Arbeitsgruppe
Datenanalyse und Visualisierung

Login |
 
 

Dr. Halldór Janetzko

Mitarbeiter

E-Mail: Halldor.Janetzko(at)uni-konstanz.de
Telefon: +49 (0)7531 88-4793
Fax: +49 (0)7531 88-3268
Raum: D 339
Adresse: Universität Konstanz
Fachbereich Informatik und Informationswissenschaft
Box 78
78457 Konstanz, Germany

Research Work

The amount of captured and stored geospatial movement data increased rapidly over the last years. Nowadays, nearly all smartphones have the capabilities to track their users via GPS. Even without GPS enabled, mobile phones can be roughly localized by the surrounding WLAN access points or by the radio cell they are logged in. Furthermore, there exist tracking services like Google Latitude not only allowing tracking of mobile phones, but also providing simple analyses, like the whereabouts of a person, differentiated in the classes home, work, and others.

Besides the large collection of human-generated data, ecological biology is a research area highly influenced by the substantial progress in tracking technology. Ecological biologists are interested in the behavior of animals in order to understand the impacts of man-made changes to habitats to the behavioral patterns of animals. Biologists capture animals in the wild and attach a GPS logging device, which is today typically capable of storing more than just positions, like body temperature or even heart rate values.

Both data sources have common properties making the analysis interesting from a research point of view. As time and location are independent variables of many phenomena (e.g., weather, obstacles, etc.) both allow a join with other data sources building a collection of possible influence factors. Furthermore, the possibly high temporal and spatial resolution makes storing, retrieving, analyzing, and visualizing of geographical movement data challenging.

Challenge

As mentioned above, the integration of external data sources is an important step to get a deeper understanding of animal's behavior. Visualizing these additional attributes along the movement trajectories is a very challenging task as occlusions might hide interesting patterns. Interesting is typically a pattern, which is local (or reoccurring) in time or space. These patterns may be local correlations or just skewed distributions. Interaction techniques like Brushing & Linking do help analyzing but do not offer insights at a glance.

Besides, visualizing the original movement trajectory comes along with challenging problems. Often, there is much overplotting induced by self-crossings of movement trails and revisits of places. Line representations of trajectories suffer from these problems even more than point-based representations as lines occupy more pixels in screen space. The overplotting problem complicates and weakens colored trajectory representations visualizing additional attributes directly along the track. Consequently, methods dealing with overplotting have to be developed.

Research Approach

Basically, Jacques Bertin differentiates in 1974 three different geospatial phenomena, namely point, line, and area phenomena, which have to be dealt with differently. As there exist two equal reasonable approaches to visually represent movement data, we develop techniques for both visualizing movement data as points and lines. Furthermore, there are geospatial datasets containing information about events with spatial extension demanding for area-based visual representations. We will discuss the different information visualization techniques in the following subsections.

Scatterplot of U.S. census data without any overplotting using a pixel placement algorithm based on local correlations. For better distinction of nearby density regions shading techniques have been applied.

Figure 1: Scatterplot of U.S. census data without any overplotting using a pixel placement algorithm based on local correlations. For better distinction of nearby density regions shading techniques have been applied.

Visualizing geospatial movement data by points is just an application for scatterplots. Scatterplots have the advantage being well-known and used often for visual analysis tasks, but at the same time have the problem of overplotting points in dense areas. We deal with this problem by moving overplotting points to the next free position in a meaningful manner.
Figure 1 shows the result of our technique applied to a U.S. census data set. We first compute local correlations and use the correlation to determine the shape of the pixel placement. More in detail, we move overplotting points in an ellipsoid manner to the next free position, while the ellipse is determined by the direction and the strength of the correlation. In order to allow a distinction of nearby density clusters, we apply a lighting model to illuminate the scatterplot like a heightmap. Our next steps will be to develop a pixel placement algorithm using the density distribution of the underlying data. This approach will perform an arbitrarily shaped pixel placement.

One of the most often used visual representation for movement data is a line-based visualization. But using lines comes with the disadvantage that lines use more screen space than just points. Especially in high density regions like the black highlighted region in Figure 2 movement patterns may be occluded due to overplotting reasons.

Figure 2: Original (left) and simplified (right) line-based representation of the same trajectory. The global movement pattern is better visible in the simplified trajectory, especially in the red highlighted area.

We introduced a density-based simplification approach tackling this issue and trying to reduce the amount of visual clutter. As it can be seen in Figure 2 we especially reduce the amount of overplotting in dense regions like the red bordered regions revealing obscured movement patterns.

