The document discusses exploring big data landscapes using elastic displays. It presents a layer concept for examining the number of clusters in data, selecting algorithm parameters, and choosing different clustering algorithms. The comparison concept allows zooming into clusters and comparing algorithms at different levels of detail. The elastic displays provide intuitive interaction through stacking of views, natural zooming, and gestural interaction with force feedback.
Exploring Big Data Landscapes with Elastic Displays
1. 10. Workshop Be-Greifbare Interaktion
Konferenz „Mensch und Computer 2017“
Spielend einfach interagieren | Regensburg
Exploring Big Data
Landscapes with
Elastic Displays
SEP 10, 2017
Chair of Media Design
Technische Universität Dresden
Dietrich Kammer, Mandy Keck, Mathias Müller, Thomas Gründer, Rainer Groh
2. Structure
Background Layer Concept
Comparison Concept Conclusions
Big Data & Clustering,
Elastic Displays
Variation of Algorithm
Parameters
Differences between
Algorithms
Lessons Learned,
Future Work
3. Research Project
VANDA - Visual Analytics Interfaces for Big Data Environments
Data Analytics,
Copyright Observation
Data Crawling, Content
Exploration
Data Analytics and
Text Mining for Smart
Adaptive Learning
Environments
Research on Human
Computer Interaction
and Information
Visualization
Purchasing Platform bet-
ween Businesses with
Millions of Products
www.vanda-project.de
Workshop Be-Greifbare Interaktion 2017 Sep 10, 2017 D. Kammer et al. 3|13
5. Use Case
Data Set
Events with 15 attributes
Quantitative attributes are normalized to
a value between 0 and 10
Glyph Visualization
6 attributes are selected for glyph visualization:
price, popularity, time, distance,
estimationmusic and category
Clusters are mapped to color
price
popularity
time
estimation-
music
distance
price
popularity
time
estimation-
music
distance[Keck et al. 2017]
Workshop Be-Greifbare Interaktion 2017 Sep 10, 2017 D. Kammer et al. 5|13
6. Elastic Displays – A Global History
Force Touch
Apple
2015
Herot & Weinzapfel
touch-input vector information
MIT
1978
Minsky
force sensitive screen
Atari
1984
KoalaPad
KoalaTechnologies
1984
PL-500
Wacom
2000
Flexible Display
Plastic Logic
2013
Sinclair
Haptic Lens
Microsoft Research
1997
Cassinelli
Ishikawa
Khronos Projector
University of Tokyo
2005
Follmer at al.
deForm
MIT
2011
Yun et al.
ElaScreen
Seoul University
2013
LG Flex
LG Electronics
2014
Workshop Be-Greifbare Interaktion 2017 Sep 10, 2017 D. Kammer et al. 6|13
7. Elastic Displays – A Personal History
Peschke et al.
An Elastic Surface for
Tangible Computing
DepthTouch
AVI 2012
Gründer et al.
Towards a Design Space for
Elastic Displays
CHI 2013 Displays Workshop
Franke et al.
Interaction in-between 2D
and 3D interfaces
FlexiWall
HCII 2014
Müller et al.
FlexiWall:
Exploring Layered Data
with Elastic Displays
ITS 2014
Müller et al.
Data Exploration on
Elastic Displays using
Physical Metaphors
xCoAx 2015
Müller at al.
A Zoomable Product Browser
for Elastic Displays
xCoAx 2017
Müller et al.
Elastische Displays
im Einsatz
MuC 2016
Kammer et al.
Exploring Big Data Landscapes
with Elastic Displays
MuC 2017
8. Layer Concept
(1) examine number of clusters (2) select parameter for algorithm (3) select another algorithm
Hierarchical
Clustering
global local
Hierarchical
Clustering
global local
K-Means Algorithm
global local
Workshop Be-Greifbare Interaktion 2017 Sep 10, 2017 D. Kammer et al. 8|13
9. Comparison Concept
Birch Algorithm K-Means Algorithm
(A) comparison of 2 algorithms (B1) zoom in one of these clusters (B2) deep zoom for another LoD
Birch Algorithm K-Means Algorithm Birch Algorithm K-Means Algorithm
Workshop Be-Greifbare Interaktion 2017 Sep 10, 2017 D. Kammer et al. 9|13
11. Conclusions
Power of Elastic Displays
Intuitive Stacking of Views [Müller, Knöfel, et al., 2014]
Natural Zoomable User Interfaces
Gestural Interaction with Force Feedback
Exploration and Modification of Clustering Algorithms
_ More visualization options (e.g. Inertia)
_ More interaction possibilities (correct algorithms by
editing ground truth data)
_ Multi-user scenarios and user identification
_ Feedback-loop with calculating backend
(cloud computing)
Workshop Be-Greifbare Interaktion 2017 Sep 10, 2017 D. Kammer et al. 11|13
12. References
Agarawala, A. & Balakrishnan, R. (2006). Keepin’ it real: Pushing the desktop metaphor with physics, piles and the pen. In Proceedings of the sigchi
conference on human factors in computing systems (pp. 1283–1292). CHI ’06. Montreal, Quebec, Canada: ACM. doi:10.1145/1124772.1124965
Arthur, D. & Vassilvitskii, S. (2007). K-means++: The advantages of careful seeding. In Proceedings of the eighteenth annual acm-siam symposium on
discrete algorithms (pp. 1027–1035). SODA ’07. New Orleans: Society for Industrial and Applied Mathematics.
