Interactive Visual Analytics and Visualization for Decision Making
Permanent URI for this collection
Browse
Recent Submissions
Item Visual Data Analysis of Production Quality Data for Aluminum Casting(2021-01-05) Jekic, Nikolina; Mutlu, Belgin; Schreyer, Manuela; Neubert, Steffen; Schreck, TobiasToday’s manufacturing industry is shaped by the Industry 4.0 vision, which is to increase the number of individual goods produced while minimizing the production costs and time. To increase the production outcome and quality, users need to continuously monitor and adjust the entire process. While the recent advances in sensor technology can help users to collect, produce and exchange data, human beings are often overwhelmed by the amount of data being collected. Still, the human visual system is a powerful tool that can be used to decode and process large datasets. To make intelligent use of this ability, we have developed an interactive visual data analysis tool called ADAM that can support production data exploration in the aluminum industry. Furthermore, we demonstrate the effectiveness of our tool using real production data and present insights which could be gained from use of our tool by domain experts.Item Understanding the Role of User Interface for Multi-Criteria Decision-Making in Supporting Exploratory Usage of Information Systems(2021-01-05) Hong, Sungsoo Ray; Kocilenik, Rafal; Aragon, Cecilia; Battersby, Sarah; Kim, JuhoMulti-Criteria Decision-Making (MCDM) is one of the essential tasks people encounter in their everyday use of information systems. In MCDM, people weigh the relative importance of multiple decision criteria to assess decision candidates. Such an MCDM task is ubiquitous yet can be cognitively taxing without the explicit support of user interfaces (UIs). However, there has been a lack of approaches aiming at systemically understanding how the design of UIs can affect users' attitudes and behavior in performing their exploratory use of information systems under MCDM scenarios. To better understand the role of UIs in MCDM, we determine two factors in characterizing UI for MCDM; (1) the internal representation, the way that UI frames end-users in determining preferences of decision criteria (i.e., individual, proportional, and pairwise quantifies), and (2) the external representation, the way that UI externalizes user preferences while the users interact with systems (1D and 2D layouts). We conducted two studies to understand how different design choices affect users' MCDM processes. We found 2D layout improves a set of attitudinal aspects in MCDM scenarios while using different quantifiers introduces a set of trade-offs.Item Towards a Task-based Guidance in Exploratory Visual Analytics(2021-01-05) Mutlu, Belgin; Gashi, Milot; Sabol, VedranExploring large datasets and identifying meaningful information is still an active topic in many application fields. Dealing with large datasets is currently not only a matter of simply collecting and structuring data for retrieval, but sometimes it also requires the provision of adequate means for guiding the user through the exploration process. Visualizations have shown to be an effective method in this context, the reason being that since they are grounded on visual cognition, people understand them and can naturally perform visual operations such as clustering, filtering and comparing quantities. However, systems which help us to create visualizations often require specific knowledge in data analysis, which ordinary users typically do not possess. To address this gap, we propose a system that guides the user in the data analysis process. To achieve this, the system observes current user behavior, tries to infer the task of the user and recommends the next analysis steps to help her to carry out the task.Item PanViz 2.0: Intregating AI into Visual analytics to adapt to the novel challenges of COVID-19(2021-01-05) Snyder, Luke; Reinert, Audrey; Ebert, DavidThe ongoing and evolving COVID-19 pandemic has resulted in tremendous negative effects on people’s daily lives. It is critical for decision makers such as health care officials and governors to foresee potential impacts and make timely decisions. We present PanViz 2.0, a visual analytics application that combines an epidemic model and AI-driven analytics to infer the best-fit parameters to enable the adaptation to ongoing pandemics at multiple spatial aggregations (nation wide, state level, and county level). Our experiments for predicting the fatality cases in each county of the state of Oklahoma demonstrate the flexibility of our application in adapting to various scenarios and regions.Item Multimodal Epidemic Visual Analytics and Modeling(2021-01-05) Jang, Yun; Kim, SeokyeonThe risk of infectious disease increases due to various factors including the dense population, development of various transportations, urbanization, and abnormal weather conditions. Since the speed of epidemic spread is fast, it is necessary to respond quickly in order to prevent the high fatality rate. Therefore, a fast search for the highly accurate spreading model has to be focused on the proper analysis of disease spreading. There have been many studies to understand the disease spreading and the epidemic model is often used to analyze and predict the spread of infectious disease. However, it is limited to apply the epidemic model for the spread analysis because the model captures spreading changes only within the defined area. In this paper, we propose a framework for the disease spreading simulation with multimodal factors in the epidemic model and networks of possible spread routes. Our system provides an interactive simulation environment with the interregional disease spreading according to various spread parameters. Moreover, in order to understand the spreading directions, we extract vector fields over time and visualize the vector fields with the fatality of the disease. Therefore, users are able to understand the disease spreading phenomena and obtain appropriate models through our framework.Item Introduction to the Minitrack on Interactive Visual Analytics and Visualization for Decision Making(2021-01-05) Fisher, Brian; Ebert, David; Gaither, Kelly