Ebook: Workshop Proceedings of the 9th International Conference on Intelligent Environments
Intelligent Environments (IE) play an increasingly important role in many areas of our lives, including education, healthcare and the domestic environment. The term refers to physical spaces incorporating pervasive computing technology used to achieve specific goals for the user, the environment or both.
This book presents the proceedings of the workshops of the 9th International Conference on Intelligent Environments (IE ‘13), held in Athens, Greece, in July 2013. The workshops which were presented in the context of this conference range from regular lectures to practical sessions. They provide a forum for scientists, researchers and engineers from both industry and academia to engage in discussions on newly emerging or rapidly evolving topics in the field. Topics covered in the workshops include artificial intelligence techniques for ambient intelligence; applications of affective computing in intelligent environments; smart offices and other workplaces; intelligent environment technology in education for creative learning; museums as intelligent environments; the application of intelligent environment technologies in the urban context for creating more sociable, intelligent cities and for constructing urban intelligence. IE can enrich user experience, better manage the environment’s resources, and increase user awareness of that environment.
This book will be of interest to all those whose work involves the application of intelligent environments.
Humans have been embedding information into their environments or onto the objects that these environments consist of since the ancient years of mankind. Epigraphs and wall paintings are examples of such communication acts.
Information may be communicated to us within an environmental context through a variety of media and accordingly these may support human activities in different ways. For example, signs  may communicate secondary environmental information needed to make wayfinding decisions; they tell the user what is where and they also specify when and how an event is likely to occur. Signs, symbols, graphic representations or linguistic communication – spoken or written – are different forms of secondary spatial information sources which may be communicated through a medium to a user in an environment and thus enrich this environment with meaning, ultimately augmenting the experience afforded by this environment. Of course, this information enhances the overall information referring to this environment that the user has already acquired from sensory input, as a result of navigating and interacting, amongst the physical objects that the environments consists of.
Information and Communication Technologies (ICTs) and the new media they support have introduced many new ways of augmenting the experience of physical environments in order to communicate meaning and support several computer-mediated activities or interpersonal mediated communication, amongst individuals who occupy these spaces. Our contemporary urban environment is already filled with various media and appropriate display systems and artifacts
Most of these representations are visual, i.e. large size prints, video projections, wall paintings, TV closed circuits, touch screens etc.
Most of these representations are visual, i.e. large size prints, video projections, wall paintings, TV closed circuits, touch screens etc.
ICTs, whether mobile, wireless or embedded in persistent architectural forms, facilitate the collection and dissemination of data, infusing the physical expression of the environment with digital layers of content, thus contributing to the emergence of new hybridized spatial experiences as well as novel forms of interacting with computers and with other participating humans. These systems and the hybrid spatial experiences they afford, encourage encounters among users; both embodied and mediated, and influence community dynamics, giving rise to networks around common interests and collectives of affect. Sometimes, such groups, irrespective of how ephemeral, unstable and dispersed they may be, negotiate a new kind of engagement with the urban environment and civic life, suggesting thus an organizational paradigm that manages to surpass traditional vertical hierarchies of space and consequently of power and control .
It is therefore evident that the deployment of intelligent environment systems and applications has very significant consequences at a psychological, social, political and cultural level for all participants of these experiences as well as for the stake holders involved. Therefore, it is suggested that the processes of designing, developing and evaluating intelligent environments should also be seen from a multidisciplinary perspective in order to assure that these systems will be embedded in our everyday lives and environments in the best possible manner, by taking into account the needs, potential and expected impact that their use may have onto individuals, groups or communities of people. Such an interdisciplinary approach may lead to the creation of ergonomically efficient, aesthetically pleasing and functional Intelligent Environment systems. Accordingly, there is a need for new design practices and methodologies that may take into account the hybrid nature of the spatial experience afforded by these media, as well as the opportunities for socialisation and communication that they may offer. Examples of the disciplines that the production of Intelligent Environments may relate to are: cognitive psychology, environmental psychology, architectural and visual design, urban studies, design studies, social and cultural studies, museum studies, political communication, etc.
The need for a multidisciplinary approach is indeed one of the implicit aims for organizing a series of international workshops for the fifth time in the context of the Intelligent Environments Conference in 2013 which is held in Athens, Greece. This need was adequately accomplished as is evident in the very interesting and challenging international workshops which are included in the program and documented in these proceedings.
