a high-level programming language for prototyping pervasive applications. Context is tightly integrated into the language itself, so developers can attach functionality to locations, persons, or situations instead of the device. Pervasive computing appliances range from consumer devices over embedded sensor boards to PCs and large-scale context servers. Because these devices vary tremendously in their capabilities, application developers must create different programming models for every class of device. This makes rapid prototyping infeasible as soon as more than one class of devices is involved. Rapid prototyping therefore requires a programming model that hides the environment's heterogeneity.
The paper discusses the Gaia metaoperating system which extends the reach of traditional operating systems to manage ubiquitous computing habitats and living spaces as integrated programmable environments. Gaia exports services to query, access, and use existing resources and context, and provides a framework to develop user-centric, resource-aware, multidevice, context-sensitive, and mobile applications.
A new mathematical method is proposed to convert the oscillator instability parameters from Allan variance to Spectrum Density (SD) of random phase fluctuations, which is the inversion of the classic transformation formula from SD to Allan variance. Due to the fact that Allan variance does not always determine a unique SD function, Power-law model of the SD of oscillator phase fluctuations is introduced to the translating algorithm. And that a constrained maximum likelihood solution is presented. Considering that the inversion is an ill-posed problem, a regularization method is brought forward in the process. Simulation results show that the converted SD of phase fluctuations from Allan variance parameters agrees well with the real SD function. Furthermore, the effects of the selected regularization factors and the input Allan variances are analyzed in detail.
Specialized elements of hardware and software, connected by wires, radio waves and infrared, will be so ubiquitous that no one will notice their presence.
With the ever increasing device count and the introduction of pervasive computing in residential homes, naturally also the energy demand constantly rises. Currently, much effort is put in counteracting this development by making appliances more energy efficient. However, a still widely neglected potential for energy savings resides in the use, control and interaction of facilities. To reach their full efficiency during operation, a comprehensive software system that orchestrates all energy facilities in the home is needed. Such a solution also provides an integration point for decentralized energy production systems and smart grid applications. To operate successfully, the system has to be aware of a multitude of different energy parameters and facilities as well as providers in order to make energy efficient decisions on behalf of the user, thus aiding in the realization of an eco-friendly operation of the smart home. In this work, such a smart home knowledge base is realized following the Web Ontology Language (OWL) standard. Its structure makes all knowledge easily available to the smart home system and considerably supports the control processes with its inherent logic.
After the mainframe and personal computer eras, the third major era in computer science, ubiquitous computing, describes the state of technology in which networked computers would surround every user. The Handbook of Research on Ubiquitous Computing Technology for Real Time Enterprises combines the fundamental methods, algorithms, and concepts of pervasive computing with current innovations and solutions to emerging challenges. With more than 25 authoritative contributions by over 50 of the world's leading experts this groundbreaking resource systemically covers such salient topics as network and application scalability, wireless network connectivity, adaptability and "context-aware" computing, information technology security and liability, and human computer interaction.
Specialized elements of hardware and software, connected by wires, radio waves and infrared, will be so ubiquitous that no one will notice their presence.
Energy saving is nowadays a mandatory requirement for buildings. In this paper, a novel holistic system for intelligent Smart Home environments is introduced, which is able to embrace energy production and consumption in a unique perspective and to handle them in conjunction with device and services management. Semantic Web technologies are employed to foster data interoperability and to supply inference power for intelligent tasks management, decisions making and energy saving. The proposed system uses an IP-based network as main communication channel and a semantic extension of the UPnP technology, to support zero-configuration, automatic discovering and intelligent control. The ontology framework, used to formally describe all relevant information of the Smart Home environment like devices, services and context, is also presented focusing on the device and the energy ontology. In addition, the issue of the lack of Semantic Web compliant device descriptions that currently are not provided by device vendors, posing a serious barrier toward the practical application of semantic technologies in Smart Home scenario, is also tackled.
Recognition of inhabitants' activities of daily living (ADLs) is an important task in smart homes to support assisted living for elderly people aging in place. However, uncertain information brings challenge to activity recognition which can be categorised into environmental uncertainties from sensor readings and user uncertainties of variations in the ways to carry out activities in different contexts, or by different users within the same environment. To address the challenges of these two types of uncertainty, in this paper, we introduce the innovative idea of incorporating activity duration into the framework of learning inhabitants' behaviour patterns on carrying out ADLs in smart home environment. A probabilistic learning algorithm is proposed with duration information in the context of multi-inhabitants in a single home environment. The prediction is for both inhabitant and ADL using the learned model representing what activity is carried out and who performed it. Experiments are designed for the evaluation of duration information in identifying activities and inhabitants. Real data have been collected in a smart kitchen laboratory, and realistic synthetic data are generated for evaluation. Evaluations show encouraging results for higher-level activity identification and improvement on inhabitant and activity prediction in the challenging situation of incomplete observation due to unreliable sensors compared to models that are derived with no duration information. The approach also provides a potential opportunity to identify inhabitants' concept drift in long-term monitoring and respond to a deteriorating situation at as early stage as possible.
