Abstract
This work presents a novel approach for the fast prediction of future positions of marine vessels utilizing a simple feed-forward artificial neural network. It is shown that this simple network architecture with a single hidden layer, containing three hidden neurons is capable of predicting the future position of a maritime vessel with an accuracy of 99.26%. For this research a simulation was developed, in order to generate enough track data needed to train the network. The input data had to be converted from common polar coordinate system used by navigators into Cartesian coordinates in order to increase the accuracy of the predictions. The predictions are based on three previous observed positions and their corresponding observation times. It was shown that the accuracy decreased linearly with an increasing noise level of the observations. If the noise level exceeded a maximum noise level c of 20 m, the performance of the network degraded beyond its practical use.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Hassab, J.C., Guimond, B.W., Nardone, S.C.: Estimation of location and motion parameters of moving source observed from a linear array. J. Acoust. Soc. Am. 70(4), 1054–1061 (1981)
Carevic, D.: Robust estimation techniques for target motion analysis using passively sensed transient signals. IEEE J. Oceanic Eng. 28(2), 262–270 (2003)
Aidala, V.J.: Kalman filter behavior in bearings-only tracking applications. IEEE Trans. Aerosp. Electron. Syst. 1, 29–39 (1979)
Babu, G., Jayaprakash, V., Mamatha, B., Annapurna, P.: A neural network target tracking using Kalman filter. Int. J. Eng. Res. Technol. (IJERT) 1(9) (2012)
Lin, X., Kirubarajan, T., Bar-Shalom, Y., Maskell, S.: Comparison of EKF, pseudo measurement, and particle filters for a bearing-only target tracking problem. In: Proceedings of the SPIE 4728, Signal and Data Processing of Small Targets 2002 (2002)
Gao, C., et al.: Maneuvering target tracking with recurrent neural networks for radar application, Brisbane, QLD, Australia: IEEE (2018)
Nolle, L.: On a novel ACO-estimator and its application to the target motion analysis problem. In: Ellis, R., Allen, T., Petridis, M. (eds.) Applications and Innovations in Intelligent Systems XV, pp. 3–16. Springer, London (2008). https://doi.org/10.1007/978-1-84800-086-5_1
Hornik, K., Stinchcombe, M., White, H.: Multilayer Feedforward networks are universal approximators. Neural Netw. 2, 359–366 (1989)
Hornik, K.: Approximation capabilities of multilayer feedforward networks. Neural Netw. 4, 251–257 (1991)
Han, J., Zhang, X., Meng, C., Cao, F.: Simulated Research on Passive Sonar Range Using Different, Science and Technology on Underwater Test and Control Laboratory, Dalian, China: EDP Sciences (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Schlüsselburg, T., Tholen, C., Nolle, L. (2023). On the Application of Feed-Forward Artificial Neural Networks to the Maritime Target Motion Analysis Problem. In: Bramer, M., Stahl, F. (eds) Artificial Intelligence XL. SGAI 2023. Lecture Notes in Computer Science(), vol 14381. Springer, Cham. https://doi.org/10.1007/978-3-031-47994-6_41
Download citation
DOI: https://doi.org/10.1007/978-3-031-47994-6_41
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-47993-9
Online ISBN: 978-3-031-47994-6
eBook Packages: Computer ScienceComputer Science (R0)