Ebook: Workshop Proceedings of the 11th International Conference on Intelligent Environments

Socrates once said “I know that I am intelligent, because I know that I know nothing”. I believe that being aware of your strengths and weaknesses, what motivates you and your decision making, how you learn from your mistakes and how that self-awareness changes your behavior is what makes human beings intelligent. Today, we have come to an era where many of these human traits are being embedded into our surroundings to create intelligent environments that address our needs and support us in our daily lives. But what is it that makes our environments intelligent? Does our environment deserve it to be called intelligent whenever it can deceive us into believing it is human, like in Alan Turing's test? Or do we expect something else beyond intelligent environments mimicking human behavior? It makes you want to think about how technology is intertwined with society and how we will evolve in the future.

With emerging trends like the Internet of Things, we are deploying and connecting sensors and actuators everywhere to gain information and solve problems. And people expect such systems to be trustworthy, dependable and reliable under all circumstances. However, developing intelligent environments with some common sense seems to be a lot more complicated, and we are probably more than a decade away from sophisticated networked systems exhibiting human-like thoughts and intelligent behavior. But with the growing digital divide, an intelligent environment that passes the Turing Test is not that unimaginable. Therefore, the goal of intelligent environments is not to strive towards the technological singularity, but rather to strengthen both human beings and the technology that surrounds us such that they both will learn to do better and continue to successfully fulfill many achievements. For us, researchers, educators and practitioners, there are long and interesting roads ahead.

As part of this journey, the 11th International Conference on Intelligent Environments focuses on the development of advanced intelligent environments, as well as newly emerging and rapidly evolving topics. This year, we are pleased to include in this volume the proceedings of the following workshops and symposia that cover exactly the above challenges, i.e. reliable intelligent environments – from the home to the workplace – and how we can use them for pedagogical purposes:

• 4th International Workshop on Smart Offices and Other Workplaces (SOOW'15)

• 4th International Workshop on the Reliability of Intelligent Environments (WoRIE'15)

• Symposium on Future Intelligent Educational Environments and Learning 2015 (SOFIEEe'15)

• 1st immersive Learning Research Network Conference (iLRN'15)

As can be witnessed from the above list, the workshops and symposia organized in conjunction with the main conference provide a forum for researchers, scientists and engineers to engage in many interesting and thought provoking discussions that will nurture further research in these key areas of Intelligent Environments. The proceedings compile research and insights into the latest developments of active researchers in these fields. We sincerely hope that you as a reader will enjoy the content of these proceedings, and find them an inspiration for your own work.

As a final note, the editor of this volume would like to take the opportunity to thank everybody who made these proceedings possible. First of all, I would like to express my gratitude to all the authors and researchers that pushed the boundaries of science and created new advances and insights in their field of work. Second, I am also grateful to the organizing committees of these workshops. Without your efforts these events would not have been possible. Thanks also to their program committees that contributed to the reviews of the papers. Finally, I would like to thank the conference organizers and local staff that worked relentlessly behind the scenes to provide a supportive environment and to make these events a success.

I am looking forward to seeing you all in Prague and enjoying the unique character and enthusiasm of the IE workshops.

May 2015

Davy Preuveneers, University of Leuven, Belgium

Workshops Chair of IE'15

Gathering a group of managers or executives (decision-makers) in a same place and at a same time is not an easy task. In fact, the decision-makers' schedule is so tight that it becomes necessary to develop tools that will aid in the communication and in the decision-making process. The intelligent systems (IS) can be the solution to overcome these necessities. In literature, there have been appearing more and more IS that make use of multi agent systems (MAS) in order to represent real decision-makers in this type of systems. In our work we address the problem of how agents should behave during the decision-making process and what strategies they can follow to represent the interests of the decision-maker. We intend to define valid behaviours for agents in group decision-making context and to relate the theoretical behaviours definition with usual attitudes and acts that are relevant for this context. We define two dimensions and relate them with two facets based on the Five Factor Model. Then we propose the behaviours classification according three different levels (low, moderate and high) for each one of the dimensions. We use the value of the personality trait correspondent to each facet in order to classify our behaviours in the scale.

This paper describes the background to a commercial software service called Threads that was developed to allow the sharing of various message types amongst a community of users – typically all working for the same organisation. Recognising the difficulty that many users have in finding even their own e-mail, a key design goal was to make the sharing and searching of large quantity of disparate messages easier than any existing personal mail client. The project has concentrated on developing a user interface that is easy to use rather than easy to program and, in so doing, has highlighted some interesting user perspectives. This paper discusses the typical user's needs and some of the features Threads uses to meet them. We then introduce a novel intelligent method for organising such messages automatically, according to statistics relating to less common words (called “keywords”) which they contain. Initial experiments using this method are described, using both e-mail data from the parent company, and on the publicly available ENRON dataset of e-mails and phone calls. These preliminary results are interesting, but suggest the method as currently implemented is only suitable for semi-automatic classification, but not yet for fully automated allocations to projects. The paper concludes with a glimpse into the future prospects for message sharing and planned future developments to the Threads system.

