Your browser does not support JavaScript!

Home    Collections    Type of Work    Post-graduate theses  

Post-graduate theses

Current Record: 19 of 5441

Back to Results Previous page
Next page
Add to Basket
[Add to Basket]
Identifier 000443513
Title Real-time optimization of Context-Aware Adaptive User Interfaces, for Enhanced Situational Awarenes
Alternative Title Βελτιστοποίηση, σε πραγματικό χρόνο, Προσαρμοστικών Διεπαφών Χρήστη που λαμβάνουν υπόψιν το Πλαίσιο Χρήσης, για επαυξημένη Επίγνωση της Κατάστασης
Author Στεφανίδη, Ζηνοβία Κ.
Thesis advisor Παπαγιαννάκης, Γεώργιος
Reviewer Τσακαλίδης, Παναγιώτης
Ζαμπούλης, Ξενοφών
Abstract User Interfaces (UIs) constitute the prominent means for interacting with computing systems and applications. Designing suitable, user-friendly UIs poses a multitude of challenges, given the heterogeneity of potential users and contexts of use. This variability cannot be handled by a onesize-fits-all approach, but needs to be addressed by adapting the UI so that it is tailored to the current user and context. Existing approaches are mainly focused on design-time or one-off adaptation of the UI at startup, as opposed to real-time continuous adaptation based on the current situation. However, UIs are nowadays increasingly being used in continuously changing contexts, such as in mobile and Extended Reality (XR) applications, calling for more dynamic approaches. The majority of research approaches regarding adaptive Graphical User Interfaces (GUIs) is primarily concerned with the development of handcrafted rule sets and heuristics. Albeit in recent years, Combinatorial Optimization has emerged as a powerful and flexible tool for the computational generation and adaptation of GUIs, providing a coherent formalism for expressing and analyzing design decisions. In general, this method treats interface adaptation and generation as an optimization problem, by defining constraints and maximizing (or minimizing) an objective function that represents the goal of the UI, for instance, maximizing the interface’s usability, or minimizing user effort. However, in existing approaches, the parameters of the optimization problem are manually specified or static, and do not reflect run-time changes in the current context of use. In addition, different types of design problems in a given UI, such as the selection of its GUI components and its layout, are solved separately and independently. A key UI design consideration in many application domains, such as healthcare, aviation and the military, is Situational Awareness (SA), playing a major role in risk management and safety. It refers to the human perception and understanding of the environment and the current situation, as well as the human ability to predict how they will evolve. In this work, a novel computational approach for the dynamic adaptation of UIs is proposed, which aims at enhancing the SA of users by leveraging the current context and providing the most useful information, in an optimal and efficient manner. By combining Ontology modeling and reasoning with Combinatorial Optimization, the system decides what information to present, when to present it, where to visualize it in the display - and how, taking into consideration contextual factors as well as placement constraints. The main objective of the proposed approach is to optimize the SA associated with the displayed UI at run-time, while avoiding information overload and induced stress. In this respect, contrary to existing approaches, parameters of the optimization problem are dynamically inferred, based on the current situation. Additionally, the design problems of GUI component selection and UI layout are solved simultaneously, exploiting interrelationships. Our proposed methodology is general-purpose, applicable to different platforms and domains, including desktop, mobile and XR applications, for a variety of potential end-users. In the context of this work, we have deployed our computational approach to the use case of an Augmented Reality (AR) system for Law Enforcement Agents (LEAs). In order to extract user requirements and model our application domain, co-creation workshops with end-users have been organized, gaining insights into context factors that impact the SA of LEAs, and identifying GUI components that would increase their SA during policing in different tasks and contexts. To explore the benefits and limitations of the developed system, two evaluations have been conducted. The first one was an expert-based evaluation with LEAs and User Experience (UX) experts, assessing the appropriateness of the system’s decisions. The second one was a user-based evaluation involving LEAs from different agencies, estimating the SA, the mental workload and the overall UX associated with the system, through an AR simulation. The results indicate that the system improves the observed and perceived user SA, by 9.25% and 25.63% respectively.
Language English
Issue date 2021-11-26
Collection   School/Department--School of Sciences and Engineering--Department of Computer Science--Post-graduate theses
  Type of Work--Post-graduate theses
Permanent Link Bookmark and Share
Views 5

Digital Documents
No preview available

No permission to view document.
It won't be available until: 2022-11-26