College of Computing & Informatics (CCI) PhD in computer science graduate Yusuf Osmanlioglu, PhD ’16 and co-authors CCI Assistant Professor
Santiago Ontañón, PhD CCI Professor & Senior Associate Dean of Research
Ali Shokoufandeh, PhD and Associate Professor
Uri Hershberg, PhD (School of Biomedical Engineering, Science and Health Systems), won Best Scientific Paper for “Efficient Approximation of Labeling Problems with Applications to Immune Repertoire Analysis” in Document Analysis, Biometrics and Pattern Recognition Applications track at the 23rd
International Conference on Pattern Recognition (ICPR). Osmanlioglu and co-authors will be recognized for the award at the ICPR Conference Banquet on Dec. 7.
Osmanlioglu and co-authors focused on labeling problems and the increasing applications to optimization problems. In this paper, they propose an efficient primal-dual solution,
MLPD, for a family of labeling problems, applying this algorithm to the analysis of immune repertoires, and comparing it against their baseline approach based on refinement operators. They also provided a comparative evaluation both in terms of accuracy and computational efficiency with respect to the baseline model, as well as to quadratic optimization.
Yusuf Osmanlioglu currently serves as a postdoctoral research fellow at the University of Pennsylvania, and was previously a research assistant at Drexel. Osmanlioglu interned at NEC Laboratories America Inc. and was a teaching assistant of the Logic Design course under the instruction of Dr. Bulent Tavli for TOBB University of Economics and Technology (ETU). Osmanlioglu also served as a research assistant for TOBB ETU and worked on a research project on microprocessor architecture, granted by The Scientific and Technological Research Council of Turkey.
The ICPR Conference will be held in Cancun, Mexico (Dec. 4-8. 2016) and is hosted by the Mexican Association for Computer Vision, Neurocomputing and Robotics (MACVNR). ICPR is an international forum for discussions on recent advances in the fields of pattern recognition, machine learning and computer vision, and on applications of these technologies in various fields.
Click here to access to the full program