This is actually the 9th Intelligent Environments (IE) conference and it is organized by the School of Architecture – National Technical University of Athens (NTUA) and the Hellenic Open University (HOU). The workshops part of the 9th IE conference is organized by the Faculty of Communication and Media Studies of the National and Kapodistrian University of Athens and the Hellenic Open University. Previously, the Intelligent Environments Conference has been successfully organized in Colchester, UK (2005), Athens, Greece (2006), Ulm, Germany (2007), Seattle, USA (2008), Barcelona, Spain (2009), Kuala Lumpur, Malaysia (2010), and Nottingham Trent University, United Kingdom (2011).
The workshops part of the conference is organized with the aim of providing a forum for scientists, researchers and engineers from both industry and academia to discuss about topics related to intelligent environments, ubiquitous computing and ambient intelligence. This year we are pleased to include the following workshops:
• AITAmI: The 8th workshop on Artificial Intelligence Techniques for Ambient Intelligence aims at gathering researchers in a variety of AI subfields together with representatives of commercial interests to explore the technology and applications for ambient intelligence. The workshop is organized, once again, by Asier Aztiria (University of Mondragon, Spain), Juan Carlos Augusto (University of Middlesex, United Kingdom), and Diane Cook (Washington State University, USA).
• ACIE: The 1st International Workshop on Applications of Affective Computing in Intelligent Environments is organized by Faiyaz Doctor (Coventry University, United Kingdom) and Victor Zamudio (Instituto Tecnolgico de Len, Mexico). This workshop provides a forum to promote and demonstrate how recent development of unobtrusive physiological sensing can be used to capture emotive or physiological information to enhance IE based applications.
• SOOW: The Smart Offices and Other Workplaces Workshop is organized by Peter Mikulecky (University of Hradec Kralove, Czech Republic), Pavel Cech from the same university and Carlos Ramos (Polytechnic of Porto's Insitute of Engineering, Portugal). This workshop fosters discussion on how ambient intelligence is useful for the development of intelligent workplaces devoted to support working activities.
• CoT: The 1st Cloud of Things Workshop is organized by Jeannette Chin (Anglia Ruskin University) and Victor Callaghan (University of Essex). The workshop will discuss on the synergy offered by the combination of the Internet of Things, Cloud Computing, Intelligent Environments and embedded computing.
• MASIE: The 1st Workshop on Museums As Intelligent Environments is organized by Nikolaos Avouris (University of Patras, Greece), Alexandra Bounia, Niloketa Yiannoutsou and Maria Roussou. The workshop invites researchers and practitioners of intelligent environments technologies with interest in applying them in museums and sites of culture as well as museologists, curators and museum educators who are interested in investigating and discussing the potential of such technologies for modern museums. The workshop is thus intended to act as a forum for cross-fertilization of ideas between museum experts and researchers of intelligent environments.
• WOFIEE: The 2nd Workshop on Future Intelligent Educational Environments is organized By Victor Callaghan (Essex University), Minjuan Wang (San Diego State University), and Juan Carlos Augusto (University of Middlesex, United Kingdom). The focus of the workshop is placed on how intelligent technologies can support the development of new educational technologies and environments around the world.
• IECL: The Workshop on Intelligent Environments for Creative Learning is organized by Elena Antonopoulou, Athina Papadopoulou, Theodora Vardouli and Eirini Vouliouri. It aims to bring together theoretical and technical work that explores ways in which intelligent environments can foster learning, enable user creativity, and develop individual and collective design intelligence.
• SSC: The 1st Sociable Smart City Workshop is organized by Eleni Christopoulou, Dimitrios Ringas and John Garofalakis. The focus of this workshop is on the social and cultural aspects of the smart city. In particular, the organisers seek to study how urban computing alters the city, the perception of people about the city, the communication among people and the social and cultural impact on the city and on city life. The goal of this workshop is to define what is a “sociable smart city” and how this vision can be realized.
• IUIC: The Workshop on Intelligent Users and Intelligent Cities is organized by Dimitris Hatzopoulos, Eleni Mitakou, Paraskevi Fanou and Efpraxia Zamani. The main goal of the workshop is to firstly identify users of intelligent environments by giving them characteristics, and then recognize the parameters that establish the city as an intelligent environment, using among our main research instruments the representational arts.
