University of Patras
Adaptive and implicit interaction techniques in human-computer interaction
Abstract
dc:descriptionAs digital technology becomes ever more embedded in day-to-day activities, control is moving away from deliberate commands toward systems that infer users’ needs. Although such Adaptive User Interfaces (AUI) promise friction-free interaction, unconstrained automation can compromise predictability, transparency, and trust. To mitigate these risks, this dissertation introduces and formalizes Passive Interaction, a deliberately scoped form of implicit adaptation whose purpose is to keep the current experience consistent in an ongoing task as the user’s physical or affective state drifts. Rather than inferring a person’s high-level intentions, a passive system makes unobtrusive adjustments to maintain perceptual stability as a user’s physical or mental state naturally changes. The dissertation is organized around three interconnected strands. First, it defines Passive Interaction and presents two working prototypes that run on commodity hardware: an adaptive-font web reader for mobile devices that resizes text according to viewing distance and scores highly on usability metrics; and an emotion-aware video game that adjusts game elements to match player affect and is rated on par with commercial titles. Second, it explores eye-tracking as a richer implicit signal. A study with UAV pilots shows how gaze-responsive cockpits could ease cognitive load, while a lecture-slide summarizer personalizes study materials by tracking what learners actually read. Third, a series of foundational studies reveals how objective performance can diverge from subjective preference, how user background and context shape satisfaction, and uncovers robust behavioral patterns, such as block-wise reading, that can inform future adaptive interfaces. Together, these strands contribute a design framework that reconciles adaptive assistance with predictability; provide empirical evidence that subtle, on-device corrections can be delivered with commodity cameras; and yield actionable insights into how user diversity shapes interface preference, ultimately guiding the design of more effective and trustworthy adaptive systems.
Degree
thesis:*- Grantor dc:publisher
- University of Patras
- Year dc:date
- 2025
Author and committee
dc:creator, dc:contributor.*- Authors dc:creator
-
- Mallas, Andreas
- Μαλλάς, Ανδρέας
Subjects
dc:subject × 26- Αλληλεπίδραση ανθρώπου-υπολογιστή
- Προσαρμοστικές διεπαφές χρήστη
- Έμμεση αλληλεπίδραση
- Παθητική αλληλεπίδραση
- Επίγνωση πλαισίου
- Ιχνηλάτηση του βλέμματος
- Συναισθηματική υπολογιστική
- Οπτική προσοχή
- Αξιολόγηση χρηστικότητας
- Αναγνώριση συναισθημάτων προσώπου
- Human-computer interaction
- Adaptive user interfaces
- Implicit interaction
- Passive interaction
- Context-awareness
- Affective computing
- Visual attention
- Eye-tracking
- Usability evaluation
- Facial emotion recognition
- Επιστήμη Ηλεκτρολόγου Μηχανικού, Ηλεκτρονικού Μηχανικού, Μηχανικού Η/Υ
- Επιστήμες Μηχανικού και Τεχνολογία
- Υπολογιστές, Υλικό (hardware) και Αρχιτεκτονική
- Electrical Engineering, Electronic Engineering, Information Engineering
- Engineering and Technology
- Computer science, Hardware and Architecture
Rights
- Language dc:language
- eng
Identifiers
dc:identifier.*- Handle dc:identifier
- http://hdl.handle.net/10442/hedi/61155