AIVDAC 2015 - 5th International Symposium Advances in Interactive and Visual Data Clustering

Visual and interactive approaches have been developed for data clustering since several decades now with the aim of improving the discovery of clusters in unlabelled data. With the new challenges that result from the accumulation of large and distributed datasets, efficient visual data clustering requires the study and implementation of new and advanced able to learn from big data that come from real-life applications.
While the need for clustering is evident, few solutions exist today for Big data. The aim of this symposium is to let researchers make a state of the art, discuss their ideas, present recent advances and results within the context of data clustering and visualizations or interactive methods.
The scope of the symposium will cover all aspects of visual and interactive data clustering. This includes many different issues like:
- How can the domain expert create clusters from an interactive visualization of large and/or distributed data?
- How visual techniques should be redesigned to handle big data?
- How can standard clustering algorithms be combined and improved with visualizations and interactions?
- What methods may efficiently reorganize a visual structure in order to let clusters appear?
- What are the recent and successful applications of visual data clustering?
Topics covered, but not limited to, include:
Visualization of clusters: maps, dendrograms, trees, matrices, 1D/2D/3D/nD ...
Clustering algorithm that produce visual results: Self-Organizing Maps, hierarchical agglomerative clustering,biomimetic algorithms, proximity graphs
Cooperation between clustering and visualization algorithms
Visualization and bi-clustering
Reorganization of visualizations, rearrangement clustering, matrix or tree reordering
Interactive discovery of clusters, other interactions with clusters in visualization
Visual analytics and data clustering
Handling large and complex data: Bioinformatics, Social networks, attributes-values, sequences, trees, graphs
Parallel Visualization of Big and Stream data
Parallel Implementation of visual clustering approaches (Cloud, CPU, GPU)
User and case studies