Journal of IKEEE (전기전자학회논문지)

Institute of Korean Electrical and Electronics Engineers (한국전기전자학회)
권호 표지
DOI QR코드

DOI QR Code

Interference Elimination Method of Ultrasonic Sensors Using K-Nearest Neighbor Algorithm

KNN 알고리즘을 활용한 초음파 센서 간 간섭 제거 기법

  • Received : 2022.04.07
  • Accepted : 2022.06.13
  • Published : 2022.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

This paper introduces an interference elimination method using k-nearest neighbor (KNN) algorithm for precise distance estimation by reducing interference between ultrasonic sensors. Conventional methods compare current distance measurement result with previous distance measurement results. If the difference exceeds some thresholds, conventional methods recognize them as interference and exclude them, but they often suffer from imprecise distance prediction. KNN algorithm classifies input values measured by multiple ultrasonic sensors and predicts high accuracy outputs. Experiments of distance measurements are conducted where interference frequently occurs by multiple ultrasound sensors of same type, and the results show that KNN algorithm significantly reduce distance prediction errors. Also the results show that the prediction performance of KNN algorithm is superior to conventional voting methods.

본 논문에서는 k-최근접 이웃 (KNN) 알고리즘을 이용하여 초음파 센서 간 간섭을 줄이고 정확한 거리값을 예측하는 기법을 제안한다. 기존 기법에서는 이전 측정값과 현재 측정값을 비교하여 그 차이가 한계값을 벗어나면 간섭 신호로 인식하고 배제하지만 부정확한 예측이 자주 발생한다. KNN 알고리즘은 다수의 초음파 센서에서 입력되는 측정값을 분류하여 정확도 높은 예측이 가능하다. 간섭이 잘 발생하는 환경을 만들기 위해 다수의 동종 초음파 센서로 간섭 신호를 발생시킨 상태에서 거리 측정 실험을 진행하였고, 간섭으로 인해 발생하는 오류를 KNN 알고리즘을 통해 크게 줄일 수 있음을 확인하였다. 또한 기존 보팅 기법과 제안하는 기법의 결과를 비교하여 제안하는 기법의 성능이 우수한 것을 확인하였다.

Keywords

Acknowledgement

This work was supported by Industrial Technology Challenge Track (20012624) and Industrial Technology R&D Programs (20003771) of the Ministry of Trade, Industry and Energy (MOTIE) / Korea Evaluation Instutite of Industrial Technology (KEIT).

References

  1. J. D. Tardos, J. Neira, P. M. Newman, and J. J. Leonard, "Robust mapping and localization in indoor environments using sonar data," International Journal of Robotics Research, vol.21, no.4, pp.311-330, 2002. DOI: 10.1177/027836402320556340
  2. J. Borenstein and Y. Koren, "Noise rejection for ultrasonic sensors in mobile robot applications," Proceedings of IEEE International Conference on Robotics and Automation, pp.1727-1732, 1992. DOI: 10.1109/ROBOT.1992.220129.
  3. T. Jin, "Reflection noise rejection of ultrasonic sensor using scheduling firing method," Journal of the Korea Institute of Information and Communication Engineering, vol.16, no.1, pp.41-47, 2012. DOI: 10.6109/jkiice.2012.16.1.041
  4. H. Im and S. Lee, "Removal Method of Signal Interference between Ultrasound Sensors," J.inst. Korean.electr.elctron.eng., vol.25, no.4, pp.584-590, 2021. DOI: 10.7471/ikeee.2021.25.4.584
  5. M. E. Mohamed, H. Gotzig, R. Zoellner and P. Maeder, "A convolution neural network based machine learning approach for ultrasonic noise suppression with minimal distortion," Proceedings of IEEE International Ultrasonics Symposium, pp.1629-1634, 2019. DOI: 10.1109/ULTSYM.2019.8925655
  6. M. E. Mohamed, H. Gotzig, R. Zoellner and P. Maeder, "A Machine Learning Approach for Detecting Ultrasonic Echoes in Noisy Environments," Proceedings of IEEE Vehicular Technology Conference, pp.1-6, 2019. DOI: 10.1109/VTCSpring.2019.8746680
  7. S. Lee, W. Choi and D. H. Lee, "Securing Ultrasonic Sensors Against Signal Injection Attacks Based on a Mathematical Model," in IEEE Access, vol.7, pp.107716-107729, 2019. DOI: 10.1109/ACCESS.2019.2932843
  8. M. T. Akhtar, M. Abe and M. Kawamata, "On active noise control systems with online acoustic feedback path modeling," IEEE Transactions on Audio Speech and Language Processing, vol.15, no.2, pp.593-600, 2007. DOI:10.1109/TASL.2006.876749
  9. S. Yadav and S. Shukla, "Analysis of k-Fold Cross-Validation over Hold-Out Validation on Colossal Datasets for Quality Classification," Proceedings of IEEE International Conference on Advanced Computing, pp.78-83, 2016. DOI: 10.1109/IACC.2016.25