실내 측위를 위한 융합데이터 전처리기술 연구 - 크라우드 소싱 기반 -

Research on convergence data pre-processing technology for indoor positioning - based on crowdsourcing -

  • 이승엽 (동국대학교 기술창업학과) ;
  • 전병훈 (동국대학교 기술창업학과)
  • 투고 : 2023.08.27
  • 심사 : 2023.09.15
  • 발행 : 2023.10.30

초록

전 세계에서 보편 일률적으로 사용되는 실외 측위 기술인 GPS와 달리, 실내 측위 기술분야는 아직 다양한 기술이 난립하고 있다. 정확한 실내 위치 정보를 획득하기 위해 대표적인 실내 측위 기술의 표준이 필요한 실정이다. 최근 실내 측위 기술이 고정밀 위치 데이터를 기반으로 한 RTLS(Real Time Location Service) 영역으로 확대되고 있다. 이에 따라 새로운 방식의 실내 측위 기술들이 제안되고 있는데, 인공지능의 발전에 힘입어 스마트폰의 무선 신호 데이터를 사용하는 인공지능 기반의 실내 측위 기술이 빠르게 발전하고 있다. 이때 인공지능 학습에 필요한 데이터를 수집하는 과정에서, 왜곡되거나 학습에 부적합한 데이터가 포함되어 실내 측위 정확도가 낮아지는 결과가 발생하기도 한다. 본 연구에서는 수집된 데이터의 정제 과정을 통해 향상된 실내 위치 확인 결과를 얻기 위한 인공지능학습용 데이터 전처리 기술을 제안한다.

Unlike GPS, which is an outdoor positioning technology that is universally and uniformly used all over the world, various technologies are still being developed in the field of indoor positioning technology. In order to acquire accurate indoor location information, a standard of representative indoor positioning technology is required. Recently, indoor positioning technology is expanding into the Real Time Location Service (RTLS) area based on high-precision location data. Accordingly, a new type of indoor positioning technology is being proposed. Thanks to the development of artificial intelligence, artificial intelligence-based indoor positioning technology using wireless signal data of a smartphone is rapidly developing. At this time, in the process of collecting data necessary for artificial intelligence learning, data that is distorted or inappropriate for learning may be included, resulting in lower indoor positioning accuracy. In this study, we propose a data preprocessing technology for artificial intelligence learning to obtain improved indoor positioning results through the refinement process of the collected data.

키워드

과제정보

이 논문은 2022 년도 정부(과학기술정보통신부)의 재원으로 한국지능정보사회진흥원의 지원을 받아 수행된 연구임 (No. 2022-데이터-위 184, 3-12. 실내측위를 위한 융합데이터셋 구축)

참고문헌

  1. Korea Innovation Foundation, "Indoor location information technology," promising market Issue Report, Korea Innovation Foundation, 2021.
  2. H. M. Noh, Y. J. Oh, N. Y. Lee, and W. J. Shin. "A Survey of Deep Learning-Assisted Indoor Localization with Wi-Fi Fingerprinting: Current Status and Research Challenges," The Journal of Korean Institute of Communications and Information Sciences, Vol. 46, No. 5, pp. 848-862, Feb. 2021. https://doi.org/10.7840/kics.2021.46.5.848
  3. D. S. Han, S. H. Jeong. "Global indoor location recognition and indoor and outdoor integrated navigation system," The Journal of The Korean Institute of Communication Sciences, Vol. 32, No. 2, pp. 89-97. Feb. 2015.
  4. J. J. Ko, J. Y. Lee, Y. G. Mun, and Y. G. Cho, "Indoor and outdoor wireless positioning technology trends and prospects," KEIT PD Issue Report, Vol. 19-10, No. 3, pp. 65-83, Oct. 2019.
  5. R. Sheikhpour, M. A. Sarram, S. Gharaghani and M. A. Z. Chahooki, "A Survey on semisupervised feature selection methods," Pattern Recognition, vol. 64, pp. 141-158, Apr. 2017. https://doi.org/10.1016/j.patcog.2016.11.003
  6. J. H. Seong, "End-to-end-based Wi-Fi RTT network structure design for positioning stabilization," Journal of Korea Multimedia Society, Vol. 24, No. 5, pp. 676-683, May. 2021. https://doi.org/10.9717/KMMS.2020.24.5.676
  7. L. Choi, "Ultra-precise indoor positioning technology using deep learning-based indoor geomagnetic field," The Journal of The Korean Institute of Communication Sciences, Vol. 37, No. 12, pp. 51-58. Nov. 2020.
  8. E. S. Lohan, J. Torres-Sospedra, H. Leppakoski, P. Richter, Z. Peng, and J. Huerta, "Wi-Fi crowdsourced fingerprinting dataset for indoor positioning," Data, 2017.
  9. H. W. An, N. M. Moon, "Artificial intelligence-based indoor positioning technology trends and prospects," Broadcasting and Media Magazine Vol. 25, No. 1, pp. 75-82, Jan. 2020.
  10. B. G. Kim, K. J. Li, and H. K. Kang. "Generation of Indoor Network by Crowdsourcing," Journal of Korea spatial information society, Vol. 23, No. 1, pp. 49-57, Feb. 2015. https://doi.org/10.12672/ksis.2015.23.1.049
  11. D. J. Kim, C. G. Hwang, and C. P. Yoon. "Learning data preprocessing technique for improving indoor positioning performance based on machine learning," Journal of the Korea Institute of Information and Communication Engineering, Vol. 24, No. 11, pp. 1528-1533, Oct. 2020. https://doi.org/10.6109/JKIICE.2020.24.11.1528
  12. Sepp Hochreiter and Jurgen Schmidhuber. Long short-term memory. Neural Computation, 9(8):1735-1780, 1997. https://doi.org/10.1162/neco.1997.9.8.1735