Classification of Audio Events in Surveillance System using Genetic Regulatory Network

Abstract

The surveillance system at important public places in a noisy environment deals with audio events detection is essential and useful application. At surveillance systems aiming to detect abnormal situations based on visual clues while, in some situations, it may be easier to detect and classify events using the audio information. Audio events classification for threatening environment through Genetic Regulatory Network (GRN) is considered. GRN is adopted as classification framework and greatly reduced input dimensions. Thus using the results from GRN framework as inputs for Support Vector Machine (SVM) can correctly classify audio events such as gunshot and explosion with low computational time and complexity. Selecting GRN in event detection system can not only reduces cost and effort but also aims to obtain high performance and accuracy in varying nature of environments