Detecção de Eventos Sonoros para Sistemas de Segurança

Tito Caco Curimbaba Spadini, Ricardo Suyama

DOI: 10.14209/sbrt.2017.193

Evento: XXXV Simpósio Brasileiro de Telecomunicações e Processamento de Sinais (SBrT2017)

Keywords: Digital Signal Processing Digital Audio Processing Machine Learning Pattern Recognition Surveillance System

Abstract

This work aims to investigate different techniques for the classification of atypical sound events, considering the accuracy and classification time, in order to find which of these techniques are most advantageous for surveillance scenarios, minimizing the possibility of relevant events to go unnoticed. LDA, QDA, Decision Tree and KNN techniques were compared. The results obtained indicate that the KNN is the most indicated classification method for the purposes described.

Download