Recently, we are in the époque of sophisticated Ambient Intelligence (AmI) applications, mainly based on utilisation of wide sensor networks together with advanced AmI approaches. If we concentrate on environmental (that is, open space or outdoor) applications, there is just a few of them, although basically focused on environmental monitoring, that enable more functionalities than just collecting environmentally related data and passing them to further elaboration. In our paper we intend to go further on with the ideas how environmentally oriented wireless sensor networks used in “large-scale” throughout the open natural environment could be enhanced using some recent AmI approaches in order to be beneficial in preventing primarily environmentally related problems, if not even disasters. We focus our attention on the area of water management with accent on two critical water related problems: floods management and drought-stricken periods. We suggest a concept of an approach how to solve a particular water management problem in Czech Republic using large-scale ambient intelligence approach enhancing thus wireless sensor network focused on environmental monitoring.

Mobile Cloud Computing paradigm has arisen as a major proposal to address collaboration support in working environments. Particularly, this paradigm has proven to be useful in emergency scenarios, education or tourism. However, these environments are commonly based on dynamic network topologies, which imply unstable connections (disconnections and network partitions). In consequence, the availability of the services can be compromised. Therefore, approaches based on the Service Oriented Architecture (SOA) are insufficient and they must be complemented with techniques and methods of Autonomic Computing, in order to ensure the quality attributes of the system against context changes. In this work, a self-adaptive architecture is proposed in order to address the availability of the services deployed in dynamic network environments. This architecture has been designed to provide a common basis for collaborative mobile systems. The architecture follows a component-based design, and it provides a distributed approach to support the dynamic replication and deployment of services. Further, an example scenario based on a real Mobile Forensic Workspace is described to show the applicability of the proposal.

The Ambient Intelligence (AmI) paradigm applied to the healthcare sector is a promising solution to develop software-based systems capable of supporting medical procedures and activities carried out in a close, high-regulated, and complex healthcare environment. An AmI Healthcare System (AmI-HS) which may impact on the health and life of its users (i.e. doctors, caregivers, patients, etc.) is considered as a Medical Device (MDs), and thus subject to pass through a cumbersome risk-based regulatory process which evaluates and certifies the system safety before it is put on the market. Thus, a human-centred risk analysis is of paramount importance to establish the safety level of an AmI-HS.

In this paper, we propose a dynamic probabilistic risk assessment (DPRA) approach for AmI-HS which allows the quantitative assessment of risk in different hazard scenarios in order both to support the design and development of AmI-HSs and to provide those objective evidences needed during the regulatory process. In addition, to support our risk-based methodology we define a probabilistic risk model (PRM), based on an extension of a Markov Decision Process (MDP), capable of taking into account two main peculiarities of AmI-HSs: context-awareness and personalisation. Some preliminary results show the feasibility of our approach and the capability of our model to assess risk of context-aware hazard scenarios.

As software systems for context-aware applications and intelligent environments become increasingly complex and adaptive, the need to understand and predict the impact of changes grows. Such changes may manifest themselves (1) as alterations in the way users behave, (2) as software customizations to handle new requirements, and (3) as variations on the dynamic context in which intelligent environment systems are deployed and operate. Such internal and external changes may be anticipated or unforeseen in nature. With reliability being a key concern for intelligent environments, we revisit in this work the state-of-practice on change impact analysis (CIA) – a well-known methodology in software engineering – and investigate to what extent it can be applied and enhanced to contribute to the development of more reliable context-aware adaptive applications to increase the confidence in intelligent environment systems.

Users are currently expected to benefit from the concurrent use of different computing devices and applications: Personal computers for an easier content production, mobile devices for increased mobility and context-awareness, wearable devices for more transparent health-related data acquisitions, etc. However, the simultaneous use of different devices and applications could be perceived as disruptive or unproductive, due to the need of additional settings, lack of integration, etc. As a first step to overcome this problem, in this paper we introduce the notion of Continuous Interaction (CoIn) systems. These systems intend to promote the simultaneous use of multiple devices and applications to complete tasks in a more effective, flexible and easy way. To achieve that goal, a set of human-centred design principles have been figured out to enable users to seamlessly share tasks across multiple devices, independently of the software applications supporting their completion. The case study of a Mobile Forensic Workspace (MFW) will be presented to highlight the benefits that CoIn systems could bring to the Ambient Intelligence (AmI) and Ubiquitous Computing research fields.

The error data obtained from the front-end in-class feedback system would be analyzed and judged by the back-end expert system, and the causes of such errors would be provided and the corresponding after-school exercises would then be automatically pushed to the students by the cloud service platform to increase targeted learning and learning efficiency.

