Peter Bajorski Headshot

Peter Bajorski

Professor

School of Mathematics and Statistics
College of Science

585-475-7889
Office Hours
M: W: 3:00-5:00 p.m. or by appointment.
Office Location
Office Mailing Address
Bldg. 14 Room 2530

Peter Bajorski

Professor

School of Mathematics and Statistics
College of Science

Education

MS, University of Wroclaw (Poland); Ph.D., Technical University of Wroclaw (Poland)

Bio

Dr. Peter Bajorski has taught undergraduate and graduate courses in fundamentals of probability and statistics, multivariate analysis, regression analysis, and experimental design. He has also developed and taught a specialized course on multivariate statistics for imaging science.

585-475-7889

Select Scholarship

Journal Paper
Pichichero, 3.R. Osgood, F. Salamone, A. Diaz, J. Casey, P. Bajorski, M. "Effect of pH and Oxygen on Biofilm Formation in Acute Otitis Media Associated NTHi Clinical Isolates." The Laryngoscope. (2015): 12-24. Print.
Bajorski, Peter, et al. "Fusing High Spatial Resolution RapidEye and High Temporal Resolution MODIS Imagery for Land Cover Classification." Remote Sensing TBD. (2015): --. Print.
Bajorski, Peter, et al. "Effect of pH and Oxygen on Biofilm Formation in Acute Otitis Media Associated NTHi Clinical Isolates." The Laryngoscope. (2014): NA. Print.
Bajorski, Peter, et al. "Stochastic Analysis and Modeling of a Tree-Based Group Key Distribution Method in Tactical Wireless Networks." Journal of Telecommunications System & Management. (2014): 1-8. Web.
Bajorski, P., P. Hall, and H. Rubinstein. "Methodology and Theory for Nonnegative-Score Principal Component Analysis." Statistica Sinica 23. 2 (2013): 963-988. Print.
Bajorski, P. "Non-Gaussian Linear Mixing Models for Hyperspectral Images." Journal of Electrical and Computer Engineering 2012. (2012): 1-8. Print.
Bajorski, P. "Practical Evaluation of Max-Type Detectors for Hyperspectral Images." IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 5. 2 (2012): 462-469. Print.
Bajorski, P. "Generalized Detection Fusion for Hyperspectral Images." IEEE Transactions on Geoscience and Remote Sensing 50. 4 (2012): 1199 - 1205. Print.
Bajorski, P. "Target Detection Under Misspecified Models in Hyperspectral Images." IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 5. 2 (2012): 470-477. Print.
Bajorski, Peter. "Generalized Detection Fusion for Hyperspectral Images"." IEEE Transactions on Geoscience and Remote Sensing 50. 4 (2012): 1199 -1205. Print.
Bajorski, Peter. "Target Detection Under Misspecified Models in Hyperspectral Images." Journal of Selected Topics in Applied Earth Observations and Remote Sensing 5. 2 (2012): 470-477. Print.
Bajorski, Peter. "Practical Evaluation of Max-Type Detectors for Hyperspectral Images." IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 5. 2 (2012): 462-469. Print.
Bajorski, Peter. "Non-Gaussian Linear Mixing Models for Hyperspectral Images." Journal of Electrical and Computer Engineering 2012. Article ID 818175 (2012): 8 pages-. Print.
Bajorski, Peter. "Generalized Detection Fusion for Hyperspectral Images." IEEE Transactions on Geoscience and Remote Sensing PP. 99 (2011): 1-7. Print.
Bajorski, Peter. "Statistical Inference in PCA for Hyperspectral Images." IEEE Journal of Selected Topics in Signal Processing 5. 3 (2011): 438-445. Print.
Bajorski, Peter. "Second Moment Linear Dimensionality as an Alternative to Virtual Dimensionality." IEEE Transactions on Geoscience and Remote Sensing 49. 2 (2011): 672-678. Print.
Bajorski, Peter. "Second Moment Linear Dimensionality as an Alternative to Virtual Dimensionality." IEEE Transactions on Geoscience and Remote Sensing 49. 2 (2011): 672-678. Print.
Bajorski, Peter. "Statistical Inference in PCA for Hyperspectral Images, IEEE Journal of Selected Topics in Signal Processing,." IEEE Signal Processing 5. 3 (2011): 438-445. Print.
Bajorski, Peter. "Generalized Detection Fusion for Hyperspectral Images"." IEEE Transactions on Geoscience and Remote Sensing PP. Issue: 99 (2011): 1-7. Print.
Published Conference Proceedings
Bajorski, Peter, et al. "Use of Clustering with Partial Least Squares Regression for Predictions Based on Hyperspectral Data." Proceedings of the Hyperspectral Image and Signal Processing: Evolution in Remote Sensing. Ed. Jocelyn Chanussot. Hoboken, NJ: n.p., 2014. Print.
Bajorski, Peter. "Directional Segmented Matched Filter for Hyperspectral Images." Proceedings of the Hyperspectral Image and Signal Processing: Evolution in Remote Sensing. Ed. A. Plaza. Lisbon: n.p., 2011. Web.
Bajorski, Peter. "Min-max Detection Fusion for Hyperspectral Images." Proceedings of the Hyperspectral Image and Signal Processing: Evolution in Remote Sensing. Ed. A. Plaza. Lisbon: n.p., 2011. Web.
Invited Paper
Bajorski, Peter. "General Remarks on Applied Mathematics and Statistics." Mathematica Applicanda. (2014). Print.
Shows/Exhibits/Installations
Bajorski, P. Target Detection in Constrained Models in Hyperspectral Images. 5 Jun. 2013. Workshop on Compositional Data Analysis, Vorau, Austria. Exhibit.
Invited Keynote/Presentation
Bajorski, Peter. "Generalized Fusion: A New Framework for Hyperspectral Detection." Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XVII. SPIE. Orlando, Orlando, FL. 25 Apr. 2011. Keynote Speech.
Full Length Book
Bajorski, Peter. Statistics for Imaging, Optics, and Photonics. 1st ed. Hoboken, NJ: Wiley, 2011. Print.
Bajorski, Peter. Statistics for Imaging, Optics, and Photonics. Rochester, NY: Wiley, 2011. Print.
Published Article
Ientilucci, E., and P. Bajorski. “Hyperspectral target detection in a whitened space utilizing forward modeling concepts.” IEEE Workshop on Hyperspectral Image and Signal Processing:Evolution in Remote Sensing (WHISPERS),14-16 June 2010. n.p. Print. *
P. Bajorski.“Investigation of Virtual Dimensionality and Broken Stick Rule for Hyperspectral Images.” IEEE Workshop on Hyperspectral Image and Signal Processing: Evolution inRemote Sensing (WHISPERS), 14-16 June 2010. n.p. Print. *
Bajorski, P., and N. Sanders, “A Modified Pixel Purity Index Method for Hyperspectral Images.” IEEE Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS), 14-16 June 2010. n.p. Print. *
Phillips, J., P. Bajorski,P. Burns, E. Fredericks, and M. Rosen. “Comparing image quality of print-on-demand books and photobooks from web-based vendors.” Journal of Electronic Imaging, 19.1 (2010): 011013-7. Web. *
P. Bajorski, “Second Moment Linear Dimensionality as anAlternative to Virtual Dimensionality,” IEEE Transactions on Geoscience and Remote Sensing, 48.10 (2010): 1—7. Print. *
Ientilucci, E.J., andP. Bajorski, “Hyperspectral target detectionin a whitened space utilizing forward modeling concepts.” Workshop onHyperspectral Image and Signal Processing:Evolution in Remote Sensing, 1.2 (2010): n.p. Print. £
Kinsman, T.B., P. Bajorski, and J.B. Pelz. “Hierarchical Image Clustering for Analyzing Eye Tracking Videos.” Western New York Image Processing Workshop, 2010. n.p. Print. " 

Currently Teaching

STAT-642
3 Credits
This course introduces students to analysis of models with categorical factors, with emphasis on interpretation. Topics include the role of statistics in scientific studies, fixed and random effects, mixed models, covariates, hierarchical models, and repeated measures.
STAT-745
3 Credits
This course is designed to provide the student with solid practical skills in implementing basic statistical and machine learning techniques for the purpose of predictive analytics. Throughout the course, many real world case studies are used to motivate and explain the strengths and appropriateness of each method of interest. In those case studies, students will learn how to apply data cleaning, visualization, and other exploratory data analysis tools to a variety of real world complex data. Students will gain experience with reproducibility and documentation of computational projects and with developing basic data products for predictive analytics. The following techniques will be implemented and then tested with cross-validation: regularization in linear models, regression and smoothing splines, k-nearest neighbor, and tree-based methods, including random forest.
STAT-756
3 Credits
Multivariate data are characterized by multiple responses. This course concentrates on the mathematical and statistical theory that underlies the analysis of multivariate data. Some important applied methods are covered. Topics include matrix algebra, the multivariate normal model, multivariate t-tests, repeated measures, MANOVA principal components, factor analysis, clustering, and discriminant analysis.
STAT-758
3 Credits
This course introduces multivariate statistical techniques and shows how they are applied in the field of Imaging Science. The emphasis is on practical applications, and all topics will include case studies from imaging science. Topics include experimental design and analysis, the multivariate Gaussian distribution, principal components analysis, singular value decomposition, orthogonal subspace projection, cluster analysis, canonical correlation and canonical correlation regression, regression, multivariate noise whitening. This course is not intended for CQAS students unless they have particular interest in imaging science. CQAS students should be taking the course STAT-756-Multivariate Analysis.

In the News

  • September 28, 2022

    person doing Tai Chi with a small humanoid robot.

    Faculty researchers develop humanoid robotic system to teach Tai Chi

    Zhi Zheng’s robot is skilled at Tai Chi, and her research team hopes it will soon lead a class of older adults at a local community center. Zheng, assistant professor of biomedical engineering in Kate Gleason College of Engineering, developed the humanoid robot as part of her assistive technology research.