MundoCore is a communication middleware specifically designed for the requirements of pervasive computing. To address the high degree of heterogeneity of platforms and networking technologies, it is based on a microkernel design, supports dynamic reconfiguration, and provides a common set of APIs for different programming languages (Java, C++, Python) on a wide range of different devices. The architectural model addresses the need for proper language bindings, different communication abstractions, peer-to-peer overlays, different transport protocols, different invocation protocols, and automatic peer discovery.
This chapter aims to illustrate a possible way of using decision trees to make Smart Homes smarter. Decision trees are popular
modelling technique, and the corresponding models are both predictive and descriptive. We formulate the modelling problem
by defining the generic question “Is the undergoing activity or event in the Smart Home usual?” Then we explain how it is
possible to gather appropriate data from the sensors and pre-process these data to form appropriate input for a decision tree
algorithm. We further explain the mainstream approaches in decision trees algorithms rather then analysing them in detail,
and we give short overview of available software. Finally, we explain some measures for quantitative and qualitative evaluation
of the induced decision tree models (e.g. expert opinion, cross-validation, statistical tests etc.).
We propose a learning and prediction based paradigm for designing smart home environments. The foundation of this paradigm
lies in information theory as it manages uncertainties of the inhabitants’ contexts (e.g., locations or activities) in daily
lives. The idea is to build compressed dictionaries of context-aware data collected from sensors and devices monitoring and/or
controlling the smart environment, efficiently learn from these profiles, and finally predict inhabitant’s future contexts.
Successful prediction helps automate device control operations and tasks within the environment as well as to identify anomalies.
Thus, the learning and prediction based paradigm optimizes such goal functions of smart environments as minimizing maintenance
cost, manual interactions and energy utilization. After identifying important features of smart environments, we present an
overview of our MavHome architecture and apply the proposed paradigm to the inhabitant’s location and activity tracking and
prediction, and automated decision-making capability.
Context-aware systems are an emerging genre of computer systems that help add some forms of intelligence to our surroundings. The ATRACO project uses the ambient ecology metaphor to conceptualize a space populated by connected devices and services that are interrelated with each other, the environment and the people, supporting the users' everyday activities in a meaningful way. Everyday appliances, devices, and context aware artifacts are part of the ATRACO ambient ecologies. In this paper we present the connected home platform adopted by ATRACO and its evolution to provide network adaptation and context-aware services. A flexible and distributed context-aware service model is introduced using the OSGi and UPnP frameworks. UPnP is used to converge the existing network infrastructure comprising of heterogeneous technologies and protocols at the IP level. Furthermore, we introduce a context-aware service model and provide paradigms of context aware services that build upon perceptual and context aware components of the platform.
As consumer electronic devices become more powerful and networked, users are required to understand more and more `complex' device functionalities just to carry out simplest tasks. Users are experiencing more and more inconvenience and frustration as the number and complexity of home devices rise and the amount of content/data stored in the home increases. To address these problems, we have developed middleware technologies to integrate heterogeneous CE devices and allow users to simply select what activities they want to perform in the home. Our middleware software allows users to use a simple pseudo-English interface to achieve home tasks without having to consider where a particular content is located and how to achieve that task
Ubiquitous computing focusing on users and tasks instead of devices and singular applications is an attractive vision for the future. The idea of nomadic, mobile users in particular poses new challenges for hardware and software. Mobile devices provide vastly different presentation capabilities and need to integrate into heterogeneous environments. Network bandwidth is far from being constant and services may be available only when online. This paper presents MUNDO, an infrastructure for ubiquitous computing that addresses these challenges. The infrastructure is intended to be non-monolithic with its parts supporting mobile computing using multi-modal user interfaces, mobile data delivery, and ad-hoc communication and networking.
Ubicomp software architecture is designed to support ubiquitous computing's fundamental challenges such as heterogeneity, scalability, dependability, security, privacy, spontaneous interoperation, mobility, and context awareness. The software structure is divided by considering application life cycle while close dependence involves context management and context awareness. Open standards with published interfaces and standardized communication mechanisms are used to facilitate the bridging between heterogeneous systems. The ubiquitous system is designed with security characteristics such as user centricity, context mechanisms, and selection. Dynamic environment with assorted infrastructures and partners are needed in Ubicomp to facilitate the development of spontaneous components and provide a generic interface to create specified entities during execution.
