On the KNN Classifier, the Type of Distance Used and the Weighting of the Votes

In this paper we analyze the influence of the distance type and votes weighting used in data classification with the help of the K-nearest neighbor (KNN) classifier. We also compare the KNN classifier with other more complex ones in the literature. For the analysis, we used two databases, one containing ECG signals and another one available in Matlab. The obtained results show that even though the KNN classifier is one of the simplest and most common, its performance competes with more complex classifiers in the literature.