• CUI: The 1st Workshop on Constructing Urban Intelligence is organized by Dimitris Papanikolaou (DDes candidate, Harrvard GSD). This workshop explores models, methods, and problems of constructing ambient intelligence through human interaction and for this purpose it has invited designers, researchers, and practitioners across multiple disciplinary domains to submit papers with positions on this subject:
We would like to thank everybody who made these proceedings possible, once again for the IE'13. Firstly, we would like to thank each and every workshop's organizing committees. They are the main contributors of this event and without them these workshops would not have been possible. We would also like to thank the local staff who worked really hard to make this series of events a success and the Faculty of Law of the National and Kapodistrian University of Athens who provided significant support for accommodating the workshop activities. Of course we would like to give special thanks to the researchers, who do the hard work, achieve the advances, set the research agenda and then come to Intelligent Environments workshops to present and discuss their insights. We sincerely hope that the audience will find this set of scientific papers interesting and inspiring for their own work. This contribution is our main goal and we believe that succeeding in this effort will ultimately make Intelligent Environments occupy the place they deserve in academia, the industry and the society. Juan A. Botía and Dimitris Charitos
General chairs of the IE'13 Workshops and Editors of the Book
Compressive sensing has become a popular technique in broad areas of science and engineering for data analysis, which leads to numerous applications in signal and image processing. It exploits the sparseness and compressibility of the data in order to reduce the size. Wavelet analysis is one of leading techniques for compressive sensing. In 2D discrete wavelet transform, the digital image is decomposed with a set of basis functions. At each level, wavelet transform is applied to compute the lowpass outcome (approximation) and highpass outcomes (three details), each with a quarter size of the source image. For the subsequent levels, the lower level outcomes turn out to be the inputs of the higher level to conduct further wavelet decompositions recursively, so that another set of approximation and detail components is generated. Discrete wavelet transform and discrete wavelet packet transform differ in higher levels other than the first level of decomposition. From the second level, discrete wavelet transform applies the transform to the lowpass outcomes exclusively, while wavelet packet transform applies the transform to lowpass and highpass outcomes simultaneously. As the more comprehensive approach, wavelet packet transform is selected for scene image compression on cases of both the lower and higher dynamic range images. Quantitative measures are then introduced to compare the outcomes of two cases.
The variety and volume of data produced by devices and sensors in Intelligent Environments (IEs) pose difficulties regarding their collection, analysis and delivery. More specifically, extraction of high level information valuable for the users requires specialized analysis techniques. In this study, we present a framework incorporating complex event processing (CEP) and publish-subscribe based messaging for addressing such needs. Within the framework, data are collected from heterogeneous data sources to go through CEP based analysis, and then the results are delivered to interested recipients. The components of the framework are loosely-coupled through the use of event driven architecture (EDA) in the form of a publish-subscribe messaging system. This enables the use of different CEP engines without requiring the modification of other components in the framework. Similarly, new data sources and delivery end-points can be as easily integrated into the framework. A real life prototype implementation is also provided for validation. The prototype includes various event producers such as electret microphone, light, temperature, motion, magnetic, optical sensors, RFID (Radio Frequency Identification) readers, smart phones, and other software systems, which are deployed in a classroom setting. End users receive relevant raw data and high level information according to their preferences, through the use of web and mobile applications. The results suggest the applicability of the framework for IEs. The prototype implementation in the classroom shows that using different event producers helps improve the analysis results and CEP is an appropriate method for data analysis in IEs.
This paper proposes a framework for an integrated, computational design system, by the agency of interdisciplinarity. The proposed design concept is approached through the formation of a holistically structured unit that is organized as an information processing brain. Considering the before-mentioned aspect about interdisciplinarity, the paper will analyze a multi-performative organization, examining networked intelligence and the role of semi-autonomous systems in design. We demonstrate a design method that addresses a multi-disciplinary problem and integrates generative synthesis mechanisms and tools, in order to formulate an effective computational system. The design concept further investigates the correlation between these concepts to architecture and, hence, materiality and structure. In order to examine the implementation of these terms in architecture, we model a case study for a generative mechanism that enacts as open research. It addresses multi-performativity and complexity by performing various functions, such as task recognition and context-aware applications. A distributed system is employed, in which discrete mechanisms assemble a data flow network. This interaction network defines an intelligent mechanism, which is further examined as a design tool. The present paper brings about design technologies that integrate methods of computer-aided architecture; therefore our case study outlines techniques and applications of machine intelligence. Henceforth, it provides the unique chance to converge multiple disciplines that exchange information at all levels, from the analogue to digital and material realm.
