UMass Lowell
Computer Science Colloquium 
Announcement
 
 
Speaker: Professor Georges Grinstein 
 Dept of Computer Science, UMass Lowell
Date: Feb. 6, 2002 
Time: 3:00pm--4:00pm
Place: Olsen 311 (The Media Lab)
 Refreshment is served at 2:30pm



 
  
 
 
  
  
 


 

Harnessing the Human in Knowledge Discovery: Visual Data Mining
 
Knowledge discovery is the process of discovering interesting, non-trivial patterns in data. 
In the sub-field called knowledge discovery in databases (KDD) the discovery process 
targets data repositories, and often includes metrics on the results it has achieved, measuring 
how good the discoveries are with respect to, for example, non-trivialness, novelty, or extent.
 
Knowledge, the primary goal of data analysis and exploration, is most often discovered by
generating information (structure) from data, and then abstracting non-trivial patterns (rules 
or associations for example) from the information. The discovery process can be done using
numerous means that share the same goal: visualization, data mining, statistics, or mathematical 
modeling and simulation.
 
Visualization is different from the rest, however, in that it is also the actual mechanism by 
which the analyses and their results can be presented to the user. Visualization, in other words, 
harnesses the perceptual and cognitive capabilities of the human user, still the most powerful 
pattern recognizer and inference engine. 
 
In this multimedia presentation I will provide a brief history of visualization and its role in 
knowledge discovery, describe state of the art visual data mining approaches, and discuss 
important research topics. 



 
  
 
 
  
  
 


 

Colloquium Coordinator: Jie Wang, wang@cs.uml.edu

Website: http://www.cs.uml.edu/~wang/colloquia/