Classification of propeller vehicle using LOFAR cubic splines interpolation in combination with triple loss variational auto encoder
172 viewsDOI:
https://doi.org/10.54939/1859-1043.j.mst.80.2022.39-48Keywords:
Underwater processing; Sonar; Interpolation; Triple loss.Abstract
In the field of ocean acoustics, both traditional and modern underwater signal processing methods have recently achieved positive results. For sonar problems serving national defense and security tasks, the need for timely and accurate classification of propeller ship types is of top importance. This study presents an underwater signal processing model for the purpose of detecting and classifying propeller ships with improved LOFAR techniques by cubic splines interpolation (CSI) combined with probability distribution in the hidden space domain. The results of the proposed model, tested on real data sets, show that the classification accuracy has increased by 10%, achieving an efficiency of 88% compared to the previous models. This solution also demonstrates that the model combining traditional and modern methods can effectively classify actual signals even when the amount of data is lacking and the signal-to-noise ratio is low.
References
[1]. W. S. Burdic, “Underwater Acoustic System Analysis”, Peninsula Pub, (2003).
[2]. R. O. Nielsen, ''Sonar signal processing'', Boston Artech House, pp. 16-85, (1991).
[3]. J.C. Martino, "An approach to detect lofar lines", Pattern Recognition Letters 17.1, pp. 37-46, (1996).
[4]. Q. Li, “Digital sonar design in underwater acoustics principles and applications", Springer Science & Business Media, (2012).
[5]. J. Choi, “Acoustic Classification of Surface and Underwater Vessels in the Ocean Using Supervised Machine Learning”, Sensors 19.16, (2019).
[6]. Y. LeCun, “Deep learning”, Nature, vol. 521, pp. 436-444, (2015).
[7]. S. Min, "Underwater target recognition based on wavelet packet entropy and probabilistic neural network", International Conference on Signal Processing, Communication and Computing, IEEE, (2013).
[8]. T. P. Hua, "Classification of Underwater Echo Based on Fractal Theory and Learning Vector Quantization Neural Network.", Applied Mechanics and Materials. Vol. 148. Trans Tech Publications Ltd, (2012).
[9]. Q. Weibiao, "Underwater targets classification using local wavelet acoustic pattern and Multi-Layer Perceptron neural network optimized by modified Whale Optimization Algorithm", Ocean Engineering 219: 108415, (2021).
[10]. W. Zhengxian, et al "A method of underwater acoustic signal classification based on deep neural network", 2018 5th International Conference on Information Science and Control Engineering (ICISCE). IEEE, (2018).
[11]. N. N. Moura, ''Novelty detection in passive sonar systems using support vector machines'', Latin America Congress on Computational Intelligence (LA-CCI), pp. 1-6, IEEE, (2015).
[12]. T. McConaghy, H. Leung, and V. Varadan, “Classification of audio radar signals using radial basis function neural networks”. IEEE Transactions on Instrumentation and Measurement, 52(6), pp. 1771-1779, (2003).
[13]. M. Farrokhrooz and M. Karimi, “Ship noise classification using probabilistic neural network and AR model coefficients”. Europe Oceans journal Vol. 2, IEEE, pp. 1107-1110, (2005).
[14]. J. Q. Gauthier and T. A. Gooley, "Cubic splines to model relationships between continuous variables and outcomes: a guide for clinicians." Bone marrow transplantation 55.4, pp. 675-680, (2020).
[15]. S. A Dyer and J. S. Dyer, "Cubic-spline interpolation", IEEE Instrumentation & Measurement Magazine 4.1, pp. 44-46, (2001).
[16]. R. Fuji et al "Intention detection based on siamese neural network with triplet loss", IEEE Access 8: 82242-82254, (2020).
[17]. K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition", arXiv preprint arXiv:1409.1556, (2014).
