DATA HUB Shilpi Ahuja CSE 591 - Data Mining 23rd April 2002
What is a Data Hub? • A website which provide links to various data repositories or data sets available on the World Wide Web
Need for a Data Hub • Large number of data sets available but all scattered • Difficult to locate relevant information • Data Hub provides links to all the relevant datasets at one place • Makes the search procedure easier for data mining researchers
Types of Data Sets Covered • Artificial Intelligence • Bioinformatics • Clinical • Ecological and Population • Economic Growth • GeoSpatial • Machine Learning • Space Science • Stats & Mathematics
Other Data Sets Covered • Algorithms • Electronic Tagging Data • Snow and Ice • Pathology • Seismic Data
Challenges Faced • Search time • Overlapping Data Sets • Division in categories • Providing introductions
Future Work • Addition of new data sets • Addition of new types of data sets • Providing search provisions on the website and improving its outlook.
References • Virtual Data Repository by Shriram Sankaran,CSE 591,Fall 2000