2026-05-02T09:01:45Z https://meral.edu.mm/oai

oai:meral.edu.mm:recid/4524 2021-12-13T03:29:58Z 1582963302567:1597824273898 user-ucsy

A Comparative Study Using Two Classifiers For Hazardous Audio Event Classification Kyaw, Tin Ei The hazardous acoustic event classificationsystem is presented and tested in threateningenvironments. The system is based on classifiedwith Support Vector Machine (SVM), k NearestNeighbor (kNN) and modeled with GeneticRegulatory Network (GRN). GRN is adopted asclassification framework and greatly reducedinput feature dimensions. Setting the results thathave already reduced the inputs dimensions fromGRN framework as inputs for SVM and kNN cancorrectly classify audio event with lowcomputational time and cost. Comparative andclassification tests are carried out using threekinds of input sets with SVM and kNN classifier.These input sets are original feature set, reduceddimension feature set by GRN and unique featureset. SVM applies as novel discriminativeapproach for dissimilarity measure in order toaddress a supervised sound-classification taskand then shows good performance in the task ofacoustic event classification. Selecting GRN inevent classification system can not only reducescost and effort but also aims to obtain highperformance and accuracy in varying nature ofenvironments. 2012-02-28 http://hdl.handle.net/20.500.12678/0000004524 https://meral.edu.mm/records/4524