Active Ageing

Active ageing can be seen as having a physically, mentally and socially active lifestyle as we age. To address these active ageing determinants, we are developing a socio-technical intervention that facilitates physical activity and social interaction among older people. The intervention contains an online social network for older people and an intelligent system that provides activities recommendation. The system is connected with a robotic friend that supports execution of everyday activities. The aim of the system is to help older people to be more physically active and socially engaged.

Human Computation for Knowledge Maintenance and Evolution

Knowledge bases are usually populated from external data sets, that have been (semi-) automatically imported from their primary sources. Different issues affect data quality in the knowledge base. The data can be incorrect, partially overlapping and inconsistent, or incomplete. Low quality may also result from the data import procedure, such as incorrect or incomplete extraction of objects, incorrect extraction of data types or incorrect links to external resources. All these factors largely influence the quality of the services that can use the knowledge base, such as various visualization, semantic or natural language applications.
Ultimately, humans are needed to create and maintain knowledge bases over time. However, while the metaphor of humans as computing processors is powerful, it is important to understand when this metaphor works, and when it breaks down. Namely, humans have to be motivated to contribute (incentives), their work has to be properly evaluated (trust and reputation), and made efficient and effective (UI and task design). We did the experiments with the word games.

Open Data Visualization

The initiative to make the data freely available opens interesting research topics. By their nature, open data are diverse and not known in advance. To improve the quality of systems that use open data, such as real-time search, exploration and recommendation, we need UIs that successfully capture open data diversity and unpredictability. There is also an issue of aligning the UIs with user preferences and expectations (more general, user experience). In this respect, I was doing research in a technology that provides user-centered open data search, exploration and visualization services.

Humans vs. Machines Challenge

The ESSENCE Challenge is a concrete, real-world problem that captures semantics as a phenomenon that can be represented, used and communicated successfully between humans and machines. The aim of the Challenge is to address this problem within a very specific, yet high-impact, real-world application problem of travel destination retrieval on the Web. It is designed as a guessing game. The task of the participants in a future ESSENCE Challenge competition is to develop an intelligent agent able to successfully play the game autonomously and without human intervention. Specificially, the objective of the Challenge is to produce an agent capable of guessing a destination (the guesser) from increasingly informative hints provided by a human user (the describer). Hints are predefined and prepared in advance. The long-term goal is to build an intelligent computer program that plays the game completely autonomously and that is even able to beat human players.

Adaptive User Interfaces

Building UIs that look and behave according to the context of interaction has always been an interesting research topic. This requires appropriate methods and techniques for formal integration of interaction context elements into UIs development and adaptation processes. I was working on a model-driven architecture for the development of adaptive user interfaces. Based on the architecture, I designed a UML‐based domain specific language for designing adaptive user interfaces. One of the interesting things here is a unified ontology of human factors that can be used for user modeling in Web-based and pervasive systems.

Interactive Visualization

I have been exploring the problem of human factors integration in the design of aircraft cockpit displays, especially in optimizing operator’s workload in manning the unmanned aircraft vehicle (UAV). In this respect, I have designed software architecture for interactive visualization of various UAV data. The architectural design is a contribution that would be useful as a template for future implementations of such systems. Following the architecture, I developed the environment for real-time visualization and interaction with multidimensional set of aircraft data.

Games for Learning

For some time, I was doing research related to the development of games for learning. Here, I proposed a technique for user modeling based on motivational states and types of intelligences.