Ensemble machine learning methods for Euler angles detection in an inertial navigation system

A.N. Grekov1, 2, A.A. Kabanov2

1Institute of Natural and Technical Systems, RF, Sevastopol, Lenin St., 28

2Sevastopol State University, RF, Sevastopol, Universitetskaya St., 33

E-mail: i@angrekov.ru

DOI: 10.33075/2220-5861-2022-1-112-120

UDC 004.852                                                              


Many countries in the world are showing great interest in the ocean, which is rich in resources and energy. In this regard, active research and development of a large number of marine equipment for the study and development of the ocean is underway. Along with the classical methods of ocean exploration, autonomous platforms such as AUVs, gliders and autonomous surface miniships have been actively introduced in recent decades.

The work is focused on increasing the reliability of the navigation information of such autonomous platforms, namely: determining the Euler angles using experimental data generated at the output of an inertial navigation system built on the basis of MEMS sensors. Two ensemble methods of machine learning are considered: majority voting (voting by majority) and weighted majority voting. The ensembles are formed by combining three supervised learning methods: support vector machine (SVM), k-nearest neighbors (KNN), and decision trees.

After hyperparameter optimization, the accuracy (accuracy) of the classification of the KNN model was 0.89 ±0.01, and the decision tree model was 0.91 ±0.01. Testing on the test data set also confirms the good performance of these classifiers: KNN accuracy – 0.90, and decision tree – 0.91. Combining the above two classifiers and the SVM classifier into an ensemble with a weighted majority gives a small increase in the accuracy (accuracy) of the classification: 0.92 on the training and test data sets, which allows recommending the obtained research results for improving the quality of navigation information. In the case of the ensemble with a majority vote, no significant increase in classification accuracy (accuracy) is found in comparison with individual classifiers.

Keywords: ensemble methods, decision tree, k-nearest neighbors, machine learning, inertial navigation system, autonomous underwater vehicles.

To quote:

Full text in PDF(RUS)


