CACR Seminar: “The Meta Clustering and Consensus approach to interactive data analysis”

June 23, 2009
2PM, Powell Booth 100

Roberto Tagliaferri
NEuRoNe Lab, DMI Università di Salerno, Fisciano (Sa)

Clustering of real-world datasets is a complex problem. Optimization models seeking to maximize a fitness function assume that the solution corresponding to the global optimum is the best clustering solution. Unfortunately, this is not always the case, mainly because of noise or intrinsic ambiguity in the data, and due to these reasons several assessment techniques fail.

Here we present a set of tools implementing classical and novel techniques to approach clustering in a systematic way, with applications to complex biological datasets. The tools deal with the problem of generating multiple clustering solutions, performing cluster analysis on such clusterings  (i.e. Meta Clustering) and reducing the final number of clusterings by the appropriate application of different Consensus techniques.

A subsequent crossing of prior knowledge to the obtained clusters helps the user in better understanding its meaning and validates the solutions. A collection of visualizations and interactive tools makes possible the challenge of managing such huge amount of information, allowing the user to extensively investigate for extracting knowledge from data.