In the present investigation we are looking for improve the features classification of a cardiac arrhythmias database using metaheuristics (Differential Evolution and Particle Swarm Optimization) and classifiers (KNN and Naive Bayes), with the purpose of select the main features and increase the percentage of classification. The classification percentage in some cases increased until 100% and the number of features was significantly reduced.
In this paper, we propose a generic Context Aware Recommendation framework for M-commerce applications. The core of the framework is a Multidimensional Contextual graph which can effectively represent various real-world objects and their relations. Once the graph is created, a Random Walk algorithm is applied to obtain a top-k recommendation list. Both products and services can be flexibly modeled into the framework, in addition to their related information such as ratings and QoS measures. As part of our ongoing work, the framework is aimed at presenting a comprehensive recommendation framework for Mobile users.
Service design in the scope of Ubiquitous and Ambient Intelligence Systems is a complex task given the characteristics and requirements that must be usually addressed, and consequently the number of design decisions that need to be made. Existing methodologies provide guidance to this process from a general-purpose point of view, lacking support for specific features of this paradigm. In this paper, a novel approach to design dynamic, runtime adaptive services based on context information, called SCUBI, is proposed. It consists of a metamodel and a method to design services in terms of components, addressing the special characteristics of Ubiquitous Computing. The proposal is illustrated and validated through a case study of the design of a positioning service.
This paper presents a method for extracting automatically association rules via multi-objective genetic algorithms. The paper also proposes a novel objective measure to quantify the comprehensibility of the rules. The other objectives of the rules are average support value and average confidence value. We experimentally evaluate our approach on socio-demographics and biochemistry datasets of schizophrenia patients and demonstrate that our algorithm encourages us to improve and apply this strategy in many real-world applications.
In Ambient Assisted Living research and development, a significant effort has been dedicated to issues like gathering continuous information at home, standardizing formats in order to create environments more easily, extracting further information from raw data using different techniques to reconstruct context. An aspect relatively less developed but also important is the design of personalized end-to-end services for technology users being them either primary (older people) or secondary (medical doctors, caregiver, relatives). This paper explores an effort, internal to the EU project GIRAFFPLUS, for designing such services starting from a state-of-the-art continuous data gathering infrastructure. The paper presents the general project idea, the current choices for the middleware infrastructure and the pursued direction for a set of services personalized to different classes of users.
Social networks proliferate daily life, many are part of big groups within social networks, many of these groups contain people unknown to you, but with whom you share interests. Some of these shared interest are based on context which has real-time properties (e.g. Who would like to go to a jazz concert during an AI conference). This paper presents a possible method for identifying such subgroups. We aim to do this by creating a social graph based on one or more “comparators”; Frequency (how often two members interact) and content (how often the two talk about the same thing). After the graph is created we apply standard graph segmentation (clique estimation) techniques to identify the subgroups. We propose a system which continuously polls social network for updates, to keep the social graph up-to-date and based on that suggest new subgroups. As a result the system will suggest new subgroups in a timely and near real-time manner. This paper will focus on the methods behind the creation of the weighted social graph and the subsequent pruning of the social graph.
There have been several advances in the field of affective computing analysis, however one of the main objectives of the brain computer interfaces (BCI), it is to interact in a natural way between human and machines; The analysis of the emotional state user is very important since it may provide a more suitable interaction generating closest approach, and efficient interaction. Furthermore extent that implementation of systems that can develope an emotional human-machine interface, applications of affective computing, it could widely used to help people with physical or deliberately to analyze and characterize the emotions that may be of interest and provide benefits on a human activity (eg, performance of athletes).
In this paper seven emotional related experiments where development according whit the model arousal/valence model, each experiment corresponds to an evoked emotion from 32 study subjects and contains information the galvanic skin response (GSR), an electrooculogram (EOG) and electromyogram (EMG), for each user, each emotion is evoked by a process audio/visual for 60 seconds, focused generate three emotions (anger, happiness, sadness). Statistical measures are used to create parameters and distances to generate an overview of classification of signals related to an emotion. For information preprocessing is used discrete wavelet transform and statistical parameters (mean, standard deviation, variance) plus a surface filter.
Future pervasive environments will take into consideration physical and digital social relations. Nowadays it is important use to collective intelligence, where the interpretation of context information can be harnessed as input for context-aware applications, especially for group collaboration. The use of collective intelligence represents new possibilities but also new challenges in terms of collective information for adaptability and personalization in intelligent environments. This paper presents a collaborative context-aware framework focusing on social matching capabilities for session formation in collaborative activities.