Curriculum Vitae

Since 2015 Postdoctorate Researcher in the Data Analysis and Visualization Group
Sep - Oct 2012 Research internship at the group for Business Intelligence, Hewlett-Packard Laboratories, Palo Alto, CA, USA
Sep - Oct 2011 Research internship at the group for Business Intelligence, Hewlett-Packard Laboratories, Palo Alto, CA, USA
2010 - 2015

PhD student and research associate in the Data Analysis and Visualisation group of Prof. Dr. Daniel Keim

PhD thesis: "Enhancements for Visualizing Temporal and Geospatial Datasets"

2008 - 2010 Master of Science in Information Engineering from the Department of Computer Science, University of Konstanz, Germany
2005 - 2008 Bachelor of Science in Information Engineering from the Department of Computer Science, University of Konstanz, Germany

Teaching

Summer Term 2016 Lecture: Geographic Information Systems
Winter Term 2015/16 Lecture: Development of High Resolution Applications for the Powerwall
Summer Term 2015 Lecture: Geographic Information Systems
Summer Term 2014 Exercise: Geographic Information Systems
Summer Term 2013 Exercise: Geographic Information Systems
Winter Term 2012/13 Exercise: Computational Methods for Document Analysis
Summer Term 2012    Exercise: Geographic Information Systems
Winter Term 2011/12 Exercise: Scripting Languages and Tools
Summer Term 2011    Exercise: Geographic Information Systems
Winter Term 2010/11  Exercise: Data Analysis & Visualization