Inequity between urban and rural education prevalently exists in China. Lack of qualified teachers is the main cause for disadvantaged education in rural area. In order to solve this problem, Live Broadcast Classroom was adopted in grade 5 English class. 90 students and 3 teachers of 3 classes from two primary schools in Yunnan Province were selected as participants. As for methodology, quantitative and qualitative methods were used. Results showed it was feasible to use Live Broadcast Classroom in solving the inequity problem in micro-level education (i.e., classroom): the gap between students' scores and attitudes towards English between urban and rural classes was narrowed. Challenges still exist and some suggestions are put forward in the end.

For classes with students from diverse disciplines, professors should consider allowing multiple formats of expression in completing assignments. We call these kind of open-ended assignments “free-range assignments”. To design free-range assignments, professors should provide freedom, resources, expectations, examples, reflection, articulation, networks, guidance and evaluation. Professors may also want to consider using technology tools to facilitate the design of such assignments.

With the rapid expanding of learning content resources and users, it is difficult for learners to find right persons they need as knowledge experts and learning peers in open knowledge communities (OKCs) using traditional search engines. According to this situation, the paper presents a social knowledge network-based intelligent framework for finding right persons in OKCs. The architectural details of the framework are proposed in this paper. The authors expound the idea of the intelligent framework design, the work principle and mechanism of each module.

Development of proficiency in mathematics is an essential aspect of many higher education programmes of study. This applies both to specialist mathematics students, and students of many other disciplines, including engineering, most natural sciences and some social/human sciences, business and commercial subjects. Students' knowledge of and expertise in mathematics (or lack thereof), at least at an elementary level, can have a major impact on many other areas of their studies and their subsequent career prospects. However, mathematics is an area which many students find difficult, particularly those from “non-traditional” academic backgrounds, including disabled and mature students, and they often do not realise its relevance and importance to their other courses, nor do they (or can they) devote as much time or effort as they perhaps ideally should, and face to face tutorial support is often limited. In this paper, we describe the design, development and initial evaluation of CalculEng, a system to offer such tutorial support for learning differential and integral calculus – primarily aimed at Engineering students. This system provides structured questions, which are automatically marked, with the aid of a Computer Algebra System, and intelligent, relevant feedback – based on the mistakes made by the student – provided. At present, this feedback is hard-coded using expert-entered rules. However, ways in which the system could be made to intelligently learn patterns of common student errors, and offer feedback accordingly, are being investigated. Our resources should be of particular benefit to students who, due to disabilities or family commitments, may have difficultly attending classes in person.

In web 2.0 era, there was little researches focused on the effect of mobile social software influencing spoken English learning in reforms of technology assist language learning. This study based on the theory of mobile micro learning and mobile learning community, a total of 72 primary school students were empirically investigated the learning outcome of using mobile social software to learn English after class for one semester. The results showed that using mobile social software to learn English after class can improve students' English speaking ability, specific performance in word accuracy, number of sentences and voice tone, and especially has significant effect on increasing the number of sentences.

This paper reports a Needs Analysis survey done on Chinese graduate students majoring in science for an open English for Academic Purpose (EAP) course design. By conducting a survey about the sample group, the researchers attempt to discover graduate students' needs, difficulties, and study habits in English learning, what contents and skill instructions should be included in an online EAP course and how designers and instructors can better involve students in online EAP learning activities. This preliminary Needs Analysis research may provide a basis for innovative online EPA courses design and delivery, and help the selection and preparation of open EPA educational resources.

A science of e-learning involves the scientific investigation of how people learn in electronic learning environments. This paper reports about experiments carried out with OPEN SoundS, which is a musical environment designed and developed as a virtual studio where students and teachers from all over the world, can create collaborative musical projects. The main aim is to uphold a strong level of motivation. The results are two-fold: firstly, students achieved better results in the area of music technology and in the area of theory, analysis and composition; secondly, e-learning strategy is superior to the traditional learning method in terms of learning motivation.

Wechat, a mobile application software with functions of communication, social interaction, and platform architecture, is widely used among college students in China and has constructed a new mobile learning support environment. By analyzing the features of Wechat and Welearn and examining related studies, we discuss how to integrate Wechat-based mobile learning into the College English curriculum in Higher-Educational Institutions of China.

In order to address the lack of student interest in STEM subjects and the dwindling number of students pursuing STEM careers, the Creative Science Foundation (CSF) has developed an easy to deploy educational strategy. This strategy, effectively titled Science Fiction Prototyping, utilizes science fiction stories and material to “explore the possible implications of research and technology on humans, societies, and the world.” It is also possible that these prototypes can be used to increase STEM motivation in students. The researchers will first perform a meta-analysis and literature review to determine the present outlook of STEM curriculum, student interest in STEM careers, and student enrollment in STEM careers after graduation. Other parts of the research project include a pilot study to explore the feasibility of using science fiction prototypes within a high school environment to increase student interest and attraction to STEM related careers.