Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
194 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Random forests for detecting weak signals and extracting physical information: a case study of magnetic navigation (2402.14131v1)

Published 21 Feb 2024 in eess.SP, cs.LG, and physics.data-an

Abstract: It was recently demonstrated that two machine-learning architectures, reservoir computing and time-delayed feed-forward neural networks, can be exploited for detecting the Earth's anomaly magnetic field immersed in overwhelming complex signals for magnetic navigation in a GPS-denied environment. The accuracy of the detected anomaly field corresponds to a positioning accuracy in the range of 10 to 40 meters. To increase the accuracy and reduce the uncertainty of weak signal detection as well as to directly obtain the position information, we exploit the machine-learning model of random forests that combines the output of multiple decision trees to give optimal values of the physical quantities of interest. In particular, from time-series data gathered from the cockpit of a flying airplane during various maneuvering stages, where strong background complex signals are caused by other elements of the Earth's magnetic field and the fields produced by the electronic systems in the cockpit, we demonstrate that the random-forest algorithm performs remarkably well in detecting the weak anomaly field and in filtering the position of the aircraft. With the aid of the conventional inertial navigation system, the positioning error can be reduced to less than 10 meters. We also find that, contrary to the conventional wisdom, the classic Tolles-Lawson model for calibrating and removing the magnetic field generated by the body of the aircraft is not necessary and may even be detrimental for the success of the random-forest method.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (34)
  1. L. Breiman, ``Random forests,'' Mach. Learn. 45, 5–32 (2001).
  2. S. J. Rigatti, ``Random forest,'' J. Insur. Med. 47, 31–39 (2017).
  3. A. Cutler, D. R. Cutler, and J. R. Stevens, ``Random forests,'' Ensemble Mach. Learn.: Methods Appl. , 157–175 (2012).
  4. J. Su and H. Zhang, ``A fast decision tree learning algorithm,'' in AAAI, Vol. 6 (2006) pp. 500–505.
  5. Y. Freund and L. Mason, ``The alternating decision tree learning algorithm,'' in ICML, Vol. 99 (1999) pp. 124–133.
  6. T. Hesterberg, ``Bootstrap,'' Wiley Interdiscip. Rev. Comput. Stat. 3, 497–526 (2011).
  7. M. A. Manzoor and Y. Morgan, ``Vehicle make and model recognition using random forest classification for intelligent transportation systems,'' in 2018 IEEE 8th Annual Comput. Commun. Workshop Conf. (CCWC) (IEEE, 2018) pp. 148–154.
  8. P. Geurts, D. Ernst, and L. Wehenkel, ``Extremely randomized trees,'' Mach. Learn. 63, 3–42 (2006).
  9. N. Meinshausen and G. Ridgeway, ``Quantile regression forests.'' J. Mach. Learn. Res. 7 (2006).
  10. A. Canciani and J. Raquet, ``Absolute positioning using the earth's magnetic anomaly field,'' NAVIGATION: J. Inst. Navig. 63, 111–126 (2016).
  11. A. J. Canciani, ``Magnetic navigation on an f-16 aircraft using online calibration,'' IEEE Trans. Aerosp. Electron. Syst. 58, 420–434 (2021).
  12. M. Kayton and W. R. Fried, Avionics Navigation Systems (John Wiley & Sons, 1997).
  13. M. J. Veth, Fusion of Imaging and Inertial Sensors for Navigation (Air Force Institute of Technology, 2006).
  14. C. C. Liebe, ``Accuracy performance of star trackers-a tutorial,'' IEEE Trans. Aerosp. Electron. Syst. 38, 587–599 (2002).
  15. J. A. Richeson, ``Gravity gradiometer aided inertial navigation within non-gnss environments,'' in Proc. 20th Int. Tech. Meeting of the Satellite Division of the Inst. of Navigation (ION GNSS 2007) (2007) pp. 1089–1100.
  16. M. Mandea and M. Korte, Geomagnetic Observations and Models, Vol. 5 (Springer, 2010).
  17. A. Gnadt, ``Machine learning-enhanced magnetic calibration for airborne magnetic anomaly navigation,'' in AIAA SciTech 2022 Forum (2022) p. 1760.
  18. W. E. Tolles, ``Compensation of aircraft magnetic fields,''  (1954), uS Patent 2,692,970.
  19. A. R. Gnadt, Advanced Aeromagnetic Compensation Models for Airborne Magnetic Anomaly Navigation, Ph.D. thesis, Massachusetts Institute of Technology (2022b).
  20. P. M. Williams, ``Aeromagnetic compensation using neural networks,'' Neural Comput. & Appl. 1, 207–214 (1993).
  21. M. C. Hezel, ``Improving aeromagnetic calibration using artificial neural networks,'' AFIT scholar  (2020).
  22. K. O'Shea and R. Nash, ``An introduction to convolutional neural networks,'' arXiv preprint  (2015).
  23. L. E. Peterson, ``K-nearest neighbor,'' Scholarpedia 4, 1883 (2009).
  24. R. Goyal, P. Chandra, and Y. Singh, ``Suitability of KNN regression in the development of interaction based software fault prediction models,'' Ieri Procedia 6, 15–21 (2014).
  25. S. Kohli, G. T. Godwin, and S. Urolagin, ``Sales prediction using linear and KNN regression,'' in Advances in Mach. Learn. and Comput. Intell.: Proc. of ICMLCI 2019 (Springer, 2021) pp. 321–329.
  26. K. Ramya, Y. Teekaraman, and K. R. Kumar, ``Fuzzy-based energy management system with decision tree algorithm for power security system,'' Int. J. Comput. Intell. Syst. 12, 1173–1178 (2019).
  27. X. Luo, J. Xia, and Y. Liu, ``Extraction of dynamic operation strategy for standalone solar-based multi-energy systems: A method based on decision tree algorithm,'' Sustain. Cities Soc. 70, 102917 (2021).
  28. M.-C. Wu, S.-Y. Lin, and C.-H. Lin, ``An effective application of decision tree to stock trading,'' Expert Syst. Appl. 31, 270–274 (2006).
  29. B. B. Nair, V. Mohandas, and N. Sakthivel, ``A decision tree-rough set hybrid system for stock market trend prediction,'' Int. J. Comput. Appl. 6, 1–6 (2010).
  30. D. W. Aha and R. L. Bankert, ``A comparative evaluation of sequential feature selection algorithms,'' in Proc. Fifth Int. Workshop on AI and Stats (PMLR, 1995) pp. 1–7.
  31. R. A. Disha and S. Waheed, ``Performance analysis of machine learning models for intrusion detection system using gini impurity-based weighted random forest (GIWRF) feature selection technique,'' Cybersecurity 5, 1 (2022).
  32. H. Han, X. Guo, and H. Yu, ``Variable selection using mean decrease accuracy and mean decrease gini based on random forest,'' in 2016 7th IEEE Int. Conf. on Software Eng. Serv. Sci. (ICSESS) (IEEE, 2016) pp. 219–224.
  33. H. Kaneko, ``Cross-validated permutation feature importance considering correlation between features,'' Anal. Sci. Adv. 3, 278–287 (2022).
  34. M. Suganuma, S. Shirakawa, and T. Nagao, ``A genetic programming approach to designing convolutional neural network architectures,'' in Proc. Genet. Evol. Comput. Conf. (2017) pp. 497–504.
Citations (5)

Summary

We haven't generated a summary for this paper yet.

X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets