전자공학회논문지 (Journal of the Institute of Electronics and Information Engineers)

  • 제52권6호
  • /
  • Pages.95-104
  • /
  • 2015
  • /
  • 2287-5026(pISSN)
  • /
  • 2288-159X(eISSN)
대한전자공학회 (The Institute of Electronics and Information Engineers)
권호 표지
DOI QR코드

DOI QR Code

실내·외 구분 및 위치의 정확성을 개선한 Stay Point 추출 기법

Stay Point Extraction Method that Improve Accuracy of Location and to Distinguish Between Indoors & Outdoors

  • Park, Jin-Gwan (Dept. Computer Engineering, Mokpo National University) ;
  • Lee, Seong-Ro (Dept. of Electronics Engineering, Mokpo National University) ;
  • Jung, Min-A (Dept. Computer Engineering, Mokpo National University)
  • 투고 : 2015.03.10
  • 심사 : 2015.05.22
  • 발행 : 2015.06.25
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

최근 모바일 기기의 발전으로 사용자의 위치를 수집하고 분석하는 방법들이 연구되고 있다. 사용자의 특성을 파악하고 궤적 예측 및 패턴을 추출하기 위해 의미 기반 위치 기록을 사용하는 방법이 있다. 의미 기반 위치 기록을 사용하기 위해서는 사용자의 GPS로그를 분석하여 Stay Point를 추출하는 과정이 선행되어야 한다. 기존의 Stay Point 추출 방법은 임의의 중간좌표 즉, 사용자가 실제로 머무르지 않은 지점을 추출하기 때문에 정확하게 사용자가 머무른 위치라고 할 수 없으며, 실내와 실외의 Stay Point를 구분하지 못하는 단점이 있다. 본 논문에서는 이러한 단점을 보완하기 위해 사용자가 실제로 머무른 지점 및 실내에서 머무른 지점만을 추출하는 Stay Point를 제안한다. 기존의 방식으로 추출된 Stay Point에서 가장 가까운 GPS 좌표를 Stay Point로 지정하는 방식(nearSP)과, 사용자가 건물에 들어간 지점을 Stay Point로 지정하는 방식(indoorSP)이다. 제안한 알고리즘은 기존 Stay Point 추출 방법보다 Output 데이터의 용량 감소 및 위치의 정확성이 향상되었고, 실내와 실외를 구분 할 수 있음을 확인할 수 있었다.

Recently, collecting and analyzing method of users location has been studied due to the development of mobile devices. There is analyzing method using Semantic Location History in order to identify of characteristics and extract pattern and predict trajectory of users. We should extraction of Stay Point in order to use Semantic Location History. The Conventional extraction method of Stay Point is not accuracy of location of Stay Points because it does not specify the GPS log of users. Also, Conventional extraction method of Stay Point cannot distinguish indoors and outdoors. In this paper, we implement extraction method of Stay Point in which specify the GPS log of users and extraction of Stay Point at indoors only. Stay Point(nearSP) specifies the nearest GPS log of users from generated Stay Point by conventional extraction method. And, Stay Point(indoorSP) specifies the GPS log of users that user get into the building. Our experimental results, accuracy of Stay Point is improved, and capacity of output data decrease than Conventional extraction method. Also, we were able to distinguish Stay Point of indoors and outdoors.

키워드

참고문헌

  1. Hyang-Jin Lee, Jung-Hwa Choi and Young-Tack Park, "Semantic Point of Interest Detection from Large-scale GPS Data of Mobile Users" Journal of KIISE : Software and Applications, Vol 39, No. 3, pp. 175-184, Mar. 2012.
  2. GUIDOTTI, Riccardo, et al. Retrieving Points of Interest from Human Systematic Movements. In: Software Engineering and Formal Methods. Springer International Publishing, 2014. p. 294-308.
  3. ZIGNANI, Matteo; GAITO, Sabrina. Extracting human mobility patterns from GPS-based traces. In: Wireless Days (WD), 2010 IFIP. IEEE, 2010. p. 1-5.
  4. ZHENG, Yu, et al. Mining interesting locations and travel sequences from GPS trajectories. In: Proceedings of the 18th international conference on World wide web. ACM, 2009. p. 791-800.
  5. XIAO, Xiangye, et al. Finding similar users using category-based location history. In: Proceedings of the 18th SIGSPATIAL International Conference on Advances in Geographic Information Systems. ACM, 2010. p. 442-445.
  6. XIU-LI, Zhao; WEI-XIANG, Xu. A clustering based approach for discovering interesting places in a single trajectory. In: Intelligent Computation Technology and Automation, 2009. ICICTA'09. Second International Conference on. IEEE, 2009. p. 429-432.
  7. Miyoung Jang, Min Yoon and Jae-Woo Chang, "A Survey on Moving Object Trajectory Mining Techniques in Location-based Services", Journal of KIISE : Databases, Vol. 28, No. 1, Apr. 2012.
  8. LI, Quannan, et al. Mining user similarity based on location history. In: Proceedings of the 16th ACM SIGSPATIAL international conference on Advances in geographic information systems. ACM, 2008. p. 34.
  9. ZHENG, Yu, et al. Mining interesting locations and travel sequences from GPS trajectories. In: Proceedings of the 18th international conference on World wide web. ACM, 2009. p. 791-800.
  10. Haversine fomula. http://wikipedia.qwika.com/en2ko/Haversine_formula. Wikipedia.
  11. ZHENG, Yu; XIE, Xing; MA, Wei-Ying. GeoLife: A Collaborative Social Networking Service among User, Location and Trajectory. IEEE Data Eng. Bull., 2010, 33.2: 32-39.
  12. Geolife GPS trajectories. http://research.microsoft.com/en-us/downloads/b16d359d-d164-469e-9fd4-daa38f2b2e13/. Microsoft Research.
  13. RUIPENG, L. U. New User Similarity Measures Based on Mobility Profiles. 2013.
  14. Google Fusion Tables. https://support.google.com/fusiontables/answer/2571232

피인용 문헌

  1. Method of User Route Analysis based on POI through Stay Point Identification vol.19, pp.11, 2021, https://doi.org/10.14801/jkiit.2021.19.11.1