Ebook: Workshop Proceedings of the 10th International Conference on Intelligent Environments

We are witnessing an historic technological revolution as computing reaches maturity to become immersed in our daily life to an extent that some decades ago was considered science fiction.

Advances in the engineering of sensing and acting capabilities distributed in a wide range of specialized devices is providing at last an opportunity for the fundamental advances that computer science achieved in the past few decades to make an impact in our daily lives.

This technical confluence is matched by a unique historical context where users are better informed (and more aware of the benefits that technology can provide) and production of more complex systems is becoming more affordable. Sensors/actuators deployed in an environment (in this context it can be any physical space like a house, an office, a classroom, a car, a street, etc.) facilitate a link between an automated decision making system connected to that technologically enriched space. This computing empowered environment enables the provision of an intelligent environment, i.e., “a digital environment that proactively, but sensibly, supports people in their daily lives”. This is a very active area of research which is attracting an increasing number of professionals (both in academia and industry) worldwide.

The prestigious 10th International Conference on Intelligent Environments (IE'14) is focused on the development of advanced Intelligent Environments and stimulates the discussion on several specific topics which are crucial to the future of the area. As part of that effort to stimulate development in critically important areas, five workshops were supported as part of IE'14. This volume is the combined proceedings of those five workshops:

• 9th Workshop on Artificial Intelligence Techniques for Ambient Intelligence (AITAmI'14)

• 2nd International Workshop on Applications of Affective Computing in Intelligent Environments (ACIE'14)

• 3rd edition of the Workshop on Future Intelligent Educational Environments (WOFIEE'14)

• 2nd Workshop on Cloud-of-Things 2014 (CoT'14)

• 3rd International Workshop on the Reliability of Intelligent Environments (WoRIE 2014)

• 4th Workshop on Creative Science 2014 (CS'14)

• 1st Workshop on Hyperrealistic Intelligent Environments 2014 (HyperRealitIE'14)

As a result of the content focus of those events described above, this volume offers you a glance at the latest developments in key areas of the development of Intelligent Environments. It compiles the latest research done by active researchers in the area working to push ahead the boundaries of science and focused on achieving the deployment of intelligent environments in the real world. The effort of these professionals will influence the way we leave tomorrow's world. We hope you enjoy as a reader the content of this volume as much as the attendees of these workshops enjoy the live presentation of the papers and the thought provoking discussions emanating from them.

The co-editors of this volume want to thank all the people that facilitated the realization of each one of these events: the remaining co-chairs of the workshops, the members of their Program Committees, which facilitated the review of papers, the external reviewers who also contributed to that task, and the conference organizers which provided a supportive environment for the realization of these events.

June 2014

Juan C. Augusto, Middlesex University, London, United Kingdom

Tongzhen Zhang (Shanghai Jiaotong University, P.R. Of China)

Workshop Co-chairs of IE'14

Development of high precision systems for recognition of human actions directly from video records is still open problem. Recently, in smart environments the recognition of dynamic actions of human in motion receives a particular interest. We propose two approaches for human action recognition. In the first approach, the envelope of 30x30 pixels is applied to enclose invariant to dimensions human silhouette separated from background. Once the area with located figure is defined, the image sequence is used as input of convolutional neural network that extracts global figure features without previous image processing. The second proposed approach is based on natural knowledge of the human figure such as proportions of body and position of feet. Together with processing global features, we extract six local features combining in this way the holistic and cluster-based approaches for representation of human figure. The input sub-sequence of previously aligned binary silhouettes from video frames is processed to concatenate local and global features into a single feature vector feeding hierarchical system of three linear support vector machines for human action classification. In order to evaluate the proposed approaches, two frameworks for recognizing human actions such as walk, jump, run, side and skip have been designed and tested on Weizmann standard and proper developed datasets achieving correct classification rate of 97–100%.

Applications of innovative technologies for elderly care in the home environment are gaining increasing popularity. A whole area of research investigates how to help older adults to maintain functional capabilities, to enhance their security, to prevent their social isolation and to support them in maintaining the multifunctional network of contacts. Particularly for people affected by a decrease in cognitive performance, cases of poor adherence to medical treatments are not uncommon, yet constitute a significant cause of physical deterioration and treatment failure. Some of the Ambient Assisted Living (AAL) tools contain functionalities to remind people to take their medications that are, usually, relatively simple time-based alarm systems that end up being not particularly effective. Their ineffectiveness can be sought in their reduced capacity to adapt to the different dynamic needs of individual users. This paper explores the possibility of designing personalized end-to-end services, giving special attention to user tailored reminding services that continuously adapt to the individual's needs. In particular the paper presents recent results from the GIRAFFPLUS project in which a basic reminding functionality is scaled up to obtain an adaptive version able to personalize the service to single users on the basis of the information continuously provided by a sensor network deployed in the living environment. The basic algorithmic aspects are described and working examples discussed.

