In today's fast-paced and demanding society, more and more people are suffering from stress-related problems; however, intelligent environments can be equipped with facilities that assist in keeping it under control. This paper presents CaLmi, a system for Intelligent Homes that aims to reduce the stress of its residents by: (a) monitoring its level through a combination of biometric measurements from a wearable device along with information about user's everyday life and (b) enabling the ubiquitous presentation of relaxation programs, which deliver multi-sensory, context-aware, personalized interventions.

Intelligent Conversational Agents are already employed in different scenarios, both in commerce and in research. In particular, they can play an important role in defining a new natural interaction paradigm between them and humans. When these Intelligent Agents take a human-like form (embodied Virtual Agents) in the virtual world, we refer to them as Virtual Humans. In this context, they can communicate with humans through storytelling, where the Virtual Human plays the role of a narrator and/or demonstrator, and the user can listen, as well as interact with the story. We propose that the behavior and actions of multiple, concurrently active Virtual Humans, can be the result of communication between them, based on a dynamic script, which resembles in structure a screenplay. This paper presents CasandRA, a framework enabling real-time user interaction with Virtual Humans, whose actions are based on this kind of scripts. CasandRA can be integrated in any Ambient Intelligence setting, and the Virtual Humans provide contextual information, assistance, and narration, accessible through various mobile devices, in Augmented Reality. Finally, they allow users to manipulate smart objects in AmI Environments.

The concept of Ambient Intelligence (AmI) is already playing an important role in enriching the educational experience. Such technologies offer students increased access to information within an augmented teaching environment, which encourages active learning and collaboration, enhancing their motivation to learn. Research work in this domain includes the learner-centered design and implementation of infrastructure technologies, prototypes of intelligent systems and applications, smart artifacts for learning and serious games. “Home game” is an innovative augmented table-top educational game that combines tangible interaction with a virtual environment, falling under the category of serious games. The system is structured into a set of mini-games (such as ‘Locate the room’ and ‘Find the wrong object’), which can be personalized for each player in terms of content and interaction paradigm, either automatically based on their profile settings or manually by the educators. Home Game is deployed in the Rehabilitation Centre for Children with Disabilities in Heraklion, Crete, Greece. The full paper will contain a detailed presentation of the User Interface and the learning analytics data that are displayed in each student’s personal dashboards, so as to facilitate educators in adjusting the learning process according the needs of each student. Furthermore, the results of an expert-based evaluation of the tool will be reported.

A fundamental assumption in most contemporary person re-identification research, is that all query persons that need to be re-identified belong to a closed gallery of known persons, i.e., they have been observed and a representation of their appearance is available. For several real-world applications, this closed-world assumption does not hold, as image queries may contain people that the re-identification system has never observed before. In this work, we remove this constraining assumption. To do so, we introduce a novelty detection mechanism that decides whether a person in a query image exists in the gallery. The re-identification of persons existing in the gallery is easily achieved based on the persons representation employed by the novelty detection mechanism. The proposed method operates on a hybrid person descriptor that consists of both supervised (learnt) and unsupervised (hand-crafted) components. A series of experiments on public, state of the art datasets and in comparison with state of the art methods shows that the proposed approach is very accurate in identifying persons that have not been observed before and that this has a positive impact on re-identification accuracy.

The proliferation of Internet of Things (IoT) devices and services and their integration in intelligent environments creates the need for a simple yet effective way of controlling and communicating with them. Towards such a direction, this work presents ParlAmI, a conversational framework featuring a multimodal chatbot that permits users to create simple “if-then” rules to define the behavior of an intelligent environment. ParlAmI delivers a disembodied conversational agent in the form of a messaging application named MAI, and an embodied conversational agent named nAoMI employing the programmable humanoid robot NAO. This paper describes the requirements and architecture of ParlAmI, the infrastructure of the “Intelligent Home” in which ParlAmI is deployed, the characteristics and functionality of both MAI and nAoMI, and finally presents the findings of a user experience evaluation that was conducted with the participation of sixteen users.

This paper explores the general concept of the classroom of the future from a technological perspective, and proposes a set of indicative key facilities that such an environment should incorporate. Over the years, there has been an abundance of related research work aiming to build a “smarter” classroom, initially incorporating distance learning, educational games, and intelligent tutoring systems. More recently, many approaches have revolved around the advancements in the domains of Ambient Intelligence and Internet of Things, resulting in the enhancement of the traditional classroom equipment and furniture with processing power and interaction capabilities (e.g. intelligent desk, smart whiteboard) and the integration of emerging solutions in teaching and learning methods (e.g. AR, VR). The proposed intelligent classroom though is a holistic approach towards a student-centric educational ecosystem, which will incorporate state-of-the-art technologies to support (among others) alternative pedagogies, learning through immersive hands-on experiences and collaboration via flexible class layouts. To that end, this paper reports the various ambient facilities of the classroom and the accompanying software, while a prototype of this environment is currently under development in the AmI Facility of FORTH-ICS.

