DC Field | Value | Language |
---|---|---|
dc.contributor.author | 염시진 | - |
dc.date.accessioned | 2023-04-07T16:33:33Z | - |
dc.date.available | 2023-04-07T16:33:33Z | - |
dc.date.issued | 2021 | - |
dc.identifier.other | OAK-2015-09793 | - |
dc.identifier.uri | http://postech.dcollection.net/common/orgView/200000601057 | ko_KR |
dc.identifier.uri | https://oasis.postech.ac.kr/handle/2014.oak/117247 | - |
dc.description | Master | - |
dc.description.abstract | In this thesis, we explain the Isolation Forest (IF) algorithm which is a basic model of the Robust Random Cut Forest (RRCF) algorithm. We will focus on the RRCF algorithm and its application to time series data. We examine how a Robust Random Cut Tree (RRCT) is created and how to calculate the \textit{Collusive Displacement} (CODISP) of each node in the tree. To improve the RRCF algorithm, we introduce a density measure which measures how ‘dense' the given data is. Using the density measure, we propose a WRCF algorithm called a WRCF which chooses the \split values considering the shape of the given data set. We apply the RRCF algorithm to the geophysical time series data collected from Gravity Recovery and Climate Experiment (GRACE) satellite which contains Earth’s water movement and surface mass changes and we investigate how the RRCF performs for the analysis of the GRACE data. | - |
dc.language | eng | - |
dc.publisher | 포항공과대학교 | - |
dc.title | RRCF 알고리즘을 이용한 이상신호 분석과 지구물리 데이터에의 응용 | - |
dc.title.alternative | Anomaly detection with robust random cut forest algorithm and its application to geophysical time series data | - |
dc.type | Thesis | - |
dc.contributor.college | 수학과 | - |
dc.date.degree | 2022- 2 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
library@postech.ac.kr Tel: 054-279-2548
Copyrights © by 2017 Pohang University of Science ad Technology All right reserved.