Davy Vanacken

Prof. Dr. Davy Vanacken

Hasselt University, Hasselt, Flanders, Belgium
orcid

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 August 2015
Verified
Book Chapter
Open access
PDF file
GRGustavo Rovelo
Gustavo Rovelo
DDDonald Degraen
Donald Degraen
DVDavy Vanacken
Davy Vanacken
KLKris Luyten
Kris Luyten
KCKarin Coninx
Karin Coninx
We present Gestu-Wan, an intelligible gesture guidance system designed to support mid-air gesture-based interaction for walk-up-and-use displays. Although gesture-based interfaces have become more prevalent, there is currently very little uniformity with regard to gesture sets and the way gestures can be executed. This leads to confusion, bad user experiences and users who rather avoid than engage in interaction using mid-air gesturing. Our approach improves the visibility of gesture-based interfaces and facilitates execution of mid-air gestures without prior training. We compare Gestu-Wan with a static gesture guide, which shows that it can help users with both performing complex gestures as well as understanding how the gesture recognizer works.

27 June 2025 in Proceedings of the ACM on Human-Computer Interaction
Verified
Journal Article
Open access
SVSebe Vanbrabant
Sebe Vanbrabant
GEGilles Eerlings
Gilles Eerlings
GRGustavo Rovelo
Gustavo Rovelo
DVDavy Vanacken
Davy Vanacken
This paper introduces ECHO, an LLM-powered system framework to explore and interrogate the internals of AI models through tool-augmented language models. While traditional XAI methods typically offer a small and technical set of explanation types, ECHO advances the accessibility and usability of AI explanations through a conversational approach, combining LLMs with a collection of tools and a human-in-the-loop process. We identify various explanation types from the literature, for which we create a set of predefined tools for tabular data. Using a modular architecture, ECHO integrates these predefined tools with dynamically generated tools to interact with AI models, facilitating tailored explanations for a large variety of user queries. This paper details ECHO’s design, implementation, and use cases, demonstrating its capabilities in the context of a movie recommender, healthcare decision tree and neural network for educational classification.



Verified
Journal Article
Open access
PDF file
BDBram van Deurzen
Bram van Deurzen
GRGustavo Rovelo
Gustavo Rovelo
DBDaniël Bot
Daniël Bot
DVDavy Vanacken
Davy Vanacken
KLKris Luyten
Kris Luyten
Buttons are everywhere and are one of the most common interaction elements in both physical and digital interfaces. While virtual buttons offer versatility, enhancing them with realistic haptic feedback is challenging. Achieving this requires a comprehensive understanding of the tactile perception of physical buttons and their transferability to virtual counterparts. This research investigates tactile perception concerning button attributes such as shape, size, and roundness and their potential generalization across diverse button types. In our study, participants interacted with each of the 36 buttons in our search space and provided a response to which one they thought they were touching. The findings were used to establish six substitute buttons capable of effectively emulating tactile experiences across various buttons. In a second study, these substitute buttons were validated against virtual buttons in VR. Highlighting the potential use of the substitute buttons as haptic proxies for applications such as encountered-type haptics.

1 January 2006
Verified
Conference Paper
Closed access
DVDavy Vanacken
Davy Vanacken
JBJoan De Boeck
Joan De Boeck
CRChris Raymaekers
Chris Raymaekers
KCKarin Coninx
Karin Coninx