Location Estimation of Multiple Emitting RF Sources Using Supervised Machine Learning Technique

Location Estimation of Multiple Emitting RF Sources Using Supervised Machine Learning Technique
  IJETT-book-cover           
  
© 2022 by IJETT Journal
Volume-70 Issue-10
Year of Publication : 2022
Authors : Kamel H. Rahouma, Aya S. A. Mostafa
DOI : 10.14445/22315381/IJETT-V70I10P242

How to Cite?

Kamel H. Rahouma, Aya S. A. Mostafa, "Location Estimation of Multiple Emitting RF Sources Using Supervised Machine Learning Technique," International Journal of Engineering Trends and Technology, vol. 70, no. 10, pp. 428-437, 2022. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I10P242

Abstract
Location estimation of many emitting RF sources in space is considered crucial in civilian and military applications. In the present work, many emitter source signals are separated into individual emitting sources, and the location of each source is estimated. Two antenna array stations, A and B, are used to collect the data of the emitting sources. A music algorithm is used to estimate the AOAs. The emitter signals are separated using the Music output angles and array signal processing. The correlation of a source signal received by station A and station B will estimate the TDOA between the two array stations. Thus, a hybrid AOA-TDOA method is used to estimate the location of every individual emitting source. Matlab programming environment is used to design the algorithms used in the geolocation estimation process and present the output results. Supervised machine learning is tested to simplify the calculation complexity and enhance the output results. The present work uses the Matlab 2019b Statistics and Machine Learning Toolbox to build the classification models of emitter station received signals. Different classification algorithms of the tool kit classification learner were tried to get better accuracy. It is found that fine tree and KNN algorithms achieve better results. The resulting output proves that ML could be used to apply multi-emitter geolocation estimation.

Keywords
Classification with Matlab toolbox, Emitter-Sensor data collection, Geolocation with machine learning, Machine learning applications, Supervised Machine learning.

Reference
[1] Alon Amar, and Anthony J. Weiss, “Fundamental Limitations on the Number of Resolvable Emitters Using a Geolocation System,” IEEE Transactions on Signal Processing, vol. 55, no. 5, pp. 2193, 2007.
[2] Kamel H. Rahouma and Aya S. A. Mostafa, “Analysis and Simulation of RF Source Location Estimation Using Hybrid AOA and TOA Technique,” International Journal of Advanced Science and Technology, vol. 29, no. 3, pp. 972-985, 2020.
[3] Anne Ferréol, Jonathan Bosse, and Pascal Larzabal, “A Low-Cost AOA-TDOA Approach for Blind Geolocation in Multi-Paths Context,” 8th European Signal Processing Conference, Denmark, 2010.
[4] K. Bryan and D. J. Walter, "Geolocation of Multiple Noncooperative Emitters Using Received Signal Strength: Sparsity, Resolution, and Detectability," in IEEE Access, vol. 8, pp. 121999-122012, 2020.
[5] Hernandez M, “Novel Maximum Likelihood Approach for Passive Detection and Localisation of Multiple Emiters,” EURASIP Journal on Advances in Signal Processing, vol. 36, 2017.
[6] C. Wu and J. Elangage, "Multiemitter Two-Dimensional Angle-of-Arrival Estimator via Compressive Sensing," IEEE Transactions on Aerospace and Electronic Systems, vol. 56, no. 4, pp. 2884-2895, 2020.
[7] M. Viberg and B. Ottersten, “Sensor Array Processing Based on Subspace Fitting,” IEEE Transactions on Signal Processing, vol. 39, no. 5, pp. 1110–1121, 1991.
[8] Ralpho 0. Schmidt, “Multiple Emitter Location and Signal Parameter Estimation,” IEEE Transactions on Antennas and Propagation, vol. AP-34, no. 3, pp 276-280, 1986.
[9] Mushtaq Ahmad, and Xiaofei Zhang, “Performance of Music Algorithm for DOA Estimation,” ICAYS Engineering Mechanics and Interdisciplinary, China, 2016.
[10] Mahmoud Mohanna, Mohamed L. Rabeh, Emad M. Zieur, Sherif Hekala, “Optimization of MUSIC Algorithm for Angle of Arrival Estimation in Wireless Communications,” NRIAG Journal of Astronomy and Geophysics, vol. 2, no. 1, pp. 116-124, 2013.
[11] Sio-Iong Ao, Burghard Rieger, and Mahyar A. Amouzegar, “Machine Learning and Systems Engineering,” Springer, 2010.
[12] Kamel H. Rahouma and Aya S. A. Mostafa, “Location Estimation of RF Emitting Source Using Supervised Machine Learning Technique,” Advances in Intelligent Systems and Computing, Proceedings of the International Conference on Advanced Intelligent Systems and Informatics, Springer, vol. 1261, 2020.
[13] Abha Tiwari, Manish Kumar, "A Review of Range Based Localization Techniques in Wireless Sensor Networks," SSRG International Journal of Electronics and Communication Engineering, vol. 8, no. 12, pp. 1-5, 2021. Crossref, https://doi.org/10.14445/23488549/IJECE-V8I12P101.
[14] G. K. Papageorgiou and M. Sellathurai, "Fast Direction-of-arrival Estimation of Multiple Targets Using Deep Learning and Sparse Arrays," IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, pp. 4632-4636, 2020.
[15] MathWorks, Statistics and Machine Learning Toolbox, R2019b.
[16] Kamel H. Rahouma, and Aya S. A. Mostafa, “Location Estimation of RF Emitting Source Using Supervised Machine Learning Technique,” Proceedings of the International Conference on Advanced Intelligent Systems and Informatics, Springer, pp. 26-37, 2020.
[17] Dinh Tho Long, To Van Binh, Roan Van Hoa, Le Van Anh, Nguyen Van Toan, "Robotic Arm Simulation by using Matlab and Robotics Toolbox for Industry Application," SSRG International Journal of Electronics and Communication Engineering, vol. 7, no. 10, pp. 1-4, 2020. Crossref, https://doi.org/10.14445/23488549/IJECE-V7I10P101.
[18] Cheng D., Zhang S., Deng Z., Zhu Y., Zong M, “kNN Algorithm with Data-Driven k Value,” Advanced Data Mining and Applications, ADMA 2014, Lecture Notes in Computer Science, Springer, vol. 8933, pp. 499-512, 2014.
[19] N. de Sousa, M., and S. Thomä R, “Enhancement of Localization Systems in NLOS Urban Scenario with Multipath Ray Tracing Fingerprints and Machine Learning,” Sensors, vol. 18, pp. 4073, 2018.
[20] Shucheng Gong and Hongyan Liu, “Constructing Decision Trees for Unstructured Data,” Advanced Data Mining and Applications, ADMA 2014, Lecture Notes in Computer Science, Springer, vol. 8933, pp. 475-498, 2014.