Publications

Publications
2016
M. Stein, H. Janetzko, T. Breitkreutz, D. Seebacher, T. Schreck, M. Grossniklaus, I. Couzin and D. A. Keim.
Director's Cut: Analysis and Annotation of Soccer Matches.
IEEE Computer Graphics and Applications (CG&A), to appear, 2016.
Download BibTeX filePublication details
D. Seebacher, M. Stein, H. Janetzko and D. A. Keim.
Patent Retrieval: A Multi-Modal Visual Analytics Approach.
EuroVis Workshop on Visual Analytics (EuroVA), The Eurographics Association, pages 013-017, DOI: 10.2312/eurova.20161118, 2016.
Download BibTeX filePublication details
H. Janetzko, M. Stein, D. Sacha and T. Schreck.
Enhancing Parallel Coordinates: Statistical Visualizations for Analyzing Soccer Data.
IS&T Electronic Imaging Conference on Visualization and Data Analysis, 2016.
Download BibTeX filePublication details
2015
M. Stein, J. Häußler, D. Jäckle, H. Janetzko, T. Schreck and D. A. Keim.
Visual Soccer Analytics: Understanding the Characteristics of Collective Team Movement Based on Feature-Driven Analysis and Abstraction.
ISPRS International Journal of Geo-Information, Special Issue Advances in Spatio-Temporal Data Analysis and Mining , DOI: 10.3390/ijgi4042159, 2015.
Download BibTeX filePublication details
J. Buchmüller, H. Janetzko, G. Andrienko, N. Andrienko, G. Fuchs and D. A. Keim.
Visual Analytics for Exploring Local Impact of Air Traffic.
Eurographics Conference on Visualization (EuroVis 2015), DOI: 10.1111/cgf.12630, 2015.
Download BibTeX filePublication details
K. Vrotsou, H. Janetzko, C. Navarra, G. Fuchs, D. Spretke, F. Mansmann, N. Andrienko and G. Andrienko.
SimpliFly: A Methodology for Simplification and Thematic Enhancement of Trajectories.
IEEE Transactions on Visualization and Computer Graphics, 21(1):107-121, DOI: 10.1109/TVCG.2014.2337333, 2015.
Download BibTeX filePublication details
2014
H. Janetzko, D. Jäckle and T. Schreck.
Geo-Temporal Visual Analysis of Customer Feedback Data Based on Self-Organizing Sentiment Maps.
International Journal On Advances in Intelligent Systems, International Academy, Research, and Industry Association (IARIA), 7(1 and 2):237--246, 2014.
Download BibTeX filePublication details
H. Janetzko, D. Sacha, M. Stein, T. Schreck, D. A. Keim and O. Deussen.
Feature-Driven Visual Analytics of Soccer Data.
Proceedings of the 2014 IEEE Symposium on Visual Analytics Science and Technology (VAST '14), DOI: 10.1109/VAST.2014.7042477, 2014.
Download BibTeX filePublication details
H. Janetzko, D. Jäckle, O. Deussen and D. A. Keim.
Visual Abstraction of Complex Motion Patterns.
SPIE 2014 Conference on Visualization and Data Analysis (VDA 2014), Best Paper Award, IS&T/SPIE, pages 90170J-0-90170J-12, 2014.
Download BibTeX filePublication details
H. Janetzko, F. Stoffel, S. Mittelstädt and D. A. Keim.
Anomaly Detection for Visual Analytics of Power Consumption Data.
Computer & Graphics, Elsevier, 38(0):27-37, DOI: 10.1016/j.cag.2013.10.006, 2014.
Download BibTeX filePublication details
2013
H. Janetzko, D. Jäckle and T. Schreck.
Comparative visual analysis of large customer feedback based on self-organizing sentiment maps.
Proc. International Conference on Advances in Information Mining and Management, Best Paper Award, 2013.
Download BibTeX filePublication details
M. C. Hao, C. Rohrdantz, H. Janetzko, D. A. Keim, U. Dayal, L.-E. Haug, M. Hsu and F. Stoffel.
Visual sentiment analysis of customer feedback streams using geo-temporal term associations.
Information Visualization, SAGE Publications, 12(3-4):273-290, DOI: 10.1177/1473871613481691, 2013.
Download BibTeX filePublication details
H. Janetzko, M. C. Hao, S. Mittelstädt, U. Dayal and D. A. Keim.
Enhancing Scatter Plots Using Ellipsoid Pixel Placement and Shading.
Proceedings of the 46th Annual Hawaii International Conference on System Sciences, IEEE Computer Society, pages 1522-1531, DOI: 10.1109/HICSS.2013.197, 2013.
Download BibTeX filePublication details
M. C. Hao, M. Marwah, S. Mittelstädt, H. Janetzko, M. Hund, D. A. Keim, U. Dayal, C. Bash, C. Felix, C. Patel and M. Hsu.
Visual analytics of cyber physical data streams using spatio-temporal radial pixel visualization.
In Proceedings of Visualization and Data Analysis, 8654():865404--865412, DOI: 10.1117/12.2002948, 2013.
Download BibTeX filePublication details
2012
M. C. Hao, M. Marwah, S. Mittelstädt, H. Janetzko, D. A. Keim, U. Dayal, C. Bash, C. Felix, C. Patel and M. Hsu.
Exploring Cyber Physical Data Streams Using Radial Pixel Visualizations.
Proc. IEEE Symposium on Visual Analytics Science and Technology (Poster Paper), Honorable Mention Award, DOI: 10.1109/VAST.2012.6400541, 2012.
Download BibTeX filePublication details
F. Mansmann, D. Spretke, H. Janetzko, B. Kranstauber and K. Safi.
Correlation-based Arrangement of Time Series for Movement Analysis in Behavioural Ecology.
Progress on Movement Analysis Workshop, Zurich, Switzerland, November 15-16, 2012.
Download BibTeX filePublication details
M. C. Hao, M. Marwah, H. Janetzko, U. Dayal, D. A. Keim, D. Patnaik, N. Ramakrishnan and R. K. Sharma.
