{"title":"Influence of Holding Smart Phone for Acceleration-Based Gait Authentication","authors":"Yuji Watanabe","doi":"10.1109/EST.2014.24","DOIUrl":null,"url":null,"abstract":"In most previous researches on acceleration-based gait authentication, dedicated accelerometers are mounted on hip or ankle, or smart phones are in the pocket in fixed manners. However, when a user walks, smart phone is not only put in the pocket but also used calling or touching on the screen. In these situations, the direction of the phone should be taken into account. In this study, we first improve the application developed in our previous study to record more information such as the rotation of the phone around the 3 axes. And then we perform preliminary experiments using the improved application for 4 subjects to collect the user-generated acceleration data on walk when the phone is held calling and touching as well as in the pocket. The authentication results show that although 1.30% false acceptance rate (FAR) at 2.34% false rejection rate (FRR) is obtained when the phone is in the pocket, the FRR is extremely bad as touching on the screen.","PeriodicalId":193536,"journal":{"name":"2014 Fifth International Conference on Emerging Security Technologies","volume":"14 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2014-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"24","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2014 Fifth International Conference on Emerging Security Technologies","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/EST.2014.24","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 24
Abstract
In most previous researches on acceleration-based gait authentication, dedicated accelerometers are mounted on hip or ankle, or smart phones are in the pocket in fixed manners. However, when a user walks, smart phone is not only put in the pocket but also used calling or touching on the screen. In these situations, the direction of the phone should be taken into account. In this study, we first improve the application developed in our previous study to record more information such as the rotation of the phone around the 3 axes. And then we perform preliminary experiments using the improved application for 4 subjects to collect the user-generated acceleration data on walk when the phone is held calling and touching as well as in the pocket. The authentication results show that although 1.30% false acceptance rate (FAR) at 2.34% false rejection rate (FRR) is obtained when the phone is in the pocket, the FRR is extremely bad as touching on the screen.