A special feature of Probability and Statistics Day at UMBC 2013 is that the conference, including the workshop, is open to all statistics graduate students
from UMBC and local universites free of charge; however, REGISTRATION IS REQUIRED! The deadline to register is Friday,
April 12, 2013. // REGISTER NOW
For more information, contact any member of the organizing committee:
Bimal Sinha
Conference Chair
443.538.3012
Kofi Adragni
410.455.2406
Yvonne Huang
410.455.2422
Yaakov Malinovsky
410.455.2968
Thomas Mathew
410.455.2418
Nagaraj Neerchal
410.455.2437
DoHwan Park
410.455.2408
Junyong Park
410.455.2407
Anindya Roy
410.455.2435
Elizabeth Stanwyck
410.455.5731
Participant Information
Mingyu Xi
Paper: Linear and Nonlinear Discriminant Analysis of Osteoarthritis Data Based on MRI Study of Cartilage
Noninvasive MRI study of cartilage plays an important role in detecting early osteoarthritis. Classification of normal and degraded cartilage using individual parameters shows substantial overlapping in parameter values, greatly limiting sensitivity and specificity. In this study we investigate linear and nonlinear discriminant analysis for the multiple parameters case. We use Support Vector Machine and Multi Cluster based on mixtures of Gaussian components to conduct nonlinear discriminant analysis. We also use linear discriminant analysis using Sliced Inverse Regression and conventional Logistic Regression for classification of degraded tissues. Results of sensitivity and specificity of training and testing sets will be compared. Important parameter combinations will be identified. Due to differing degrees of tissue degradation, we also suggest a continuous measurement by assigning a probability to each sample belonging to the control group and degraded group. This continuous scoring method represents a more realistic classification.
