Classification of Gunshots with KNN Classifier

Abstract

In this article a system of detection and classification of gunshots is proposed, which consists of using the KNN classifier in the presence and absence of Gaussian additive noise. The results guarantee that the classifier reaches up to 94 % of performance in the absence of noise and only using 10 attributes. The attributes proposed in this article are easy to obtain and in the time domain. Finally, brief comparison of popular classifiers in WEKA is also performed to confirm the KNN classifier's advantage in the presence of noise.