Na Tang's Research

 

 

 

My research focuses on applying web knowledge to the classification on insufficient statistical data. Instead of using the traditional statistical methods on the incomplete data, we explore methods to automatically retrieve web knowledge and methods to further exploit the web knowledge for better classification. How to retrieve the desired web documents, how to extract the desired knowledge from the documents and how to combine the knowledge into classifiers with incomplete data are the major challenge.

 

 

 

 

  • N. Tang and V. Rao Vemuri, "Bayesian Inference by Combining Poor-quality Data with Knowledge. Submitted to International Journal on Artificial Intelligence Tools (IJAIT). 2006. PDF
  • N. Tang and V. Rao Vemuri, " A Web-knowledge-based Clustering Model for Gene Expression Data Analysis. In Proceedings of the 2006 Atlantic Web Intelligence Conference (AWIC06). 2006. PDF
  • N. Tang and V. Rao Vemuri, "User-interest-based Document Filtering via Semi-supervised Clustering. In Proceedings of the 15th International Symposium on Methodologies for Intelligent Systems (ISMIS 2005). Pages 573-582. 2005. PDF
  • N. Tang and V. Rao Vemuri, "An Artificial Immune System Approach to Document Clustering," In Proceedings of the 20th ACM Symposium on Applied Computing (SAC2005), Evolutionary Computing and Optimization (EC) Track. Pages 918 - 922. 2005.PDF
  • Na Tang and V. Rao Vemuri, "Web-based Knowledge Acquisition to Impute Missing Values for Classification," In Proceedings of the 2004 IEEE/WIC/ACM International Joint Conference on Web Intelligence. Pages 124-130. Sep. 20-24, 2004. Beijing, China. PDF
  • V. Rao Vemuri and N. Tang,  “Solving Inverse Problems via Machine Learning and Knowledge Discovery," in (Eds. Takumi Ichimura and Katsumi Yoshida.), Knowledge-Based Intelligent Systems for Healthcare, CRC Press, 2004. PDF