As the proportion of older adults grows, the number of special care provisions to help individuals with declining cognitive abilities needs to also increase. Information Communication Technology (ICT) is beginning to play an increasing role in facilitating the work of specialists to support and monitor individuals with cognitive impairment within their everyday environments. In addition, advances in artificial intelligence and the development of new algorithmic approaches can be used to approximate the computational processes of human behaviour in different circumstances. In this paper, we report on the development of a software system using game based therapies for older adults in Mexico suffering from cognitive impairment, where this system has been deployed in a unique day therapy centre. We further propose an evaluation module based on using AI approaches and affective sensing to monitor and detect significant changes in performance cognation that might indicate a possible cognitive decline.
In this paper we describe part of our recent work where we aim to create a ground-truth dataset for affective computing to facilitate in particular the application and development of computational intelligence and other automated reasoning techniques. Following a multi-disciplinary approach, we highlight the need for but also the challenge of creating such a dataset that provides validated mappings of physiological data to a series of affective states (“happy”, “neutral” and “sad” in our case). We proceed to discuss the experimental approach and setup employed in this paper where a recall task is combined with a series of groups of pre-rated images which are employed as affective stimuli shown to participants while their physiological data is captured. The physiological data sources captured include galvanic skin responses (GSR) and heart rate (HR). Preliminary analysis of the results indicates that the statistically the resulting data does not allow the differentiation between the different stimuli/emotions shown/experienced. We provide an initial interpretation of these findings, including a reflection on the complexity of designing “laboratory-style” experiments while still capturing an emotional response from participants.
This paper contributes an overview and criticism of Google's newly emerging mass-personalized mapping, as a model of urban intelligence. What is being brought into question is the model's interactivity. The analytical tool comprises J.C.R. Licklider's computer-enabled communication model and M. Webber's urban planning model, both from the early 1960's. The overall goal is to re-contextualize the human-computer partnership in the direction of cooperatively shaping the urban experience.
Infrastructure is a physical device that delivers a service needed to an end-user (consumer). Thus, it is in its identity to be formed by two distinct layers: the physical structure and the carried service. Today transition to decentralized and distributed infrastructures models focuses on redesigning the way of electricity infrastructures operate considering both a local production of the service from renewable resources and technology, and a more proactive role of the end-user
International Renewable Energy Agency William J. Mitchell
International Renewable Energy Agency
William J. Mitchell
This paper outlines an ongoing project (MITOS), which aims to customize and deploy a software platform providing advanced transportation services in the city of Santander, Spain. The system will be presented with a focus on the design framework and the rationale for evaluating User Experience in such a framework. Concepts for Future Internet environments, such as participatory sensing, game-inspired practices, and ad hoc social networks, will be employed toward this purpose. A set of experiments will be conducted, aiming to qualitatively and quantitatively evaluate the deployed system and assess the impact that its services have on the city, on its citizens/commuters, and on their attitudes towards public transportation use. The project is expected to provide methodological insights on the design and evaluation of interactive location-based systems in hybrid urban contexts. The impact of the system will be manifold and fully aligned to all dimensions related to the impact of the SmartSantander project: environmental, transportation, societal and research/technological. The deployed platform will be available to the city for further experimentation and commercial exploitation, thus being a sustainable system that can affect the activities of the citizens even after the end of the SmartSantander project.
Intelligent Environments are tightly connected with the extended flow of information to and from their users. Their constant need for data together with the desired unobtrusive character put the issue of privacy in stake. As mapping public and private space in the way Nolli did in 1748 is not possible anymore, a contemporary cartography of privacy is sought. This leads to the awareness of a new state of privacy. Through the use of a case study we propose a model that aims to offer anonymity and control of information. Weaknesses do exist and we recognize that much has yet to be done, in both technical and legal aspects.
Understanding the specific qualities of dynamic factors that shape how urban environments work is important to analyzing these environments effectively. Prominent among these factors is the movement of people and the patterns or trends that emerge from that movement over time. In order to better study movement as a dynamic factor in how urban spaces work an academic project titled Sen-Sys (for its use of personal GPS sensors to map dynamic urban systems) was designed and implemented to a limited degree over the course of a semester to produce a movement-based model in which the proportions of urban areas are dynamically distorted to reflect areas of high and low occupation to reflect moment-to-moment spatial behavior and visual elements are generated to reflect recurring trends in movement over of time. This paper provides an overview of Sen-Sys, frames it in relation to similar existing work and discusses it's conceivable strengths, limitations and directions for future development.