Visual exploration of frequent patterns in multivariate time series.
Information Visualization (IVS), Palgrave Macmillan, 11(1):71--83, DOI: 10.1177/1473871611430769, 2012.
Download BibTeX filePublication details
F. Stoffel, H. Janetzko and F. Mansmann.
Proportions in Categorical and Geographic Data: Visualizing the Results of Political Elections.
Proceedings of the AVI 2012, May 21 - 25, Capri Island (Naples), Italy, ACM Press, DOI: 10.1145/2254556.2254644, 2012.
Download BibTeX filecm submissionPublication details
M. C. Hao, C. Rohrdantz, H. Janetzko, D. A. Keim, U. Dayal, L.-E. Haug and M. Hsu.
Integrating Sentiment Analysis and Term Associations with Geo-Temporal Visualizations on Customer Feedback Streams.
SPIE 2012 Conference on Visualization and Data Analysis (VDA 2012), Best Paper Award, DOI: https://dx.doi.org/10.1117/12.912202, 2012.
Download BibTeX filePublication details
2011
D. Spretke, H. Janetzko, F. Mansmann, P. Bak, B. Kranstauber, S. Davidson and M. Mueller.
Exploration through Enrichment: A Visual Analytics Approach for Animal Movement.
Proceedings of the 19th SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM, pages 421--424, 2011.
Download BibTeX filePublication details
D. Oelke, H. Janetzko, S. Simon, K. Neuhaus and D. A. Keim.
Visual Boosting in Pixel-based Visualizations.
Computer Graphics Forum, 30(3):871-880, DOI: 10.1111/j.1467-8659.2011.01936.x, 2011.
Download BibTeX filePublication details
F. Mansmann, D. Spretke and H. Janetzko.
Lessons Learned from Tool Development for Animal Movement Analysis.
Poster Proc. 1st IEEE Symposium on Biological Data Visualization (IEEE BioVis), Poster Paper, 2011.
Download BibTeX filePublication details
M. C. Hao, C. Rohrdantz, H. Janetzko, U. Dayal, D. A. Keim, L.-E. Haug and M. Hsu.
Visual Sentiment Analysis on Twitter Data Streams (Poster Paper).
Proceedings of the IEEE Conference on Visual Analytics Science and Technology (VAST 2011), IEEE, pages 277-278, DOI: 10.1109/VAST.2011.6102472, 2011.
Download BibTeX filePublication details
M. C. Hao, H. Janetzko, S. Mittelstädt, W. Hill, U. Dayal, D. A. Keim, M. Marwah and R. K. Sharma.
A Visual Analytics Approach for Peak-Preserving Prediction of Large Seasonal Time Series.
Computer Graphics Forum, 30(3):691--700, DOI: 10.1111/j.1467-8659.2011.01918.x, 2011.
Download BibTeX filePublication details
M. C. Hao, M. Marwah, H. Janetzko, R. K. Sharma, D. A. Keim, U. Dayal, D. Patnaik and N. Ramakrishnan.
Visualizing Frequent Patterns in Large Multivariate Time Series.
Proceedings of Visualization and Data Analysis 2011 (VDA 11), pages 10, DOI: 10.1117/12.872169, 2011.
Download BibTeX filePublication details
2010
M. C. Hao, U. Dayal, R. K. Sharma, D. A. Keim and H. Janetzko.
Visual Analytics of Large Multi-Dimensional Data Using Variable Binned Scatter Plots.
Proceedings of Visualization and Data Analysis 2010 (VDA 10), SPIE, DOI: 10.1117/12.840142, 2010.
Download BibTeX filePublication details
M. C. Hao, U. Dayal, R. K. Sharma, D. A. Keim and H. Janetzko.
Variable binned scatter plots.
Information Visualization Journal (IVS), 9():194-203, DOI: 10.1057/ivs.2010.4, 2010.
Download BibTeX filePublication details
2009
D. Oelke, M. C. Hao, C. Rohrdantz, D. A. Keim, U. Dayal, L.-E. Haug and H. Janetzko.
Visual Opinion Analysis of Customer Feedback Data.
Proceedings of the 2009 IEEE Symposium on Visual Analytics Science and Technology (VAST '09), IEEE, pages 187-194, DOI: 10.1109/VAST.2009.5333919, 2009.
Download BibTeX filePublication details
D. A. Keim, M. C. Hao, U. Dayal, H. Janetzko and P. Bak.
Generalized Scatter Plots.
Information Visualization Journal (IVS), Macmillan Publishers Ltd., DOI: 10.1057/ivs.2009.34, 2009.
Download BibTeX filePublication details
H. Janetzko, F. Mansmann, P. Bak and D. A. Keim.
Northern Lights Maps: Spatiotemporal Exploration of Mice Movement.
EuroVis2009 (Poster), 2009.
Download BibTeX filePublication details
M. C. Hao, H. Janetzko, R. K. Sharma, U. Dayal, D. A. Keim and M. Castellanos.
Visual Prediction of Time Series (Poster).
Proceedings of the IEEE Symposium on Visual Analytics Science and Technology (VAST 2009), pages 229 - 230, DOI: 10.1109/VAST.2009.5333420, 2009.
Download BibTeX filePublication details
P. Bak, F. Mansmann, H. Janetzko and D. A. Keim.
Spatiotemporal Analysis of Sensor Logs using Growth Ring Maps.
IEEE Transactions on Visualization and Computer Graphics (TVCG), 15(6):913-920, 2009.
Download BibTeX filePublication details
2007
M. Kramis, V. Wildi, B. Lemke, S. Graf, H. Janetzko and M. Waldvogel.
jSCSI - A Java iSCSI Initiator.
Proc. Jazoon '07, The International Conference on Java Technology, 2007.
Download BibTeX filePublication details
2006
H. Janetzko, D. A. Keim, M. Kramis, F. Mansmann and M. Waldvogel.
Interactive Poster: Exploring Block Access Patterns of Native XML Storage.
Conference Compendium of IEEE Symposium on Information Visualization (InfoVis 2006), IEEE, 2006.
Download BibTeX filePublication details