DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Kim, Heeyoung | - |
dc.contributor.advisor | 김희영 | - |
dc.contributor.author | Kim, Keunseo | - |
dc.date.accessioned | 2019-09-03T02:41:59Z | - |
dc.date.available | 2019-09-03T02:41:59Z | - |
dc.date.issued | 2017 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=867014&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/266238 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 산업및시스템공학과, 2017.2,[v, 46 p. :] | - |
dc.description.abstract | Trail surface information is critical to prevent from the mountain accidents such as falls and slips. In this paper, we propose a new mobile crowdsensing system that automatically infers whether trail segments are risky to climb, by using sensor data collected from multiple hikers' smartphones. We extract cyclic gait based features from walking motion data to train machine learning models, and multiple hikers' results are then aggregated for robust classification. We evaluate our system with two real-world datasets. We firstly collect 14 climbers' data in a mountain trail which includes 13 risky segments. The average accuracy of individuals is about 80%, but after clustering the results, our system can accurately identify all the risky segments. We then collect an additional dataset from five climbers in two different mountain trails, which have 10 risky segments in total. Our results shows that the model trained in one trail can be used to accurately identify all the risky segments in the other trail, which documents generalizability of our system. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Crowdsensing system▼awalking pattern analysis▼arisky mountain trail detection▼aOne-class support vector machine▼awavelet analysis | - |
dc.subject | 크라우드 센싱 시스템▼a보행 분석▼a위험 등산로 탐지▼a단항 서포트 벡터 머신▼a웨이블릿 분석 | - |
dc.title | TrailSense | - |
dc.title.alternative | 보행 분석을 이용한 등산로 위험 구간 탐지를 위한 크라우드 센싱 시스템에 관한 연구 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :산업및시스템공학과, | - |
dc.contributor.alternativeauthor | 김근서 | - |
dc.title.subtitle | a crowdsensing system for detecting risky mountain trail segments with walking pattern analysis | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.