The selection of clothes and accessories is part of the daily routine of individuals [1]; however, it is not a straightforward process for people with large inventories or limited time, while it is a challenging task for user with disabilities. In the recent past, the Internet-of-Things (IoT) and Ambient Intelligence (AmI) have been enhancing the domestic environment with new connected devices, appliances, and smart furniture, aspiring to assist independent living [2]. Building upon these developments, this work proposes Vesti-AmI; an intelligent wardrobe which, in cooperation with the existing technological infrastructure of the Intelligent Home, aims to assist people in getting ready for their various activities in a context-sensitive, user-friendly and intelligent manner. With respect to the target audience, the facilities of Vesti-AmI are foreseen to accommodate a wide variety of users, including adults, children, elderly people, and people with disabilities. Indicatively, Vesti-AmI permits end-users to: (i) browse clothing items manually or digitally, (ii) preview their choices on a Smart Mirror, (iii) retrieve and store clothing items (semi-)automatically, (iv) get outfit recommendations based on contextual information, and (v) keep their garments odor-, mold-, moisture-, and moth-free with the help of appropriate sensors and actuators that monitor the interior of the wardrobe. Vesti-AmI features a full-height hanging space appropriate for storing clothing like shirts or skirts, but also longer garments such as dresses. An electrically-powered closet rod automatically raises and lowers the clothes so as to bring them closer to the user, while a sophisticated mechanism permits the system to identify each hanging item and present it to the user upon request. The next two compartments contain shelves and drawers in order to provide organized storage solutions for folded clothes and accessories, and a custom-made in-closet steamer that permits users to freshen up their clothes. Sophisticated mechanisms permit the shelves and drawers to move in a vertical fashion (like a carousel), making the stored items easily accessible. Additionally, cameras hidden on the top of each drawer and shelf permit Vesti-AmI to be aware of their contents, while light and sound cues in combination with vibration feedback are employed to assist users (especially blind or visually challenged individuals) to locate the required items inside the wardrobe. In order to maximize time efficiency, an embedded "Smart Mirror" allows users to virtually try their clothes on in an immersive way. Vesti-AmI promotes multimodal interaction that includes touch interaction, air gestures and voice interaction, which can be used complementary to support all users (including those with disabilities). For example, voice interaction can be used by blind or visually challenged users to ask for certain items, while motion-based interaction and gestures can enable users to naturally select the outfit they wish to try on the “Smart Mirror”.

This work concerns the automatic registration of spectral images of paintings upon planar, or approximately planar, surfaces. An approach that capitalizes upon this planarity is proposed, which estimates homography transforms that register the spectral images into an aligned spectral cube. Homography estimation methods are comparatively evaluated for this purpose. A non-linear, robust estimation method that is based on keypoint features is adopted, as the most accurate. A marker-based, quantitative evaluation method is proposed for the measurement of multispectral image registration accuracy and, in turn, utilized for the comparison of the proposed registration method to the state of the art. For the same purpose, characteristic for this application domain, benchmark datasets that are annotated with correctly corresponding points have been compiled and are publicly availed.

ICS-FORTH has recently initiated AmI-Garden, a smart farming project in the framework of its Ambient Intelligence Research Programme. A small experimental IoT greenhouse has been constructed and equipped with polycarbonate cover sheets and all the necessary infrastructure and hardware (automatic window-roof opening/closing, sliding door, fan installation for heating/cooling, vegetable breeding lamps etc.). Inside the greenhouse, a network of wireless sensors is used to measure environmental conditions and parameters, such as air/soil temperature and moisture, sunlight level, soil conductivity, quality and level of chemical ions in irrigation water, etc. The sensors communicate through IoT gateways to the greenhouse’s data centre for storage and post-processing. The system comes with pre-installed agricultural scenarios, a set of activity flows based on environmental conditions that are ideal for each plant species and are monitored in the greenhouse as explained above. The scenarios currently contain parameters to predict common diseases of the plants, as well as unexpected changes in the greenhouse’s microclimate. For example, the irrigation process is built as an agricultural scenario using data from current plant status and past data in order to establish the optimal amount of water to irrigate. The parameters of this scenario are based on specific plant breed and environmental variables. The intelligence behind the scenarios is based on critical limits and thresholds to create cultivation rules. On top of this rule based process, event-driven activation of various automations in the greenhouse is provided, for example, automatic humidity/temperature control, soil fertilisation (hydro fusion) and precise irrigation. Various sets of raw data are produced and ingested into the system, as the life cycle of each one of the plants evolves, in order to be used as the main input for the system’s actuations based on the agricultural treatment scenarios.