60 likes | 207 Views
Cam Weighted Distance vs. Statistical Confidence. Optimized Nearest Neighbor Methods. Robert R. Puckett. Cam-Weighted Distance. Deforms the distribution by transformation Simulates strengthening and weakening effects between prototypes.
E N D
Cam Weighted Distance vs. Statistical Confidence Optimized Nearest Neighbor Methods Robert R. Puckett
Cam-Weighted Distance • Deforms the distribution by transformation • Simulates strengthening and weakening effects between prototypes. • k-nearest neighbors used to estimate parameters of the distribution • Inverse transform used to provide a “cam weighted distance”
Statistical Confidence Confidence proportional majority value of neighbors. On low confidence choose bigger k An alternative to globally increasing the k value. Algorithm selectively increases the k-value only when the confidence is below some threshold.
Goals Implement NN-Base System Cam-NN Add-on Statistical Confidence Add-on Create hybrid method Test against dataset
Schedule Main Milestones Software development Dataset generation Analysis Report Writing Schedule
References Duda, R. O., P. E. Hart, et al. (2001). Pattern classification. New York, Wiley. Wang, J., P. Neskovic, et al. (2006). "Neighborhood size selection in the k-nearest-neighbor rule using statistical confidence." Pattern Recognition 39 (3): 417-423. Zhou, C. Y. and Y. Q. Chen (2006). "Improving nearest neighbor classification with cam weighted distance." Pattern Recognition 39 (4): 635-645.