DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Han, Dong Soo | - |
dc.contributor.advisor | 한동수 | - |
dc.contributor.author | Lee, Nam Kyoung | - |
dc.date.accessioned | 2018-06-20T06:24:21Z | - |
dc.date.available | 2018-06-20T06:24:21Z | - |
dc.date.issued | 2017 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=718726&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/243452 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전산학부, 2017.8,[iv, 32 p. :] | - |
dc.description.abstract | A magnetic indoor positioning system utilizes magnetic landmarks, which are formed due to distorted geomagnetic fields, to estimate locations. However, existing magnetic positioning methods have difficulties in positioning, especially in a wide space because of the ambiguity of magnetic data. Multiple magnetic sensors should work in collaboration to yield a high accuracy, hindering the techniques from being used by mobile devices such as smartphones. To address this problem, we propose a new magnetic indoor positioning method using deep neural network. Features are extracted from magnetic sequences, and then the deep neural network is used for classifying features of magnetic landmarks detected from a dense magnetic map. The magnetic map is constructed by a robot. The proposed method achieved over 80% accuracy in a two-dimensional environment. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | magnetic fields▼aindoor-positioning▼asequence classification▼adeep neural network▼aindoor robot | - |
dc.subject | 지자기▼a실내 측위▼a시계열 분류▼a심층 신경망▼a실내 로봇 | - |
dc.title | Magnetic indoor positioning system using deep neural network | - |
dc.title.alternative | 딥러닝을 이용한 지자기 실내 측위 시스템 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전산학부, | - |
dc.contributor.alternativeauthor | 이남경 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.