Eindhoven University of Technology
View profile | Read Abstract
March 13 - 16, 2017
In recent years, retrieval techniques operating on text or semantic annotations, have become the industry standard for retrieval from large data collections, such as documents, images, videos, music, medical data. The aim of this workshop is to explore new methods and interface/system design for interactive data analytics and management in various domains, including specialised text collections (e.g. legal, medical, scientific), multimedia, and bioinformatics, as well as for various tasks, such as semantic information retrieval, conceptual organization and clustering of data collections for sense making, semantic expert profiling, and document/multimedia recommender systems. The primary audience of the workshop are researchers and practitioners in the area of interactive and personalised system design as well as interactive machine learning both from academia and industry.
Brain-computer interfaces (BCIs) hold the promise for being the ultimate intelligent interfaces; what could surpass an interface that is able to interpret your 'thoughts' and preferences, in real time, and behave accordingly? In practice, despite a lot of progress in BCI research in the last 10-15 years, the focus of this field of research has mostly been on allowing paralyzed patients a channel for communication and device control; while this is certainly a major challenge with utmost importance, in this workshop we will try to understand what are the opportunities of BCI for able-bodied users, and specifically how BCI can contribute to or replace existing interaction paradigms. Of particular interest is taking BCI from the laboratory into the real world. It is important to understand BCI in the context of ecologically valid human natural behavior. In parallel, there is growing interest in moving from clinical applications to the general population, but this transition needs to be analyzed in the context of current limitations in BCI accuracy and communication bit rate. Moving out of the lab may post specific new challenges, such as dealing with motion artifacts for mobile BCI.
There is an ongoing trend on embedding computing and communication capabilities into everyday objects, turning them into smart objects. Examples range from smart (tangible) objects over smart cars to even large-scale urban infrastructures. Other recent examples deal with the fabrication of smart objects, smart sensory augmentation and smart spaces. The smart objects workshop will focus on how the intelligence situated in these smart objects can be used to provide more efficient and enjoyable interaction possibilities for the users. The underlying research fields pose unique challenges and opportunities for designing the interaction with such devices.
New technologies are changing the way we learn and teach. Emerging technologies such as social semantic web, cloud computing, and the growing popularity of mobile devices, embedded devices and adaptive context-aware technologies are leading to a paradigm shift in the way educational services are provided towards a “smart learning”. Mobile and smart learning environments allow for accessing and interacting with digital resources in learning systems anytime and anywhere with intelligent, adaptive and appropriate guidance, support, suggestions and customizations. Through technologies and approaches such as ubiquitous learning and adaptive learning, learning becomes adaptable, personalized, flexible, and suitable to meet diverse and rapidly changing technologies, environments and learner needs, while opening unprecedented possibilities for education. The “Intelligent Interfaces for Ubiquitous and Smart Learning” workshop aims to bring together researchers from industry and academia to address the challenges of the intelligent user interfaces and smart learning fields, discuss new ideas and present their research to the scientific community in order to enhance the methodologies and techniques for intelligent learning environments for the 21st century.
Awareness is a key user interface and interaction paradigm. Choosing what to make the user aware of, at what time, and how, has a critical impact on system usage and overall perception. In this workshop, we will bring together those from academia and industry who have researched applications, interfaces, or algorithms incorporating awareness mechanisms or focusing on awareness problems, such as ambient displays, alerting mechanisms, urgency widgets, visualization (& other) dashboards, assisted browsing, information overload, information filtering, and recommender systems. Researchers will have the opportunity to share their positions and experiences with these through 5-minute Ignite-style presentations (of previously submitted 4 page position papers), debate key topics, and brainstorm possible future collaborations in this area.
HUMANIZE 2017 aims to explore the potential of combining theoretical user models with practical mining methods for personalization. When designing user interfaces practitioners rely on knowledge and experience about the interfaces’ intended users and their needs (in the form of a theory-informed model, such as the user's cognitive style or personality) to provide the optimal interface for its users. In contrast to this in content recommendations, a more data-driven approach is taken without the need to have to rely on user knowledge.
Combining these two approaches, model-driven and data-driven, provides an interesting research direction. By relying on knowledge about what types of users require what type of user interface, and by using data mining techniques to infer the formal user models from interaction behavior, interfaces can be personalized in an informed, grounded way. Advances in combining formal user models with data mining can be made in grossly two ways. On the one hand this can be done by identifying formal user models that can be used to base personalization on (such as cognitive style). On the other hand, this can be done by finding ways to infer these user models from data.
The HUMANIZE workshop combines practical data mining methods and theoretical knowledge for personalization, so it provides a venue where researchers from different fields come together to share their thoughts and experiences. In addition, the workshop will allow for an exploration of future opportunities in hopes of identifying possible links between the algorithmic side of behavioral analysis and the theoretical understanding of users for personalization.