A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2016; you can also visit the original URL.
The file type is application/pdf.
A novel neighbor selection approach for KNN
2012
Proceedings of the 1st International Workshop on Context Discovery and Data Mining - ContextDD '12
Preserved Fulltext
Conventional weighting KNNs enhance the accuracy of label selection by weighting the neighbors. In this paper, however, we propose a novel weighting approach which weights the distances to find the neighbors more accurately. We take importance of size of classes and dispersity of samples into account for this purpose. Moreover we use LDA that saves discrimination level of data for reducing dimension of problem space. We show the effectivity of our proposed method on PDMC-04 dataset to predict physiological status of human subjects.
doi:10.1145/2346604.2346607
fatcat:gfgc2gn5q5cnljizhi2klql7tu