Cassinelli, A., Ishikawa, M. Khronos projector. In SIGGRAPH 2005 Emerging technologies, ACM, New York, 2005.
Ester, M., Kriegel, H.-P., Sander, J., & Xu, X. (1996). A density-based algorithm for discovering clusters a density-based algorithm for discovering
clusters in large spatial databases with noise. In Proceedings of the second international conference on knowledge discovery and data mining
(pp. 226–231). KDD’96. Portland, Oregon: AAAI Press. Frey, B. J. & Dueck, D. (2007). Clustering by passing messages between data points. Science,
315(5814), 972–976. doi:10.1126/science.1136800
Franke, I. S., Müller, M., Gründer, T., Groh, R. FlexiWall: Interaction in-between 2D and 3D Interfaces. In Proc. HCII 2014, Springer, Berlin 2014.
Gründer, T., Kammer, D., Brade, M., & Groh, R. (2013). Towards a design space for elastic displays. In Acm sigchi conference on human factors in
computing systems - workshop: Displays take new shape: An agenda for future interactive surfaces. Paris - France.
Jacob, R. J., Girouard, A., Hirshfield, L. M., Horn, M. S., Shaer, O., Solovey, E. T., & Zigelbaum, J. (2008). Reality-based interaction: A framework for
post-wimp interfaces. In Proceedings of the sigchi conference on human factors in computing systems (pp. 201–210). CHI ’08. Florence, Italy: ACM.
doi:10.1145/1357054.1357089
Keck, M., Kammer, D., Gründer, T., Thom, T., Kleinsteuber, M., Maasch, A., & Groh, R. (2017). Towards glyph-based visualizations for big data cluste-
ring. In The symposium on visual information communication and interaction - vinci 2017. Bangkok, Thailand (in press).
Workshop Be-Greifbare Interaktion 2017 Sep 10, 2017 D. Kammer et al. 12|13
13. Müller, M., Gründer, T., & Groh, R. (2015). Data exploration on elastic displays using physical metaphors. In Proceedings xcoax 2015, 25./26. juni,
glasgow, schottland. Müller, M., Knöfel, A., Gründer, T., Franke, I. S., & Groh, R. (2014). Flexiwall: Exploring layered data with elastic displays. In Pro-
ceedings its 2014, november 16.-19., germany.
Ng, A. Y., Jordan, M. I., &Weiss, Y. (2002). On spectral clustering: Analysis and an algorithm. In T. G. Dietterich, S. Becker, & Z. Ghahramani (Eds.),
Advances in neural information processing systems 14 (pp. 849–856). MIT Press.
Peschke, J., Göbel, F., Gründer, T., Keck, M., Kammer, D., & Groh, R. (2012). Depthtouch: An elastic surface for tangible computing. In Proceedings of
the international working conference on advanced visual interfaces (pp. 770–771). AVI ’12. Capri Island, Italy: ACM. doi:10.1145/2254556.2254706
Peschke, J., Göbel, F., Gründer, T., Keck, M., Kammer, D., Groh, R. DepthTouch: An Elastic Surface for Tangible Computing. In Proc. AVI 2012, ACM,
New York, 2012.
Sibson, R. (1973). Slink: An optimally ecient algorithm for the single-link cluster method. The Computer Journal, 16(1), 30. doi:10.1093/comjnl/16.1.30
Troiano, G. M., Pedersen, E. W., & Hornbæk, K. (2014). User-defined gestures for elastic, deformable displays. In Proceedings of the 2014 internatio-
nal working conference on advanced visual interfaces (pp. 1–8). AVI ’14. Como, Italy: ACM. doi:10 . 1145 /2598153.2598184
Watanabe, Y., Cassinelli, A., Komuro, T., Ishikawa, M. The deformable workspace: A membrane between real and virtual space. In Proc TABLETOP
2008, IEEE, 2008.
Zhang, T., Ramakrishnan, R., & Livny, M. (1996). Birch: An ecient data clustering method for very large databases. SIGMOD Rec. 25(2), 103–114.
doi:10.1145/235968.233324
Workshop Be-Greifbare Interaktion 2017 Sep 10, 2017 D. Kammer et al. 13|13