Adapting And Integrating A Visual Analytics Process For The University Examination Timetabling Problem

Loading...
Thumbnail Image
Date
2015-05
Authors
John Victor, Joshua Thomas
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
University Examination Timetabling Problem (UETP) is a computationally complex scheduling problem. Visual Analytics (VA) is a modern visualization supported with automated processing method. The major impulse of the method lies in its ability to integrate the key component of scientific visualization and search based heuristics in the same optimization model. This thesis presents a visual analytics process (VAP) adapted for UETP. The adaption involves the human context of visual analytics on timetabling data which are typically processed computationally with local search algorithm and then visualized and interpreted by the user in order to perform problem solving with direct interactions between the primary data, processing and visualization. An integrated problem solving environment (PSE) that analyzes the combined effect of user-driven steering with automatic tuning of algorithmic parameters based on constraints and the criticality of the application for the simulations is proposed. It is important to allow the human timetabler to steer the ongoing simulation, especially in the case of critical clashes between conflicting courses to exams and to time slots. An integrated visual design Examviz which is based on the parallel coordinate’s style of visualization that uses a novel mapping of courses to exams and to time slots has been developed. Examviz has three processing phases which combines human factors and the algorithm to explore conflicting data through visualization particularly to provide incremental improvements over the solution: (i) preprocessing phase (Pre-P); (ii) during the processing phase (Due-P), and (iii) Post processing phase (Pos-P). The proposed framework has been tested on standard dataset of different sizes and complexity. The Examviz achieves optimal solution for the small datasets, and best overall results for the medium and large datasets.
Description
Keywords
Visual Analytics , Timetabling
Citation