  1. Grekov A.N., Grekov N.A., and Sychov E.N. Srednechastotnye akusticheskie metody i sredstva dlya issledovaniya vodnoj sredy (Mid-frequency acoustic methods and instruments for the study of the aquatic environment). Sevastopol’: IPTS, 2020, 126 p. ISBN 978-5-6044196-6-3
  2. Kiselev L.V., Inzarcev A.V., and Matvienko Yu.V. Sozdanie intellektual’nyh ANPA i problemy integracii nauchnyh issledovanij (Creation of intelligent AUVs and problems of scientific research integration). Podvodnye issledovaniya i robototekhnika, 2006, No. 1. pp. 6–17.
  3. Gajkovich B.A., Zanin V.YU., and Kozhemyakin I.V. Voprosy razrabotki morskih robototekhnicheskih platform na primere sozdaniya podvodnogo apparata tipa “Glajder” (Issues of development of marine robotic platforms on the example of the creation of an underwater vehicle of the “Glider” type). Morskaya robototekhnika. Perspektivnye sistemy i zadachi upravleniya: trudy konferencii, 2016, pp. 151.
  4. Shishkin Y.E. and Grekov A.N. Koncepcija intellektual’noj sistemy avtomatizirovannogo jekologicheskogo monitoringa na baze malogabaritnyh avtonomnyh robotov (The concept of automated environmental monitoring intellectual system based on compact autonomous robots). Sistemy kontrolja okruzhajushhej sredy, 2018, No. 4(34), pp. 63–69.
  5. Grekov A.N., Grekov N.A., and  Alekseev S.Yu. Besplatformennyj navigacionnyj kompleks s inercial’noj sistemoj orientacii na ”grubyh” chuvstvitel’nyh elementah i sposob korrekcii ego inercial’nyh datchikov (Strapdown navigation system with an inertial orientation system on “coarse” sensitive elements and a method for correcting its inertial sensors); Pat. 2548115 Rossiya, MPK G01S 23/00. № 2014151906/93; zayavl. 18.12.14; opubl. 10.04.15, Byul. № 10.
  6. Li Y. et al. Inertial Sensing Meets Machine Learning: Opportunity or Challenge? IEEE Transactions on Intelligent Transportation Systems, 2021.
  7. Raschka S. and Mirjalili V. Python Machine Learning: Machine Learning and Deep Learning with Python. Scikit-Learn, and TensorFlow, 2017.
  8. Ruta D. and Gabrys B. Classifier selection for majority voting. Information fusion, 2005, Vol. 6, No. 1, pp. 63–81.
  9. Kuncheva L.I. Combining pattern classifiers: methods and algorithms. John Wiley & Sons, 2014.
  10. Alpaydin E. Introduction to machine learning. MIT press, 2020.
  11. Dietterich T.G. Ensemble Methods in Machine Learning. In International Workshop on Multiple Classifier Systems; Springer: Berlin/Heidelberg, Germany, 2000, pp. 1–15.
  12. Pedregosa F. et al. Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research, 2011, Vol. 12, pp. 2825–2830.
  13. Grekov A.N., Kabanov A.A., and Alekseev S.Yu. Metod opornyh vektorov dlya opredeleniya uglov Ejlera v inercial’noj navigacionnoj sisteme (Support vector machine for determining Euler angles in an inertial navigation system). Sistemy kontrolja okruzhajushhej sredy, 2021, No. 4 (46), pp. 134–142. DOI:10.33075/2220-5861-2021-4-134-142
  14. Grekov A.N., Alekseev S.Yu., and Bashkirov V.Yu. Rezul’taty laboratornyh ispytanij podvodnoj navigacionnoj sistemy dlya apparatov ekologicheskogo kontrolya (The results of laboratory tests underwater navigation system for environmental monitoring devices). Sistemy kontrolya okruzhayushchej sredy, 2020, No. 3 (41), pp. 65–74. DOI:10.33075/2220-5861-2020-3-65-74
  15. Molin S. and Jee K. Hands-On Data Analysis with Pandas – Second Edition: A Python Data Science Handbook for Data Collection, Wrangling, Analysis, and Visualization. Packt Publishing, 2021, 788 p. ISBN 9781800563452.
  16. Kohavi R. et al. A study of cross-validation and bootstrap for accuracy estimation and model selection. Ijcai, 1995, Vol. 14, No. 2, pp. 1137–1145.
  17. Varma S. and Simon R. Bias in error estimation when using cross-validation for model selection. BMC bioinformatics, 2006, Vol. 7, No. 1, pp. 1–8.
  18. Rashka S. and Mirdzhalili V. Python i mashinnoe obuchenie: mashinnoe i glubokoe obuchenie s ispol’zovaniem Python, scikit-learn i TensorFlow 2 (Python and machine learning: machine and deep learning using Python, scikit-learn and TensorFlow 2), Saint-Petersburg: OOO “Dialektika”, 2020, 848 p.
  19. Peterson L.E. K-nearest neighbor. Scholarpedia, 2009, Vol. 4, No. 2, p. 1883.
  20. Zhang S. et al. Efficient kNN classification with different numbers of nearest neighbors. IEEE transactions on neural networks and learning systems, 2017, Vol. 29, No. 5, pp. 1774–1785.
  21. Guo G. et al. KNN model-based approach in classification. OTM Confederated International Conferences “On the Move to Meaningful Internet Systems”, Springer, Berlin, Heidelberg, 2003, pp. 986–996.
  22. Dzhoshi P. Iskusstvennyj intellekt s primerami na Python (Artificial Intelligence with Python Examples). Moscow; Saint-Petersburg: Dialektika, 2019.
  23. Quinlan J.R. Induction of decision trees. Machine learning, 1986, Vol. 1, No. 1, pp. 81–106.
  24. Breiman L., Friedman J.H., Olshen R.A., and Stone C.J. Classification and regression trees. Wadsworth Inc. 1984, Vol. 67, 368 p.
  25. Everitt B.S., Landau S., Leese M., and Stahl D. Miscellaneous Clustering Methods. Cluster Analysis: John Wiley & Sons, Ltd., Chichester, UK, 2011, 352 p.