International journal of advanced smart convergence

The Institute of Internet, Broadcasting and Communication (한국인터넷방송통신학회)
권호 표지
DOI QR코드

DOI QR Code

Implementation of On-Device AI System for Drone Operated Metal Detection with Magneto-Impedance Sensor

  • Jinbin Kim (Department of Plasma Bio Display, Kwangwoon University) ;
  • Seongchan Park (Department of Plasma Bio Display, Kwangwoon University) ;
  • Yunki Jeong (Department of Plasma Bio Display, Kwangwoon University) ;
  • Hobyung Chae (Industry-Academic Cooperation Foundation, Kwangwoon University) ;
  • Seunghyun Lee (Ingenium College Liberal Arts, Kwangwoon University) ;
  • Soonchul Kwon (Graduate School of Smart Convergence, Kwangwoon University)
  • Received : 2024.07.12
  • Accepted : 2024.07.25
  • Published : 2024.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

This paper addresses the implementation of an on-device AI-based metal detection system using a Magneto-Impedance Sensor. Performing calculations on the AI device itself is essential, especially for unmanned aerial vehicles such as drones, where communication capabilities may be limited. Consequently, a system capable of analyzing data directly on the device is required. We propose a lightweight gated recurrent unit (GRU) model that can be operated on a drone. Additionally, we have implemented a real-time detection system on a CPU embedded system. The signals obtained from the Magneto-Impedance Sensor are processed in real-time by a Raspberry Pi 4 Model B. During the experiment, the drone flew freely at an altitude ranging from 1 to 10 meters in an open area where metal objects were placed. A total of 20,000,000 sequences of experimental data were acquired, with the data split into training, validation, and test sets in an 8:1:1 ratio. The results of the experiment demonstrated an accuracy of 94.5% and an inference time of 9.8 milliseconds. This study indicates that the proposed system is potentially applicable to unmanned metal detection drones.

Keywords

Acknowledgement

This research has been supported by the Defense Challengeable Future Technology Program of the Agency for Defense Development, Republic of Korea (No.912780601).

References

  1. Y. Yazid, I. Ez-Zazi, A. Guerrero-Gonzalez, A. El Oualkadi, and M. Arioua, UAV-Enabled Mobile Edge-Computing for IoT Based on AI: A Comprehensive Review, Drones, vol. 5, no. 4. MDPI AG, p. 148, Dec. 13, 2021, DOI: https://doi.org/10.3390/drones5040148.
  2. P. McEnroe, S. Wang, and M. Liyanage, A Survey on the Convergence of Edge Computing and AI for UAVs: Opportunities and Challenges, IEEE Internet of Things Journal, vol. 9, no. 17. Institute of Electrical and Electronics Engineers (IEEE), pp. 15435-15459, Sep. 01, 2022, https://doi.org/10.1109/jiot.2022.3176400.
  3. N. Cheng et al., AI for UAV-Assisted IoT Applications: A Comprehensive Review, IEEE Internet of Things Journal, vol. 10, no. 16. Institute of Electrical and Electronics Engineers (IEEE), pp. 14438-14461, Aug. 15, 2023, https://doi.org/10.1109/jiot.2023.3268316.
  4. J. C. TOZER, R. H. IRELAND, D. C. BARBER, and A. T. BARKER, Magnetic Impedance Tomographya, Annals of the New York Academy of Sciences, vol. 873, no. 1. Wiley, pp. 353-359, Apr. 1999, https://doi.org/10.1111/j.1749-6632.1999.tb09483.x.
  5. S. Ha et al., Neural Network for Metal Detection Based on Magnetic Impedance Sensor, Sensors, vol. 21, no. 13. MDPI AG, p. 4456, Jun. 29, 2021, https://doi.org/10.3390/s21134456.
  6. H. Kim, H. Chae, S. Kwon, and S. Lee, Optimization of Deep Learning Parameters for Magneto-Impedance Sensor in Metal Detection and Classification, Sensors, vol. 23, no. 22. MDPI AG, p. 9259, Nov. 18, 2023, https://doi.org/10.3390/s23229259.
  7. A. Barnawi, K. Kumar, N. Kumar, B. Alzahrani, and A. Almansour, A Deep Learning Approach for Landmines Detection Based on Airborne Magnetometry Imaging and Edge Computing, Computer Modeling in Engineering & Sciences, vol. 139, no. 2. Computers, Materials and Continua (Tech Science Press), pp. 2117-2137, 2024, https://doi.org/10.32604/cmes.2023.044184.
  8. L.-S. Yoo, J.-H. Lee, Y.-K. Lee, S.-K. Jung, and Y. Choi, Application of a Drone Magnetometer System to Military Mine Detection in the Demilitarized Zone, Sensors, vol. 21, no. 9. MDPI AG, p. 3175, May 03, 2021, https://doi.org/10.3390/s21093175.
  9. G. Wang et al., Anomaly Detection for Data from Unmanned Systems via Improved Graph Neural Networks with Attention Mechanism, Drones, vol. 7, no. 5. MDPI AG, p. 326, May 19, 2023, https://doi.org/10.3390/drones7050326.
  10. Guinon, Jose Luis, et al., Moving average and Savitzki-Golay smoothing filters using Mathcad, Papers International Conference on Engineering and Education 2007(ICEE), pp. 3-7, September 2007.
  11. H. Azami, K. Mohammadi, and B. Bozorgtabar, An Improved Signal Segmentation Using Moving Average and Savitzky-Golay Filter, Journal of Signal and Information Processing, vol. 03, no. 01. Scientific Research Publishing, Inc., pp. 39-44, 2012, https://doi.org/10.4236/jsip.2012.31006.
  12. J. Chung, C. Gulcehre, K. Cho, and Y. Bengio, Empirical Evaluation of Gated Recurrent Neural Networks on Seq uence Modeling. arXiv, 2014, https://doi.org/10.48550/ARXIV.1412.3555.