publications

2026

1. Modelling Eye Mechanics Using Eye-tracking Glasses and Deep Learning

   Konstantinos Roumpas and Michalis Xenos

   In 2026 4th Cognitive Models and Artificial Intelligence Conference (AICCONF), Apr 2026

   Abs DOI

   Physics-Informed Neural Networks (PINNs) have gathered a lot of attention in the past years, as they have shown promising results in Physics, Chemistry, and other science-related projects. The application of such networks has also been explored in Human-Computer Interaction (HCI), and there is a lot of interest around eye-tracking (ET), as the partial differential equations (PDEs) that describe their movement are simplistic and can be easily applied in a PINN. Past research showed that with wearable ET devices, the PDEs that were described showed better results; however, there was no further study on them. Also, the potential of exploring different types of deep learning neural networks was discussed, although it was not elaborated further. In this work, we aim to apply Graph Neural Networks, Temporal Convolutional Networks, and their PINN-hybrid counterparts to explore if higher accuracy can be achieved in predicting a user’s gaze. The results showcased that the pure PINN is the best solution to tackling this problem, with the other neural networks falling shortly behind it. This is a significant finding for HCI research, as it showcases the most effective method for predicting a user’s gaze using ET data and deep learning, while also providing insight into the mechanics of eye movement itself.

2025

1. Distinguishing Voluntary and Involuntary Blinks Through Eye Openness Metrics

   Konstantinos Roumpas, Dimosthenis Minas, Alberto Calvo-Cordoba, and 1 more author

   In Proceedings of the 3rd International Conference of the ACM Greek SIGCHI Chapter, Sep 2025

   Abs DOI

   Understanding and characterizing blinks can contribute to developing applications in human-computer interaction, fatigue monitoring, and medical diagnosis. This study involved the collection and analysis of eye-tracking data from 44 subjects to monitor voluntary and involuntary blinks. Using eye-openness metrics, our work builds on previous research that uses the same metric to monitor blinks. Blink duration thresholds were obtained from past studies involving eye images and were categorized as voluntary, involuntary, or invalid. In addition, a neural network model was developed and trained to classify blinks as voluntary or involuntary. The model achieved 92% accuracy on the test set, demonstrating the effectiveness of using eye-openness values for this classification task. This open-access dataset and model can provide a solid foundation for further research and applications in automated blink detection and analysis, and the potential creation of interactive systems that take voluntary blinks as input.

2. Bridging the Gap Between Educators and Game-Based Learning: A Study of an AI-Assisted Course Creation Tool for Minecraft Education

   Konstantinos Roumpas and Michalis Xenos

   In 2025 3rd Cognitive Models and Artificial Intelligence Conference (AICCONF), Jun 2025

   Abs DOI

   This paper explores the involvement of artificial intelligence in the context of educational technology. Specifically, it presents findings from a study evaluating CourseCrafter, an AI-enhanced prototype designed to assist to the creation of Minecraft Education courses by educators, regardless of their coding expertise or familiarity with Minecraft’s controls. The study aimed to gather insights on user experiences, interface usability, and the effectiveness of AI integration within the tool. Ten educators, all of whom had some experience with Minecraft Education prior to the experiment, from different geographical areas, teaching grade and subject areas tested the prototype, completed a System Usability Scale (SUS) questionnaire, and attended a semi-structured interview. To ensure a controlled environment throughout the prototype testing, user personas were randomly handed out to participants, they were instructed to follow a detailed scenario, and alternative options would be explained with the Wizard of Oz method. The participants unanimously found the idea useful, agreed on the functionality of certain features, but shared varied concerns about the use of AI in education and the complexity of the platform. Additionally, feedback highlighted the importance of intuitive design, adequate instructional resources, and the potential impact of the tool on teaching and student engagement. These findings emphasize both the need for refinements to enhance user experience and maximize educational effectiveness but also the demand of such a tool in the industry.

