{"title":"Short term prediction of crowd density using v-SVR","authors":"Yongjun Ma, G. Bai","doi":"10.1109/YCICT.2010.5713088","DOIUrl":null,"url":null,"abstract":"The monitoring and management of the high density crowd in large scale public place is an important factor of city disaster reduction and mitigation. Automatic short term prediction of crowd density is a key problem. This paper introduces a prediction algorithm using v-support vector regression (v-SVR), which can control the accuracy of fitness and prediction error by adjusting the parameter v. An on-line training algorithm is discussed in detail to reduce the training complexity of v-SVR. As an important input feature, high crowd density estimation is also discussed. The experimental results show that v-SVR has low error rate and better generalization with appropriate v.","PeriodicalId":179847,"journal":{"name":"2010 IEEE Youth Conference on Information, Computing and Telecommunications","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2010 IEEE Youth Conference on Information, Computing and Telecommunications","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/YCICT.2010.5713088","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5
Abstract
The monitoring and management of the high density crowd in large scale public place is an important factor of city disaster reduction and mitigation. Automatic short term prediction of crowd density is a key problem. This paper introduces a prediction algorithm using v-support vector regression (v-SVR), which can control the accuracy of fitness and prediction error by adjusting the parameter v. An on-line training algorithm is discussed in detail to reduce the training complexity of v-SVR. As an important input feature, high crowd density estimation is also discussed. The experimental results show that v-SVR has low error rate and better generalization with appropriate v.