KNN/ANN Hybrid Location Determination Algorithm for Indoor Location Base Service

실내 위치기반서비스를 위한 KNN/ANN Hybrid 측위 결정 알고리즘

  • Lee, Jang-Jae (Dept. of Computer Science and Statistics, Chosun University) ;
  • Jung, Min-A (Dept. of Computer Engineering, Mokpo National University) ;
  • Lee, Seong-Ro (Dept. of Information and Electronics Engineering, Mokpo National University) ;
  • Song, Iick-Ho (Dept. of Electrical Engineering, KAIST)
  • 이장재 (조선대학교 컴퓨터통계학과) ;
  • 정민아 (목포대학교 컴퓨터공학과) ;
  • 이성로 (목포대학교 정보전자공학과) ;
  • 송익호 (한국과학기술원 전기및전자공학과)
  • Received : 2010.10.11
  • Accepted : 2010.11.23
  • Published : 2011.03.25

Abstract

As fingerprinting method, k-nearest neighbor(KNN) has been widely applied for indoor location in wireless location area networks(WLAN), but its performance is sensitive to number of neighbors k and positions of reference points(RPs). So artificial neural network(ANN) clustering algorithm is applied to improve KNN, which is the KNN/ANN hybrid algorithm presented in this paper. For any pattern matching based algorithm in WLAN environment, the characteristics of signal to noise ratio(SNR) to multiple access points(APs) are utilized to establish database in the training phase, and in the estimation phase, the actual two dimensional coordinates of mobile unit(MU) are estimated based on the comparison between the new recorded SNR and fingerprints stored in database. In the proposed algorithm, through KNN, k RPs are firstly chosen as the data samples of ANN based on SNR. Then, the k RPs are classified into different clusters through ANN based on SNR. Experimental results indicate that the proposed KNN/ANN hybrid algorithm generally outperforms KNN algorithm when the locations error is less than 2m.

Fingerprinting 방식에서 KNN은 WLAN 기반 실내 측위에 가장 많이 적용되고 있지만 KNN의 성능은 k 개의 이웃 수와 RP의 수에 따라 민감하다. 논문에서는 KNN 성능을 향상시키기 위해 ANN 군집화를 적용한 KNN과 ANN을 혼합한 알고리즘을 제안하였다. WLAN 환경하에서 알고리즘 기반의 패턴 매칭을 위해 training 단계에서는 여러 개의 AP에서 신호 잡음비의 특성값을 데이터베이스에 만들어 활용하고 estimation 단계에서는 단말기(MU)의 2차원 좌표값을 단말기로부터 새롭게 얻은 SNR과 데이터베이스에 저장된 fingerprint을 비교함으로써 추정한다. 제안한 알고리즘은 신호잡음비 데이터를 KNN 방법에 적용하여 k개의 RP을 선택한 후 선택된 RP의 신호잡음비를 ANN에 적용하여 k개의 RP를 군집하여 분류한다. 실험 결과에서는 위치 오차가 2m 이내에서 KNN/ANN 알고리즘이 KNN 알고리즘보다 성능이 우수하다.

Keywords

References

  1. T. Roos, P. Myllymaki, H. Tirri, P. Misikangas, J. Sievanen, "A Probabilistic Approach to WLAN User Location Estimation", Int. J. Wireless Inform. Network, Vol. 9, 2002.
  2. P. Bahl and V.N. Padmanabhan, RADAR: An In-Building RF-based User Location and Tracking System, Proc. IEEE Computer and Communications Societies, Vol. 2, 2000.
  3. 임재철, "옥내 측위을 위한 지문방식 알고리즘들의 성능분석", 전자공학회논문지, 제43권 CI편, 제6호, 2006년.
  4. K. Derr, M. Manic, "Wireless Based Object Tracking Based on Neural Network", 3rd IEEE Conference on Industrial Electrial Electronics and Application, 2008.
  5. A. LaMarca, Y. Chawathe, S. Consolvo, J. Hightower, I. Smith, J. Scott, T. Sohn, J. Howard, J. Hughe, F. Potter, J. Tabert, P. Powledge, G. Borriello, B. Schilit, "Place Lab:Device Positioning using Radio Beacons in The Wild", Pervasive Computing, Vol. 3468, 2005.
  6. 김학용, "무선랜 기반 위치정보 서비스", Telecommunication Review, 16(4), pp. 580-590 2006.
  7. A. Hatami, K. Pahlavan, "Comparative Statistical Analysis of Indoor Positioning Using Empirical Data and Indoor Radio Channel Models", IEEE CCNC 2006 proceedings. 2006.
  8. K. Kamol, K. Prashant, "Modeling of Indoor Positioning Systems Based on Location Fingerprinting", IEEE, 2004.
  9. M. Brunato, R, Battiti, "Statistical Learning Theory for Location Fingerprinting in Wireless LANs", Computer Networks, 2005.