3. A comparative study of physics-informed and conventional neural networks for predicting on-screen gaze points from eye-tracking data

   Konstantinos Roumpas, Eleftheria-Lito Michanetzi, Dimosthenis Minas, and 2 more authors

   Expert Systems with Applications, Jul 2025

   Abs DOI

   Physics-Informed Neural Networks (PINNs) take advantage of physical constraints to improve the predictive performance of neural networks. They have demonstrated remarkable success in physics, chemistry, biology, and medicine, sparking interest in their potential applications in other fields, such as Human-Computer Interaction (HCI). Despite their versatility, PINNs are underutilized in certain disciplines due to the challenge of defining Partial Differential Equations (PDEs) that adequately constrain specific problems. This study investigates the application of PINNs to predict fixations captured by an eye-tracking device, employing equations that model head and eye movements. The data for this study were collected during an experiment involving an adaptive user interface for pilots, encompassing a variety of fixation points and rapid glances. The results establish PINNs as a superior method, achieving a mean absolute error (MAE) of 0.61 for horizontal predictions (X) and 0.35 for vertical predictions (Y), significantly outperforming the conventional neural network (NN). Additionally, the PINN demonstrated stronger predictive accuracy for vertical gaze dynamics, as evidenced by an RY2 of 0.91 compared to 0.85 for the NN. These findings underscore the robustness of the PINN approach in modeling gaze points with enhanced precision and reliability. While conventional neural networks perform adequately, the added benefit of physical constraints in PINNs encourages further exploration of their application in non-natural science domains. These promising results point toward the potential of PINNs in creating more adaptive and context-aware systems for various HCI applications.

4. Adaptive Real-Time Translation Assistance Through Eye-Tracking

   Dimosthenis Minas, Eleanna Theodosiou, Konstantinos Roumpas, and 1 more author

   AI, Jan 2025

   Number: 1

   Abs DOI

   This study introduces the Eye-tracking Translation Software (ETS), a system that leverages eye-tracking data and real-time translation to enhance reading flow for non-native language users in complex, technical texts. By measuring the fixation duration, we can detect moments of cognitive load, ETS selectively provides translations, maintaining reading flow and engagement without undermining language learning. The key technological components include a desktop eye-tracker integrated with a custom Python-based application. Through a user-centered design, ETS dynamically adapts to individual reading needs, reducing cognitive strain by offering word-level translations when needed. A study involving 53 participants assessed ETS’s impact on reading speed, fixation duration, and user experience, with findings indicating improved comprehension and reading efficiency. Results demonstrated that gaze-based adaptations significantly improved their reading experience and reduced cognitive load. Participants positively rated ETS’s usability and were noted through preferences for customization, such as pop-up placement and sentence-level translations. Future work will integrate AI-driven adaptations, allowing the system to adjust based on user proficiency and reading behavior. The study contributes to the growing evidence of eye-tracking’s potential in educational and professional applications, offering a flexible, personalized approach to reading assistance that balances language exposure with real-time support.

2024

1. Design of an AI-Assisted Platform that will Facilitate Educators in Creating Minecraft Education Courses

   Konstantinos Roumpas and Michalis Xenos

   In 2024 6th International Workshop on Artificial Intelligence and Education (WAIE), Sep 2024

   Abs DOI

   The potential of Education Technology has reached a point where teachers cannot keep up with the latest trends, nor they can spend the time to get accustomed to innovative technologies that might become obsolete in a few years. With the rise in the popularity of Minecraft Education, an educational platform based on the engine of the world-famous video-game: Minecraft, as well as the benefits of gamification in classrooms for all student ages, it seems that an application that would help teachers create educational video games that are run on Minecraft Education, without any code and with artificial intelligence assistance, could be just the thing that they need to update their teaching techniques. We propose the creation of a platform like that, and we present its potential design, after being consulted by the available research that has been done to this day regarding instructional design, user interface and applications that utilize large language models.