Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

BLE Signals-based Machine Learning for Determining Indoor Presence

BLE 신호 기반 기계학습을 이용한 재실 여부 결정 방법

  • Kim, Seong-Chang (Department of Computer Engineering, Kyung-Nam University) ;
  • Kim, Jin-Ho (Department of Computer Engineering, Kyung-Nam University)
  • Received : 2022.10.25
  • Accepted : 2022.11.20
  • Published : 2022.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Various indoor location-based services can be provided through indoor presence determination and indoor positioning technology using Beacon. However, since the BLE signal advertised by the beacon has an unstable RSSI due to problems such as multi-path fading, it is difficult to guarantee the accuracy of indoor presence determination. In this paper, data were collected while the classroom door was open to ensure accuracy in various situations. Based on the collected data, we propose an indoor presence determination method considering the characteristics of the signal. The proposed method uses support vector machine, showed about 10% accuracy improvement compared to the results using raw RSSI only. This method has the advantage of being able to accurately determine indoor presence with only one receiver. It is expected that the proposed method can implement a low-cost system for determining indoor presence with high accuracy.

Beacon을 이용한 실내 재실 여부 결정 및 실내 측위 기술을 통해 다양한 실내 위치기반 서비스를 제공할 수 있다. 하지만, Beacon이 송출하는 BLE 신호는 다중 경로 페이딩 등의 문제로 인해 RSSI 값이 불안정하기 때문에 재실 여부 결정의 정확도를 보장하기 어렵다. 본 논문에서는 다양한 상황에서도 정확성을 보장하기 위해 강의실의 문이 열린 상태에서 데이터를 수집하였다. 수집된 데이터를 기반으로 신호의 특성을 고려한 재실 여부 결정 방법을 제안한다. 제안된 방법은 SVM 모델을 사용하며, 수신 신호 강도만을 사용한 결과에 비해 약 10% 정확도 향상을 보였다. 이 방법은 수신기 하나만으로도 재실 여부를 정확하게 판단할 수 있다는 장점이 있다. 제안된 방법을 통해 정확도 높은 염가형 재실 여부 결정 시스템을 구현할 수 있을 것으로 기대된다.

Keywords

Acknowledgement

This research was supported by University Innovation Support Project 2023.

References

  1. C. Zhou, J. Liu, M. Sheng, Y. Zheng, and J. Li, "Exploiting Fingerprint Correlation for Fingerprint-Based Indoor Localization: A Deep Learning Based Approach," IEEE Transactions on Vehicular Technology, vol. 70, no. 6, pp. 5762-5774, Jun. 2021. https://doi.org/10.1109/TVT.2021.3075539
  2. J. N. Lee, H. Y. Kang, Y. T. Shin, and J. B. Kim, "Indoor Positioning Algorithm Combining Bluetooth Low Energy Plate with Pedestrian Dead Reckoning," Journal of the Korea Institute of Information and Communication Engineering, vol. 22, no. 2, pp. 302-313, Feb. 2018. https://doi.org/10.6109/JKIICE.2018.22.2.302
  3. T. Y. Jung and E. R. Jeong, "Recurrent Neural Network Based Distance Estimation for Indoor Localization in UWB Systems," Journal of the Korea Institute of Information and Communication Engineering, vol. 24, no. 4, pp. 494-500, Apr. 2020. https://doi.org/10.6109/JKIICE.2020.24.4.494
  4. J. H. Lee, B. G. Park, Y. K. Kim, J. H. Choi, J. T. Kim, and K. H. Bae, "Common Chord based Trilateration Correction Algorithm and Hybrid Positioning System Development," Journal of the Korea Institute of Information and Communication Engineering, vol. 24, no. 3, pp. 448-458, Mar. 2020. https://doi.org/10.6109/JKIICE.2020.24.3.448
  5. C. G. Hwang, C. P. Yoon, and D. J. Kim, "Indoor positioning method using WiFi signal based on XGboost," Journal of the Korea Institute of Information and Communication Engineering, vol. 26, no. 1, pp. 70-75, Jan. 2022. https://doi.org/10.6109/JKIICE.2022.26.1.70
  6. H. J. Bae and L. Choi, "Large-Scale Indoor Positioning using Geomagnetic Field with Deep Neural Networks," in Proceedings of 2019 IEEE International Conference on Communications (ICC), Shanghai, China, pp. 1-6, 2019.
  7. R. H. Kim, S. H. Oh, and J. G. Kim. "Development of an Indoor Positioning Platform for Mobile Devices Based on BLE and WkNN Method," The Journal of Korean Institute of Communications and Information Sciences, vol. 47, no. 9, pp. 1406-1419. Sep. 2020.
  8. A. Guidara, G. Fersi, F. Derbel, and M. B. Jemaa, "Impacts of Temperature and Humidity variations on RSSI in indoor Wireless Sensor Networks," in Procedia Computer Science, Belgrade, Serbia, vol. 126, pp. 1072-1081, 2018. https://doi.org/10.1016/j.procs.2018.08.044
  9. J. Kim and B. Gu, "Machine Learning Method based on Beacon Signal Strength Pattern for Deciding Indoor Presence of User," The Journal of Korean Institute of Information Technology, vol. 18, no. 8, pp. 1-8, Aug. 2020. https://doi.org/10.14801/jkiit.2020.18.8.1
  10. S. C. Kim and J. H. Kim "Optimization Method of Kalman Filter Parameters Based on Genetic Algorithm for Improvement of Indoor Positioning Accuracy of BLE Beacon," Journal of the Korea Institute of Information and Communication Engineering, vol. 25, no. 11, pp. 1551-1558, Nov. 2021. https://doi.org/10.6109/JKIICE.2021.25.11.1551
  11. A. Mackey, P. Spachos, L. Song, and K. N. Plataniotis, "Improving BLE Beacon Proximity Estimation Accuracy Through Bayesian Filtering," IEEE Internet of Things Journal, vol. 7, no. 4, pp. 3160-3169, Apr. 2020. https://doi.org/10.1109/jiot.2020.2965583
  12. N. Singh, S. Choe, and R. Punmiya, "Machine Learning Based Indoor Localization Using Wi-Fi RSSI Fingerprints: An Overview," IEEE Access, vol. 9, pp. 127150-127174, Sep. 2021. https://doi.org/10.1109/ACCESS.2021.3111083
  13. M. Somvanshi, P. Chavan, S. Tambade, and S. V. Shinde, "A review of machine learning techniques using decision tree and support vector machine," in 2016 International Conference on Computing Communication Control and automation (ICCUBEA), Pune, India, pp. 1-7, 2016.
  14. Machine Learning in Python [Internet]. Available: https://scikit-learn.org/stable/auto_examples/svm/plot_rbf_parameters.html
  15. H. A. H. Alhalabi, T. -C. Wan, L. Missif, and M. Ehalabi, "Performance analysis of the constructive interference flooding in wireless sensor networks," in 2017 8th International Conference on Information Technology (ICIT), Amman, Jordan, pp. 75-81, 2017.
  16. ScienceDirect - Confusion Matrix [Internet]. Available: https://www.sciencedirect.com/topics/engineering/confusion-matrix.