Research groups in both academia and industry have developed prototype systems to demonstrate the benefits of pervasive computing in various application domains. Unfortunately, many first-generation pervasive computing systems lack the ability to evolve as new technologies emerge or as an application domain matures. To address this limitation, the University of Florida's Mobile and Pervasive Computing Laboratory is developing programmable pervasive spaces in which a smart space exists as both a runtime environment and a software library. Service discovery and gateway protocols automatically integrate system components using generic middleware that maintains a service definition for each sensor and actuator in the space. The Gator Tech Smart House in Gainesville, Florida, is the culmination of more than five years of research in pervasive and mobile computing. The project's goal is to create assistive environments such as homes that can sense themselves and their residents and enact mappings between the physical world and remote monitoring and intervention services.
Sentient computing systems, which can change their behaviour based on a model of the environment they construct using sensor data, may hold the key to managing tomorrow's device-rich mobile networks. At AT&T Laboratories Cambridge, we have built a system that uses sensors to update a model of the real world. We designed the model's terms (object positions, descriptions and state, and so forth) to be immediately familiar to users. Thus, the model describes the world much as users themselves would. We can use this model to write programs that react to changes in the environment according to the user's preferences. We call this sentient computing because the applications appear to share the user's perception of the environment. Treating the current state of the environment as common ground between computers and users provides new ways of interacting with information systems. A sentient computing system doesn't need to be intelligent or capable of forming new concepts about the world, it only needs to act as though its perceptions duplicate the user's. In earlier work, we described a prototype of this system and stated our intention to deploy it on a large scale. We have now installed an enhanced version throughout an office building. Over the past year, approximately 50 staff members have used the system daily with a set of trial applications
Sensor networks have become an important source of data with numerous applications in monitoring various real-life phenomena as well as industrial applications and traffic control. Unfortunately, sensor data is subject to several sources of errors such as noise from external sources, hardware noise, inaccuracies and imprecision, and various environmental effects. Such errors may seriously impact the answer to any query posed to the sensors. In particular, they may yield imprecise or even incorrect and misleading answers which can be very significant if they result in immediate critical decisions or activation of actuators. In this paper, we present a framework for cleaning and querying noisy sensors. Specifically, we present a Bayesian approach for reducing the uncertainty associated with the data, that arise due to random noise, in an online fashion. Our approach combines prior knowledge of the true sensor reading, the noise characteristics of this sensor, and the observed noisy reading in order to obtain a more accurate estimate of the reading. This cleaning step can be performed either at the sensor level or at the base-station. Based on our proposed uncertainty models and using a statistical approach, we introduce several algorithms for answering traditional database queries over uncertain sensor readings. Finally, we present a preliminary evaluation of our proposed approach using synthetic data and highlight some exciting research directions in this area.
In this particular case, no superfluous information is received, and hence the Filter of this applications does not remove any data
- Filter
Filter. In this particular case, no superfluous information is received, and hence the Filter of this applications does not remove any data.
Finally, the Dashboard software stores all instances in arff for-mat and also in SQL in the relational database, since these are useful References
- Output Input
- bullet
- Store
Input and output. @BULLET Store. Finally, the Dashboard software stores all instances in arff for-mat and also in SQL in the relational database, since these are useful References
A context aware connected home platform for pervasive applications, Second IEEE Interna-tional Conference on Self-Adaptive and Self-Organizing Systems Workshops
- A Meliones
- D Economou
- I Grammatikakis
- A Kameas
- C Goumopoulos
A. Meliones, D. Economou, I. Grammatikakis, A. Kameas, C. Goumopoulos, A context aware connected home platform for pervasive applications, Second IEEE Interna-tional Conference on Self-Adaptive and Self-Organizing Systems Workshops, 2008, pp. 120–125.
Application of Decision Trees to Smart Homes Cleaning and querying noisy sensors
- V Stankovski
- J Trnkoczy
- E Elnahrawy
- B Nath
V. Stankovski, J. Trnkoczy, Application of Decision Trees to Smart Homes, Springer,
2006.
[35] E. Elnahrawy, B. Nath, Cleaning and querying noisy sensors, Proceedings of the 2nd
ACM International Conference on Wireless sensor Networks and Applications, 2003.
- R Ballagas
- A Szybalski
- A Fox
R. Ballagas, A. Szybalski, A. Fox, Patch Panel: Enabling Control-flow Interoperability
in Ubicomp Environments, Event (London), 2004.
A multi-agent approach to controlling a smart environment
- D Cook
- M Youngblood
- S Das
D. Cook, M. Youngblood, S. Das, A multi-agent approach to controlling a smart
environment, Lect. Notes Comput. Sci 4008 (2006) 165.