The Laboratory of Optimization and Intelligent Systems (LOIS) pursues basic research in optimization, intelligent systems and automated learning methods, including data mining, statistical methodology, and knowledge discovery, driven by applications to problems of societal importance. Applications related to weather prediction, manufacturing, medical prognosis, financial engineering, automatic categorization of gene expression data from DNA microarrays are currently under investigation.
Machine learning, data mining, statistics, and discovery are growing rapidly in importance and commercial interest as more data becomes available online, as networking makes this data more accessible, and as basic research reaches maturity. The term “data mining” refers to new methods for the intelligent analysis of large data sets. One of the most fascinating application areas of these emerging technologies is finance and bio-informatics becoming more amenable to data-driven modeling as large sets of financial and gene expression data become available.
Recent research of the LOIS has developed new algorithms and theory, integrating state of the art techniques of mathematical optimization and machine learning to solve large scale data mining problems with applications to meteorology, manufacturing, gene expression data analysis, and finance. Theoretical work has been developed in building a bridge between operations research and machine learning. Specifically, our research investigates new algorithms for fast training of a class of machine learning techniques called Support Vector Machines (SVMs), based on sophisticated techniques of optimization (Interior Point Methods (IPMs)). Robust optimization techniques have been also developed for SVM problems with uncertainty in data.
For more information about the laboratory, please consult the news, the laboratory people, the courses offered, the publications, the research projects and the details about the research funding.
Contact Information
Dr. Theodore B. Trafalis
School of Industrial Engineering
University of Oklahoma
202 W Boyd St Rm 124
Norman OK 73019-1022, USA
Phones: 1-405-325-4347 (voice), 1-405-325-7555 (fax)
E-mail: ttrafalis@ou.edu