Visualization of GTD and Multimedia

1
Visualization of GTD and Multimedia

• Remco Chang
• Charlotte Visualization Center
• UNC Charlotte

2
Visual GTD Flow Chart
Entity Relationships (Geo-temporal Vis)
Dimensional Relationships (ParallelSets)
Entity Analysis (Search By Example)
3
WHO Terrorist Groups
Five Flexible Entry Components
What
WHERE
WHEN
4
Seeing Patterns
FARC showing an outlier
Unusual temporal pattern of NPA
5
Parallel Sets View

• Parallel Sets
• Displays relationships among categorical
  dimensions
• Shows intersections and distributions of
  categories

6
Parallel Sets View

• Dynamic filtering on continuous dimensions can
  show more information
• Here we see the large proportion of facility
  attacks and bombings in Latin America during the
  early 1980s

7
ParallelSets - Framing
8
Entity Comparison

• Uses the algorithm Longest Common Subsequence
  (LCS) to identify similar patterns

9
Grouping using MDS in 2D

• Each o represents a terrorist group
• Groups form cluster according to naturally
  occurring trend sizes
• Clusters are easily visible

MDS Analysis by Country
10
Auto Video Extraction
11
Multimedia Visual Analysis
12
Concept Graph
13
Video Analysis Example

• CNN Fox News MSNBC

• News contains view points and opinions
• Find local, regional, national, and international
  reports of the same event to get a complete
  picture

14
News Lens
15
Integrating Terrorism Data Analysisand News
Analysis
Terrorism Visual Analysis
Terrorism Databases
Terrorism VA
Jigsaw
NVAC
Stab/ TIBOR Reasoning Environment
Framing, Affective Analysis
Broadcast VA
News Visual Analysis
News Story Databases
16
Future Work

• Event-based video analysis
• Smart Visual GTD
• Collaboration with Daniel Kiem (Univ Konstanz,
  Germany)
• Multimedia Analysis
• Collaboration with PNNL (A. Sanfilipo, W. Pike)
• Analyzes (layout of) webpages, videos, images,
  and unstructured texts.
• Tracking temporal changes

17
Questions?

• Thank you!
• rchang_at_uncc.edu
• http//viscenter.uncc.edu

18
Backup
19
Entity Comparison

• Two strings of data (each representing a series
  of events)
• GATCCAGT
• GTACACTGAG
• Basic algorithm returns length of longest common
  subsequence 6
• Can return trace of subsequence if desired
• GTCCAG
• GATCCAGT
• GTACACTGAG
• Additional variations can take into account event
  gap penalties, time gap penalties, and
  exploration of shorter, or alternate, common
  subsequences

20
ParallelSets - Framing