Interactive Visual Analytics and Visualization for Decision Making – Making Sense of a Growing Digital World
Permanent URI for this collection
Browse
Recent Submissions
Item Towards a Theory of Analytical Behaviour: A Model of Decision-Making in Visual Analytics(2019-01-08) Booth, Paul; Gibbins, Nicholas; Galanis, SpyrosThis paper introduces a descriptive model of the human-computer processes that lead to decision-making in visual analytics. A survey of nine models from the visual analytics and HCI literature are presented to account for different perspectives such as sense-making, reasoning, and low-level human-computer interactions. The survey examines the people and computers (entities) presented in the models, the divisions of labour between entities (both physical and role-based), the behaviour of both people and machines as constrained by their roles and agency, and finally the elements and processes which define the flow of data both within and between entities. The survey informs the identification of four observations that characterise analytical behaviour - defined as decision-making facilitated by visual analytics: bilateral discourse, divisions of labour, mixed-synchronicity information flows, and bounded behaviour. Based on these principles, a descriptive model is presented as a contribution towards a theory of analytical behaviour. The future intention is to apply prospect theory, a economic model of decision-making under uncertainty, to the study of analytical behaviour. It is our assertion that to apply prospect theory first requires a descriptive model of the processes that facilitate decision-making in visual analytics. We conclude it necessary to measure the perception of risk in future work in order to apply prospect theory to the study of analytical behaviour using our proposed model.Item Design Spaces in Visual Analytics Based on Goals: Analytical Behaviour, Exploratory Investigation, Information Design & Perceptual Tasks(2019-01-08) Booth, Paul; Gibbins, Nicholas; Galanis, SpyrosThis paper considers a number of perspectives on design spaces in visual analytics and proposes a new set of four design spaces, based on user goals. Three of the user goals are derived from the literature and are categorised under the terms exploratory investigation, perceptual tasks, and information design. The fourth goal is categorised as analytical behaviour; a recently defined term referring to the study of decision-making facilitated by visual analytics. This paper contributes to the literature on decision-making in visual analytics with a survey of real-world applications within the analytical behaviour design space and by providing a new perspective on design spaces. Central to our analysis is the introduction of decision concepts and theories from economics into a visual analytics context. Given the recent interest in decision-making we wanted to understand the emerging topic of analytical behaviour as a design space and found it necessary to look at more than just decision-making to make a valuable contribution. The result is an initial framework suitable for use in the analysis or design of analytical behaviour applications.Item Toward Technology Transfer Evaluation Criteria(2019-01-08) KASIK, DAVID; Dill, JohnTechnology transfer is often focused on how to get novel technology transferred into an industrial using group or company. We focus in this paper on the target of the process and present guidelines which can help assess the likelihood of a successful transfer.Item BlueCollar: Optimizing Worker Paths on Factory Shop Floors with Visual Analytics(2019-01-08) Herr, Dominik; Grund, Sebastian; Ertl, ThomasThe optimization of a factory's productivity regarding quality and efficiency is an important task in the manufacturing domain. To optimize the productivity, production lines are optimized to have short transportation paths and short processing times at the stations that process intermediate components or the final product. A factory's layout is a key factor in this optimization aspect. This optimization mostly comprises the machine tools' positions with respect to places where supply goods are being delivered and other tools are stationed, often neglecting the paths that workers need to take at the shop floor. This impairs a factory's productivity, as machines may need to wait for workers, who operated another machine and are still on the way due to the long distance between the machines. In this work, we present BlueCollar, a visual analytics approach that supports layout planners to explore and optimize existing factory layouts regarding the paths taken by workers. Planners can visually inspect the paths that workers need to take based on their work schedule and the factory's layout. An estimation of distribution algorithm supports them in choosing which layout elements, e.g., shared tool caches, to relocate. Its intermediate and final results are used to provide visual cues for suitable relocation areas, and to suggest new layouts automatically. We demonstrate our approach through an application scenario based on a realistic prototype layout provided by an external company.Item Visual Interactive Comparison of Part-of-Speech Models for Domain Adaptation(2019-01-08) John, Markus; Heimerl, Florian; Sudra, Constanze; Ertl, ThomasItem Human Interpretation of Trade-Off Diagrams in Multi-Objective Problems: Implications for Developing Interactive Decision Support Systems(2019-01-08) Oprean, Danielle; Spence, Caitlin; Simpson, Mark; Miller Jr, Randy; Bansal, Saurabh; Keller, Klaus; Klippel, AlexanderThe growing need for efficient and effective human decision-makers warrants a better understanding of how decision support systems (DSS) guide users to improved decisions. Decision support approaches utilize visual aids to assist decision-making, including trade-off diagrams. These visualizations help comprehension of key trade-offs among decision alternatives. However, little is known about the role of trade-off diagrams in human decision-making and the best way to present them. Here, we discuss an empirical study with two goals: 1) evaluating DSS interactivity and 2) identifying decision-making strategies with trade-off diagrams. We specifically investigate the value of interface interactivity and problem context as users make nine increasingly complex decisions. Our results suggest that problem context and interactivity separately influence ability to navigate trade-off diagrams.Item Introduction to the Minitrack on Interactive Visual Analytics and Visualization for Decision Making – Making Sense of a Growing Digital World(2019-01-08) Ebert, David; Fisher, Brian; Gaither, Kelly