{"title":"Environmental sound classification for recognition of house appliances","authors":"M. A. Guvensan, Z. C. Taysi","doi":"10.1109/SIU.2010.5652796","DOIUrl":null,"url":null,"abstract":"Monitoring of daily activities is highly important to build environmental intelligence. Especially monitoring of house appliances is a key point for creating an intelligent home environment. Run levels of home appliances can be useful to detect such activities. Many house appliances produce different sounds during their differerent run levels. In this paper, we focus on recognition of running house appliances based on sound samples collected from house environment. MFCC and physical features of the sound are tested. Performance of both k-NN and SVM are evaluated. Our proposed system is able to identify working house appliances with 98% success rate.","PeriodicalId":152297,"journal":{"name":"2010 IEEE 18th Signal Processing and Communications Applications Conference","volume":"168 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2010-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2010 IEEE 18th Signal Processing and Communications Applications Conference","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SIU.2010.5652796","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2
Abstract
Monitoring of daily activities is highly important to build environmental intelligence. Especially monitoring of house appliances is a key point for creating an intelligent home environment. Run levels of home appliances can be useful to detect such activities. Many house appliances produce different sounds during their differerent run levels. In this paper, we focus on recognition of running house appliances based on sound samples collected from house environment. MFCC and physical features of the sound are tested. Performance of both k-NN and SVM are evaluated. Our proposed system is able to identify working house appliances with 98% success rate.