A Bitwise Design and Implementation for Privacy-Preserving Data Mining: From Atomic Operations to Advanced Algorithms

Algorithm 6

The algorithm of kNN classification.

	Input: training data (X, Y, l), test data (x, y), and the number of neighbors, k
	Output: test label
(1)	Calculate distance with training data (X, Y) and test data (x, y) with absolute value operation.
(2)	Sort the smallest k distance using conditional swap operation on selection sort algorithm.
(3)	Output most major label among the labels of nearest k data.