My research interests are mainly in the fields of biologically inspired computer vision, statistical pattern recognition, and machine learning. The specific problems in which I am interested are knowledge representation, learning, and classification. In addition, I am currently developing image processing and quantitative analysis techniques for basic and clinical neuroscience.

Biography

Although my formal training is in physics, my research is at the intersection of computer science, cognitive science and neuroscience, engineering, and applied mathematics. I am particularly interested in developing new learning and classification models. In developing these models I use methods from computer science (e.g. artificial neural networks and Bayesian inference), mathematics (e.g. statistical pattern recognition), engineering (e.g. signal processing), and physics (e.g. statistical mechanics). In addition, the inspiration for constructing learning algorithms comes from human perception and the way information is processed by the human visual system.

Research Description

In short, I am working on: a) developing models for pattern recognition that are inspired by the properties of human vision, and b) using statistical pattern recognition techniques to study the brain.

For detailed description of my research, please see my home page:
http://www.physics.brown.edu/physics/userpages/faculty/Predrag_Neskovic/Research.htm

Awards

Brown University Research Seed Fund Award
Brown University Brain Science Program's Pilot Research Award

Affiliations

N/A

Funded Research

"Using advanced mathematical techniques to analyze physiological responses to stimulation of specific acupoints." The Rhode Island Foundation, $10,000, PI, 2007.

"Using physiological measurements and artificial neural networks to monitor and predict cognitive states." Research Seed Fund Award, Brown University, $81,620, PI (with William Heindel), 2005-2006.

"Visual analysis of complex scenes: breaking camouflage and detecting occluded objects using Bayesian inference." Army Research Office (ARO), W911NF-04-1-0357, $457,548, Co-PI (with Leon Cooper), 2004-2009.

"Reducing the cognitive workload while operating in complex sensory environments: constructing a recognition system that utilizes aspects of human perception and cognition." ARO, DAAD19-01-1-0754, $300,000, Co-PI (with Leon Cooper), 2001-2004.

Selected Publications

• J. Wang, P. Neskovic, and L. N. Cooper. Selecting Data for Fast Support Vector Machine Training. Studies in Computational Intelligence, Vol. 35, pp. 61-84, 2007.(2007)
• J. Wang, P. Neskovic, and L. N. Cooper. Improving Nearest Neighbor Rule with a Simple Adaptive Distance Measure. Pattern Recognition Letters, 28(2), pp. 207-213, 2007.(2007)
• J. Wang, P. Neskovic and L. N. Cooper. Bayes Classification Based on Minimum Bounding Spheres. Neurocomputing, Vol. 70, pp. 801-808, 2007.(2007)
• J. Wang and P. Neskovic and L. N. Cooper. A minimum Sphere Covering Approach to Pattern Classification. ICPR, pp. 433-436, 2006.(2006)
• J. Wang and P. Neskovic and L. N. Cooper. Neighborhood Size Selection in the k-Nearest Neighbor Rule Using Statistical Confidence. Pattern Recognition, 39(3), pp. 417-423, 2006.(2006)
• P. Neskovic, L. Wu and L. N. Cooper. Learning by Integrating Information Within and Across Fixations. Lecture Notes In Computer Science: Artificial Neural Networks - ICANN, Vol. 4132, pp. 488-497, 2006.(2006)
• J. Wang and P. Neskovic and L. N. Cooper. A Probabilistic Model For Cursive Handwriting Recognition Using Spatial Context. ICASSP, 2005.(2005)
• T. Steinherz, E. Rivlin, N. Intrator, and P. Neskovic. An Integration of Online and Pseudo-Online Information for Cursive Word Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI, 27(5), pp. 669-684, 2005.(2005)
• P. Neskovic, D. Schuster and L. N Cooper. Biologically inspired recognition system for car detection from real-time video streams. Neural Information Processing: Research and Development, J. C. Rajapakse and L. Wang (eds.), Springer-Verlag, pp. 320-334, 2003.(2003)
• P. Neskovic, P. C. Davis and L. N. Cooper. Interactive Parts Model: an Application to Recognition of On-line Cursive Script. Advances in Neural Information Processing Systems (NIPS), pp. 974-980. 2000.(2000)