Please use this identifier to cite or link to this item: http://hdl.handle.net/10125/50047

Immersive Visualization for Abnormal Detection in Heterogeneous Data for On-site Decision Making

File SizeFormat 
paper0160.pdf9.97 MBAdobe PDFView/Open

Item Summary

Title: Immersive Visualization for Abnormal Detection in Heterogeneous Data for On-site Decision Making
Authors: Mahfoud, Elias
Wegba, Kodzo
Li, Yuemeng
Han, Honglei
Lu, Aidong
Keywords: Interactive Visual Analytics and Visualization for Decision Making � Making Sense of Big Data
Abnormal Detection, Augmented Reality, Immersive Visualization, On-site Decision Making
Issue Date: 03 Jan 2018
Abstract: The latest advances in mixed reality promote new capabilities that allow head-mounted displays, such as Microsoft HoloLens, to visualize various data and information in a real physical environment. While such new features have great potential for new generations of visualization systems, they require fundamentally different visualization and interaction techniques that have not been well explored. This paper presents an immersive visualization approach for investigating abnormal events in heterogeneous, multi-source, and time-series sensor data collections in real-time on the site of the event. Our approach explores the essential components for an analyst to visualize complex data and explore hidden connections in mixed reality; it also combines automatic event detection algorithms to identify suspicious activities. We demonstrate our prototype system by using the developer version of Microsoft HoloLens and presenting case studies that require an analyst to investigate related data on site. We also discuss the limitations of the current infrastructure and potential applications for security visualization.
Pages/Duration: 10 pages
URI/DOI: http://hdl.handle.net/10125/50047
ISBN: 978-0-9981331-1-9
Rights: Attribution-NonCommercial-NoDerivatives 4.0 International
Appears in Collections:Interactive Visual Analytics and Visualization for Decision Making - Making Sense of Big Data


Please contact sspace@hawaii.edu if you need this content in an alternative format.

Items in ScholarSpace are protected by copyright, with all rights reserved, unless otherwise indicated.