The implementation of assistance systems for Intelligent Environments still is a challenging task. Behavioral models help to derive supportive actions from the observation by sensors. But the creation of such models on the level of detail required is a resource consuming task. Methods for the (partly) generation of behavioral models for use cases require protocolled event traces. This paper suggests an approach to record user behavior without the need of real users performing in the real environment. Results of this method can easily be incorporated into the model generation.

This work relates to context-awareness of things that belong to IoT networks. Preferences understood as a priority in selection are considered, and dynamic preference models for such systems are built. Preference models are based on formal logic, and they are built on-the-fly by software agents observing the behavior of users/inhabitants, and gathering knowledge about preferences expressed in terms of logical specifications. A 3-level structure of agents has been introduced to support IoT inference. These agents cooperate with each other basing on the graph representation of the system knowledge. An example of such a system is presented.

Early diagnosis of social isolation in older adults can prevent physical and cognitive impairment. This diagnosis usually consists on personal and periodic application of psychological assessment instruments. Unfortunately this is often a tedious process and therefore this is a situation that opens up opportunities in creating new ways of diagnosis. In this context, ambient intelligence and social networking sites are suitable technologies for automatic monitoring of significant changes in social interactions of older adults. However, current instruments that measure social isolation are based on subjective aspects since they only evaluate emotional social support and they do not consider objective aspects. This is the reason why a prediction model based on objective isolation variables is needed in order to measure the social interactions through computing mechanisms. This paper presents the development of a prediction model from the social interaction activities that can be registered through smartphone's sensory capabilities, the personal communications using an online social network and also radio-frequency identification mechanisms. The proposed model will benefit institutions interested in developing technological solutions to detect early stages of social isolation and improve the quality of life of older adults.

Affect plays an essential role in the creative ideation of artists. This paper presents work in developing an intelligence framework for augmented environments with the aim of facilitating higher levels of creativity in arts education environments. We base our study on data collected from students at a leading US arts institution, as well as other research, that have shown a direct correlation between positive mood and high-levels of creative ideation. This paper discusses several participatory sensing methods we have employed in collecting affective information, the ongoing development of an intelligence framework, and several ways in which we are working to apply this framework in augmented art environments.

It has been demonstrated that there is correlation between increased blood perfusion in the orbital muscles and stress levels for human beings. It has also been suggested that this peri-orbital perfusion can be quantified through the processing of thermal video. The idea has been based on the fact that skin temperature is heavily modulated by superficial blood flow. We have developed a high-definition thermal-imaging technique that can detect stress by recording the thermal patterns from people's faces. This technique has an accuracy comparable to that of polygraph examination by experts and has potential for application in remote and rapid security screening, without the need for skilled staff or physical contact. Although polygraph examinations, which have high precision when applied by experts, are good at identifying liars, they are impracticable for mass screening because skilled operators are needed, subjects have to be attached to instrumentation for several minutes, data analysis is time-consuming and the interpretation of data is delayed. We explored the possibility of using high-definition thermal imaging of the face for detecting deceit because it enables rapid automated analysis of changes in regional facial blood flow to be quantified. For stress recognition, support vector machines (SVM) and LDA are applied to design the stress classifiers and its characteristics are investigated. Using gathered data under psychological polygraphy experiment; the classifiers are trained and tested. The pattern recognition method classifies stressful from non-stressful subjects, based on labels which come from polygraphy data. The successful classification rate is 96% for 12 subjects. This means that facial thermal imaging because of its non-contact advantages, could be a remarkable alternative for psycho physiological methods.

Applications had grown into complex applications, where such complexity negatively impacts usability by owing to provide single static user interface that should meet all users. We focus on adaptive user interfaces, which automatically customize user interface without direct user's invitation. In our previous work we have developed a novel adaptive interface called Boulevard, a panel container with a user interface automatically personalized to an individual user. We present our work-in-progress focused on enhancing Boulevard by utilization of affective computing and eye tracking, since considering user's current emotional state and point of gaze may play important role for performance of adaptive user interface.

This paper presents an approach to the development of emotional avatars that is based on the use of widely available technologies, such as 3D modeling and animation software. We demonstrate the application of a simplified version of the Facial Action Coding System (FACS) to represent basic emotions (anger, disgust, fear, happiness, sadness and surprise) and build an experimental platform to explore how animation and various avatar traits may impact emotion representation and recognition. We experimented with subjects in Mexico and China. Our results show remarkable recognition levels for some prototypical emotions, particularly happiness, sadness and surprise. This is relevant for some intelligent environments in which detecting whether a user experiences a positive or negative emotion is helpful. Our results also show that animation is an important factor in conveying emotion. Finally, from observing subjects with very different cultural backgrounds (Mexico and China), we confirmed the universality of prototypical emotions and the wide applicability of our approach for emotion representation.

