- Degree Overview
- Special Programs
- Student Resources
- Get Involved
- Professional & Career Resources
- New Students
- Degree Overview
- Student Resources
- Financial Support
- Graduate Student Directory
NSF Award Recognizes IUPUI Professor for Work to Enhance Machine Learning Applications
Apr 4 2013
Computer science research could improve bio-detection, medical monitoring
(INDIANAPOLIS) A computer science professor at IUPUI has earned the prestigious CAREER Award from the National Science Foundation (NSF) to research ways to help computers actively adjust models and classify new data by enhancing machine learning technology.
Murat Dundar, Ph.D., assistant professor in the Department of Computer and Information Science, becomes the fourth faculty member in the School of Science at IUPUI actively working under an NSF CAREER Award. The award is the most prestigious honor given by the NSF in support of faculty members early in their careers who exemplify the role of teacher-scholars through outstanding research, excellent education and integration of education and research.
Dundar will use the five-year, $500,000 award to continue to test theories related to machine learning, which traditionally is limited by the number of parameters or criteria a computer uses to classify data. In other words, a computer can only classify data (test results, biological samples, keyword indicators, for example) based on the training data set established at the beginning of an analysis. This oftentimes leads to misclassifications of data.
Dundar says this traditional method may not be accurate when you account for the continually evolving nature of data sets in many real-life situations.
His theory explores ways to refine how a computer actively and continually updates and adapts to the information it is collecting, thereby creating a more exhaustive set of categories by which to classify data. In essence, the computer is able to teach itself to recognize changes in the data and adjust accordingly.
“This new approach will let the data speak for itself in determining how many classes a computer can use,” said Dundar, who specializes in machine learning and artificial intelligence applications in a biological or medical context.
Dundar, who earned his Ph.D. in electrical and computer engineering from Purdue University in West Lafayette, has several ongoing research projects encompassing areas such as computer-aided diagnosis and detection and bio-detection technology.
This new direction in machine learning will be applied to some of his current work, including research to determine new bacteria subclasses, mineral diversity on Mars and how to create a better method of sorting and classifying large collections of documents or records. His research has been supported by agencies such as the National Institute of Biomedical Imaging and Bioengineering and the National Institute of Allergy and Infectious Diseases.
The CAREER Award grant also includes an element of outreach associated with Dundar’s research. He intends to organize a summer camp for K-12 students to introduce them to fundamental concepts in computer science and data mining and mentor student teams to compete in regional science fairs. He also hopes to organize a workshop on self-adjusting classification models at a premier machine learning conference.
Other School of Science faculty members conducting research under an NSF CAREER Award include Yogesh Joglekar, physics; Mohammad Al Hasan, computer science; and Greg Druschel, earth sciences.
About the School of Science at IUPUI
The School of Science is committed to excellence in teaching, research and service in the biological, physical, behavioral and mathematical sciences. The School is dedicated to being a leading resource for interdisciplinary research and science education in support of Indiana's effort to expand and diversify its economy. For more information, visit www.science.iupui.edu
More like this
- Murat Dundar
- Dr. Murat Dundar and Collaborator at Purdue West Lafayette Garner $385,000 NIH R21 Grant
- Computer trained to predict which AML patients will go into remission, which will relapse
- Eat Safer: Novel Technology Detects Unknown Food Pathogens
- IUPUI study: Training computers to differentiate between people with the same name