11/08/2026
The following eXtended Reality (XR) or food research papers from our department were presented in AHFE conference in Istanbul, Turkey, 20-24 July 2026. Taneli Nyyssönen conducted usability testing of Virtual Reality tool for visualizing indoor smoke propagation and extraction visualization, Xiaoran Han's paper examines the real-world use of Mixed Reality technology in distance theatre education, Shyam Bhetuwal's paper studies the problem of mapping heterogeneous AI-generated food component names in a real-world restaurant setting, and Rehan Khalil's paper evaluates the deployment of an AI- and IoT-based food recognition and weighing system in a hospital ward.
Taneli Nyyssönen conducted the usability study within Jussi Haapasaari's paper that investigates whether immersive VR improves the perception of smoke behavior in complex environments and supports the verification and validation of smoke-extraction system designs.
Participants of varying levels of experience in VR and smoke-extraction system design attended the usability testings. User interaction data, task completion metrics, observations, and post-study questionnaires were collected to assess usability, learnability, and perceived usefulness.
The results indicate that VR enables clearer perception of smoke movement, airflow direction, and temperature distribution, and supports exploratory interaction with simulation data.
https://doi.org/10.54941/ahfe1007534
Xiaoran Han's paper explores how MR reshapes pedagogical effectiveness, perceived presence, and teacher–student experience in distance theatre education. While many domains benefit from remote on-screen teaching, it diminishes the 3D presence fundamental to teaching performing arts. MR technology enables the wearer to observe and interact with a remote person or object as a 3D hologram in their own real space, opening revolutionary possibilities.
The qualitative study took MR technology into a concrete pedagogical context, providing valuable insights into the affordances, limitations, and design implications of MR systems for embodied distance learning. The data collected from audio–video recordings, semi-structured post-session interviews, and post-course written reflections were analysed using Braun and Clarke’s six-step thematic analysis.
The findings demonstrate that MR can meaningfully reconstruct aspects of presence and physicality in distance performance arts education, yet they also reveal notable limitations in sensory and non-verbal communication.
https://doi.org/10.54941/ahfe1007522
Adequate dietary intake is essential for positive clinical outcomes of hospitalized patients, yet monitoring food intake is labor-intensive and often subjective. Rehan Khalil's study evaluates FlavoriaFlex, an AI-powered food recognition system, to assess its detection performance, deployment feasibility, and acceptability among dietitians.
The study examined the capability of FlavoriaFlex system's automatic food detection and name mapping, the feasibility of deploying and integrating the system in a hospital to estimate food and nutrient intake, and what benefits and limitations dietitians see in FlavoriaFlex compared to current monitoring systems.
The study demonstrates that the FlavoriaFlex system could be effectively integrated into hospital workflows. The nutritionists reported meaningful benefits, such as reduced cognitive burden, improved objectivity, and actionable insights into consumption patterns.
https://doi.org/10.54941/ahfe1007465
In food informatics, dietary assessment systems, and data-driven public health research, accurate harmonization of food names across heterogeneous and multilingual datasets remains a major challenge. Shyam Bhetuwal's study evaluates practical methods for mapping AI-generated food component names to Finnish menu-based ground truth in a real-world restaurant setting.
The work was implemented within the Flavoria Flex platform, integrating hardware, software, and AI-based components (LogMeal, FoodSAM, OpenAI) into an end-to-end pipeline enabling automated food recognition, menu-aware correction, and nutritional analysis. Food-name mapping performance was evaluated on the 167 multi-component meal images. Mapping quality was measured against the Finnish lunch-line ground-truth component labels.
The findings suggest that menu-aware, segment-level mapping is a practical and scalable foundation for improving food-name standardization in dietary monitoring and menu analytics systems.
https://doi.org/10.54941/ahfe1007316
