Challenges for Visual Analytics

Abstract

Visual analytics has seen unprecedented growth in its first 5 years of mainstream existence. Great progress has been made in a short time, yet significant challenges must be met in the next decade to provide new technologies that will be widely accepted throughout the world. This article explains some of those challenges in an effort to provide a stimulus for research, both basic and applied, that can realize or even exceed the potential envisioned for visual analytics technologies. We start with a brief summary of the initial challenges, followed by a discussion of the initial driving domains and applications. These are followed by a selection of additional applications and domains that have been a part of recent rapid expansion of visual analytics usage. We then look at the common characteristics of several tools illustrating emerging visual analytics technologies and conclude with the top 10 challenges for the field of study. We encourage feedback and continued participation by members of the research community, the wide array of user communities and private industry.

Persistent challenges in geovisualization – a community perspective

“…There are community-driven traditions/conventions where GeoVis, InfoVis and SciVis differ; however, when we look at the research challenges expressed in these domains, we see a large overlap in the stated research problems (e.g. Chaomei Chen, 2005;Laramee & Kosara, 2006;Munzner, 2009;Thomas & Kielman, 2009). We might think spatial is special (Anselin, 1989), but of course InfoVis and SciVis are also spatial (although often not geographic).…”

Combining Automated and Interactive Visual Analysis of Biomechanical Motion Data

“…The specific datasets driving the framework presented here come from a study at Brown University that made use of marker-based X-ray Reconstruction of Moving Morphology (XROMM) 4 to capture measurements of the lower jaw movements of miniature swine (Sinclair strain) during mastication.…”

“…By leveraging a blended model of learning approaches with interactive visual analysis, we aim to enable a new style of hybrid investigation [4,5]. Using this system, an investigator can utilize automated computational methods to identify hidden temporal patterns embedded within the data while retaining full interactive exploration capabilities to analyze the data either in raw or post-processed form.…”

An Effective Sensor Network for Museum Operations: The Experience of a Pilot Implementation

“…Although analytics tools are rather ad-hoc and customized to specific data sets or needs [5,6], the current research and practices in cloud computing and Web API development provide the common ground for dealing with analysis processing and visualization widgets independently with the flexibility for creating mix-and-match mashup applications to fit different user needs. To ease the integration effort to existing business applications like ERP, there is an opportunity to develop modularized analytics processing and visualization and summarization widgets to deal with large volume of sensor data in the coming years.…”