{"title":"Accessing UXO Classification Technologies at a Challenging Live-UXO Site","authors":"I. Shamatava, Gregory S. Schultz, F. Shubitidze","doi":"10.1109/DIPED.2018.8543317","DOIUrl":null,"url":null,"abstract":"In this paper classification performances of advanced electromagnetic induction (EMI) models are evaluated at Fort Ord, CA live UXO site. The EMI data sets are collected using a next-generation EMI system, such as MetalMapper, in the cued mode. The limitation and valid range of application of advanced models: such as the Ortho Normalized Volume Magnetic Sources (ONVMS), Joint Diagonalization and Differential Evolution, are demonstrated for subsurface targets classification at a Live Site by taking into account the number of objects in a close proximity to the sensor, the size and material heterogeneity of those targets, and the local geologic conditions. The comparisons between classification results achieved by our team, using the advanced classification approach, and other teams are demonstrated.","PeriodicalId":146873,"journal":{"name":"2018 XXIIIrd International Seminar/Workshop on Direct and Inverse Problems of Electromagnetic and Acoustic Wave Theory (DIPED)","volume":"143 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 XXIIIrd International Seminar/Workshop on Direct and Inverse Problems of Electromagnetic and Acoustic Wave Theory (DIPED)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/DIPED.2018.8543317","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
In this paper classification performances of advanced electromagnetic induction (EMI) models are evaluated at Fort Ord, CA live UXO site. The EMI data sets are collected using a next-generation EMI system, such as MetalMapper, in the cued mode. The limitation and valid range of application of advanced models: such as the Ortho Normalized Volume Magnetic Sources (ONVMS), Joint Diagonalization and Differential Evolution, are demonstrated for subsurface targets classification at a Live Site by taking into account the number of objects in a close proximity to the sensor, the size and material heterogeneity of those targets, and the local geologic conditions. The comparisons between classification results achieved by our team, using the advanced classification approach, and other teams are demonstrated.