Video-based chat has become an increasingly popular communication paradigm. This type of connection involves video, voice and message exchanges that require high data rate transmissions and may lead to long delays due to the huge amount of information bits involved. If transmission rates are not high enough, video quality is reduced and important elements in communication, such as the expression of emotions, may be lost. We have observed that some emotion detection and recognition techniques rely on simplified code representations that could enable representing key images or videos by using much smaller file sizes. In this paper, we investigate the combination of emotion detection and wireless transmission techniques so that the encoded video with emotion representations can be transmitted over low data rate wireless networks. Various tools and applications may be employed to convert the real-time emotions of the sender to codes, each representing a specific emotion state of the sender. Consequently the file size of a video can be reduced to a few coded Kbytes. We then transmit the encoded file over Bluetooth and Wi-Fi wireless networks and compare the latency of different video files with and without emotion encoding. Experimental results show that significant reduction in latency has been achieved using the emotion encoded video files.

The advances of Augmented Reality (AR) technology make the solving of many difficulties become possible. Decades of development in the Augmented Reality field have shown that this emerging technology has the ability to bring about sweeping improvement in numerous areas, especially in education where the AR technology could see its most meaningful fulfillment in one's development. In this paper, we present a comprehensive survey of AR technologies and applications in education domain. In the end of this paper, we summarize several future directions that the educational AR technology would be heading to. We aim to provide instructors and learners, who are using or plan to use AR as a tool in their educational practice, a useful insight into the state-of-the-art AR developments and applications.

In this paper we present an educational model called University Open to the Community. This model is inspired on the social needs and context of our University and aims to align our research efforts toward social impact. Universidad del Valle de Atemajac Campus León is very closed to a zone where people has not all the opportunities they deserved; in fact, it has been found one of the poorest zones in the region. Research, lecturing and social impact should be aligned in order to get the synergy we need in order to have real impact in our community. This project is on an early stage, however we are sure our initiative will impact not only our students and lectures, but our region.

The main purpose of this study was to investigate the views of the primary teachers' future intention to use digital textbooks. In this paper, we take the Technology Acceptance as a foundation and extend the external variables including satisfaction usefulness, interactive learning activities, digital textbook effectiveness and user-interface design. Data was collected through questionnaire from 220 schools in some Chinese province; research is designed as structural equation modelling to analyze the key factors which influence teachers to use digital textbooks that is a new way of digital learning. This paper proposes a number of scientific hypotheses and validates the extending model. Results show that most of hypotheses are supported, which indicate that the extended variables are important factors to make a multi-level influence on teachers. Finally it is inferred that a conceptual model which is accepted easily by teachers, for understanding teachers' satisfaction, effectiveness and intention of digital textbooks and developing or designing the digital textbooks.

Ubiquitous computing is now mature enough to unleash the potential of Smart Homes. The obstacle is no more about hardware concerns but lies in how inhabitants can build, configure and control their Smart Home. In this paper, we defend the idea that End-User-Development (EUD), which considers inhabitants as makers rather than mere consumers, is an effective approach for tackling this obstacle. However, to unleash its potential, we argue that considering the Smart Home as a big computer composed a sensors and actuators that can be weaved together is not enough. We propose to use Activity Theory as a structuring framework to guide the design of futures EUD systems. We reflect on the lifecycle of devices and services to discuss challenges that EUD system will have to address in the Smart Home context: installation and maintenance, designation, control, development (including programming and testing), and sharing.

The rapid development of sensing and communication technology is providing us a wide array of solutions that are related to home-based e-healthcare to support the health, safety and independence of older people. While these technologies bring us magnificent prospects, everything is still in its infancy when consumers' demand is unclear, researchers do not judge well among various technologies and marketplace is also too early to be defined. We must realize that it is not just an academic problem, but also is related to the demand and market. To better understand the perceptions from different stakeholders, implications of demand, research and market are discussed here.

Residential district is the mainstream living form in Chinese cities. China launched 193 smart cities pilot in 2013. Smart Residential District is a great important part of smart city and there is an urgent need for complete service system as theoretical support. Based on people's higher demands for living and life qualities in China and combined with our construction experiences of Intelligent Residential District, the service system of Smart Residential District was proposed. The result of this research gives the guidance to the top layer design for Smart Residential District and will improve its construction level and quality.