Science Fair Project Encyclopedia
K-Nearest Neighbor algorithm
In pattern recognition, the k-Nearest Neighbor algorithm is a method similar to the nearest neighbour classification method. The diffrence lies in the fact that rather than assigning a classification based upon the classification of the nearest neighbour the algorithm selects a set which contains the k nearest neighbours and assigns the class label to the new data point based upon the most numerous class with the set.
The contents of this article is licensed from www.wikipedia.org under the GNU Free Documentation License. Click here to see the transparent copy and copyright details