Colloquium Cognitive Systems

Behaviour-Aware User Interfaces

Dr. Daniel Buschek (LMU Munich)

 

Abstract. I introduce the concept of behaviour-aware user interfaces, which improve interaction by assessing and taking into account *how* the user performs interactions with a system. In particular, they do so by addressing or exploiting variability in user behaviour. The fundamental hypothesis is that we can advance Human-Computer-Interaction not only by investigating new interaction techniques and devices, but also by utilising more of the information that is already contained in input actions.
This talk first presents an overview of my work on mobile touch devices, demonstrating the value of behaviour-aware user interfaces in three application areas: 1) Enhancing input - by modelling users' touch behaviour to increase accuracy and adapt to constraints. 2) Facilitating privacy and security - by observing behaviour patterns to implicitly verify user identity or detect user changes. 3) Increasing expressiveness - by enabling interfaces to pass on behaviour variability from input to output space.
This overview is complemented by a methodological reflection and an outlook on further projects that utilise user behaviour details and context information.  

Bio. Daniel Buschek is a post doctoral researcher at the University of Munich  (LMU). He is interested in innovating interaction at the intersection of Human-Computer-Interaction and Machine Learning / AI. This includes in particular leveraging user- and context-specific human behaviour patterns to create secure, personalised, and expressive interactions with understandable intelligent systems. He received his PHD from the University of Munich in 2018. His studies included research projects at Siemens AG Munich, the University of Glasgow, and the Helsinki Institute for Information Technology (HIIT). His work has been published at venues such as CHI, MobileHCI, IUI, TOCHI and IMWUT/Ubicomp, including two Best Paper Honourable Mention Awards at CHI and MobileHCI.