HOLOVIEW: Exploring Patient Data in Mixed Reality

Hoppenstedt, Burkhard and Schneider, Christian and Pryss, Rüdiger and Schlee, Winfried and Probst, Thomas and Neff, Patrick and Simoes, Jorge and Treß, Alexander and Reichert, Manfred (2018) HOLOVIEW: Exploring Patient Data in Mixed Reality. In: TRI / TINNET Conference 2018 , Regensburg.

[thumbnail of HoloView.pdf] PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Download (544kB)

Abstract

Over the last years, the TrackYourTinnitus project collected data from worldwide tinnitus patients using smart mobile devices. The gathered data set, in turn, is high-dimensional and it is therefore challenging to visualize it for analyzing purposes. To remedy this drawback, a 3D approach that applies the Microsoft HoloLens is proposed. More specifically, we visualize tinnitus records as a hologram, which is augmented by the real world. The developed prototype particularly tackles three challenges in the context of analyzing the TrackYourTinnitus data set visually. First, the detection of correlations between dimensions is simplified by highlighting the relations between the diagram axes and visually displaying the correlation coefficient. Second, an outlier detection method reveals striking data points and, third, a clustering approach allows for the recognition of related data points. Finally, the performance of the prototype can be controlled by subsampling the data set in order to receive different types of resolutions. Therefore, the prototype is able to handle large data sets.

Item Type: Conference or Workshop Item (Poster)
Subjects: DBIS Research > Publications
Divisions: Faculty of Engineering, Electronics and Computer Science > Institute of Databases and Informations Systems
Faculty of Engineering, Electronics and Computer Science > Institute of Databases and Informations Systems > DBIS Research and Teaching > DBIS Research > Publications
Depositing User: Herr Burkhard Hoppenstedt
Date Deposited: 20 Jun 2018 08:37
Last Modified: 20 Jun 2018 08:37
URI: http://dbis.eprints.uni-ulm.de/id/eprint/1611

Actions (login required)

View Item
View Item