KNN and SVM Classification for Chainsaw sound Identification in the Forest Areas - Institut d'électronique, systèmes de communication et microsystèmes Accéder directement au contenu
Article Dans Une Revue International journal of advanced computer science and applications (IJACSA) Année : 2019

KNN and SVM Classification for Chainsaw sound Identification in the Forest Areas

Résumé

We present in this paper a comparative study of two classifiers, namely, SVM (support vector machine) and KNN (K-Nearest Neighbors), which we combine to MFCC (Mel-Frequency Cepstral Coefficients) in order to make possible the detection of chainsaw's sounds in a forest environment. Optimization's calculation of the relevant characteristics of the sounds recorded in the forest and the judicious choice of the key parameters of the classifiers allows us to obtain a true positive rate of 95.63% for the SVM-LOG-KERNEL and 94.02% for the KNN. The SVM-LOG-KERNEL classifier offers a better classification result and a processing time 30 times faster than KNN.
Fichier principal
Vignette du fichier
Paper_70-KNN_and_SVM_Classification_for_Chainsaw_Sound.pdf (1.01 Mo) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-02424029 , version 1 (09-01-2020)

Identifiants

Citer

N’tcho Assoukpou Jean Gnamélé, Yelakan Berenger Ouattara, Tokpa Arsene Kobea, Geneviève Baudoin, Jean-Marc Laheurte. KNN and SVM Classification for Chainsaw sound Identification in the Forest Areas. International journal of advanced computer science and applications (IJACSA), 2019, 10 (12), ⟨10.14569/IJACSA.2019.0101270⟩. ⟨hal-02424029⟩
190 Consultations
163 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More