RobinGilbert.com

I presented my latest works in meteorology at the ANNIE 2009 Conference, in a presentation titled “Real-Time Prediction using Kernel Methods and Data Assimilation”. The conference was held in St. Louis, MO, on November 2-4 2009. Proceedings of the conference are also available here.

I recently presented the latest improvements I obtained in large scale robust classification at the INFORMS Western Regional Conference, in a presentation titled “Quadratic Programming Formulations for Classification and Regression”. The conference was held at the Arizona State University on April 24-25, 2009.

A poster presentation on my current work in biomedicine was made for the MCBIOS IV conference at New Orleans on February 1-3. The aim was to introduce new approaches for locating DNA and peptide sequences in databases of medical journals by using Support Vector Machines (SVMs). While the project is still under development, significant improvements were made in term of speed of computation. Newly developed SVMs can be trained on sets containing up to one million instances in less than 90 seconds by using an average computer. The accuracy is nearly perfect for locating DNA substrings and still acceptable for peptide sequences. Nevertheless further accuracy improvements are under way for peptide substrings.

The reference for the poster is:

• R. C. Gilbert, T. B. Trafalis, and J. D. Wren, “Scalable methods of locating peptide sequence data within full-text articles,” in 4th Annual Conference of the MidSouth Computational Biology and Bioinformatics Society, MCBIOS IV, New Orleans, Louisiana, USA, 2007.

You can also visit the websites of the co-authors:

• Jonathan D. Wren
• Theodore B. Trafalis

I participated this week in the 2006 NSF Design, Service, and Manufacturing Grantees and Research Conference that was held in St. Louis on July 24-27, 2006. The results of the collaboration between the Manufacturing Laboratory and the Laboratory of Optimization and Intelligent Systems of the School of Engineering of the University of Oklahoma were shown during a three days long poster session. A paper detailing our work on the form inspection of face milled plates using Support Vector Machines was specially written for the occasion. It is available for download at the publications page (see “Support vector regression towards adaptive flatness determination”, by R. C. Gilbert, S. Raman, T. B. Trafalis, and J. Aguirre-Cruz).