Ship acoustic signal classification is essential for vessel identification, underwater navigation, and maritime security. Traditional methods struggle with the non-stationary nature and noise of ship acoustic signals, reducing classification accuracy. To address these challenges, we propose an automated pipeline that integrates Empirical Mode Decomposition (EMD), adaptive wavelet filtering, feature selection, and a Bayesian-optimized Random Forest classifier. The framework begins with EMD-based decomposition, where the most informative Intrinsic Mode Functions (IMFs) are selected using Signal-to-Noise Ratio (SNR) analysis. Wavelet filtering is applied to reduce noise, with optimal wavelet parameters determined via SNR and Stein's Unbiased Risk Estimate (SURE) criteria. Features extracted from statistical, frequency domain (FFT), and time-frequency (wavelet) metrics are ranked, and the top 11 most important features are selected for classification. A Bayesian-optimized Random Forest classifier is trained using the extracted features, ensuring optimal hyperparameter selection and reducing computational complexity. The classification results are further enhanced using a majority voting strategy, improving the accuracy of the final object identification. The proposed approach demonstrates high accuracy, improved noise suppression, and robust classification performance. The methodology is scalable, computationally efficient, and suitable for real-time maritime applications.

Department of Computer Technologies in Publishing and Printing Processes Printing Art and Media Technologies Institute Lviv Polytechnic National University 79000 Lviv Ukraine

Department of Digital Economy and Business Analytics Ivan Franko National University 79000 Lviv Ukraine

Department of Informatics Jan Evangelista Purkyně University in Ústí nad Labem Pasteurova 3632 15 400 96 Ústí nad Labem Czech Republic

Department of Physics Kherson State University 73008 Kherson Ukraine

Zobrazit více v PubMed

Ahmad F., Ansari M., Anwar R., Shahzad B., Ikram A. Deep Learning Based Classification of Underwater Acoustic Signals. Procedia Comput. Sci. 2024;235:1115–1124. doi: 10.1016/j.procs.2024.04.106. DOI

Lokhande S., Malarkodi A., Latha G., Srinivasan S. Autonomous detection, localization and tracking of ships by underwater acoustic sensing using vector sensor array. Appl. Ocean. Res. 2025;154:104389. doi: 10.1016/j.apor.2024.104389. DOI

Li G., Zhang L., Yang H. Adaptive denoising model for ship-radiated noise based on dynamic weighted filtering. Appl. Ocean. Res. 2024;236:115042. doi: 10.1016/j.measurement.2024.115042. DOI

Yao X., Liu S., Chen J., Yan S., Ji F., Liu H., Chen J. Underwater Acoustic Target Classification Using Scattering Transform with Small Sample Size. IEEE Sens. J. 2024;24:25998–26010. doi: 10.1109/JSEN.2024.3419434. DOI

Wu F., Yao H., Wang H. Recognizing the State of Motion by Ship-Radiated Noise Using Time-Frequency Swin-Transformer. IEEE J. Ocean. Eng. 2024;49:667–678. doi: 10.1109/JOE.2024.3369663. DOI

Zhang Y., Zeng Q. MSLEFC: A low-frequency focused underwater acoustic signal classification and analysis system. Eng. Appl. Artif. Intell. 2023;123:106333. doi: 10.1016/j.engappai.2023.106333. DOI

Du L., Liu M., Lv Z., Wang Z., Wang L., Wang G. Classification Method for Ship-Radiated Noise Based on Joint Feature Extraction. Commun. Comput. Inf. Sci. 2024;2036:75–90. doi: 10.1007/978-981-97-0065-3_6. DOI

Nuruddin H., Azizi M.H., Mansor M.N., Ismail S.B., Kamal I.Z. Advancement in Emerging Technologies and Engineering Applications. Springer; Singapore: 2020. Forensic Investigation on the Propulsion Train System for Vibration Induced Phenomenon Onboard a Naval Vessel Using Fast Fourier Transform; pp. 25–32. Lecture Notes in Mechanical Engineering. DOI

Chen L., Luo X., Zhou H. A ship-radiated noise classification method based on domain knowledge embedding and attention mechanism. Eng. Appl. Artif. Intell. 2024;127:107320. doi: 10.1016/j.engappai.2023.107320. DOI

Li D., Liu F., Shen T., Chen L., Yang X., Zhao D. Generalizable Underwater Acoustic Target Recognition Using Feature Extraction Module of Neural Network. Appl. Sci. 2022;12:10804. doi: 10.3390/app122110804. DOI

Tang J., Gao W., Ma E., Sun X., Ma J. Deep Learning Based Underwater Acoustic Target Recognition: Introduce a Recent Temporal 2D Modeling Method. Sensors. 2024;24:1633. doi: 10.3390/s24051633. PubMed DOI PMC

Zhou A., Li X., Zhang W., Zhao C., Ren K., Ma Y., Song J. An attention-based multi-scale convolution network for intelligent underwater acoustic signal recognition. Ocean Eng. 2023;287:115784. doi: 10.1016/j.oceaneng.2023.115784. DOI

Li G., Han Y., Yang H. A new underwater acoustic signal denoising method based on modified uniform phase empirical mode decomposition, hierarchical amplitude-aware permutation entropy, and optimized improved wavelet threshold denoising. Ocean Eng. 2024;293:116629. doi: 10.1016/j.oceaneng.2023.116629. DOI

Jin S.Y., Su Y., Guo C.J., Ma C.Y., Fan Y.X., Tao Z.Y. Intrinsic mode ensembled statistical cepstral coefficients for feature extraction of ship-radiated noise. Appl. Acoust. 2025;227:110255. doi: 10.1016/j.apacoust.2024.110255. DOI

Li Y., Ning F., Jiang X., Yi Y. Feature Extraction of Ship Radiation Signals Based on Wavelet Packet Decomposition and Energy Entropy. Math. Probl. Eng. 2022;2022:8092706. doi: 10.1155/2022/8092706. DOI

Li Y.X., Wang L. A novel noise reduction technique for underwater acoustic signals based on complete ensemble empirical mode decomposition with adaptive noise, minimum mean square variance criterion and least mean square adaptive filter. Def. Technol. 2020;16:543–554. doi: 10.1016/j.dt.2019.07.020. DOI

Yang X., Shao J., Yang S., Wang X., Chen X. Feature Extraction and Classification Recognition of Ship Radiated Noise Based on 2D-ACVMD; Proceedings of the 2023 3rd International Symposium on Computer Technology and Information Science, ISCTIS 2023; Chengdu, China. 7–9 July 2023; pp. 619–623. DOI

Liu D., Yang H., Hou W., Wang B. A Novel Underwater Acoustic Target Recognition Method Based on MFCC and RACNN. Sensors. 2024;24:273. doi: 10.3390/s24010273. PubMed DOI PMC

Hong F., Liu C., Guo L., Chen F., Feng H. Underwater acoustic target recognition with a residual network and the optimized feature extraction method. Appl. Sci. 2021;11:1442. doi: 10.3390/app11041442. DOI

Wang B., Zhang W., Zhu Y., Wu C., Zhang S. An Underwater Acoustic Target Recognition Method Based on AMNet. IEEE Geosci. Remote Sens. Lett. 2023;20:5501105. doi: 10.1109/LGRS.2023.3235659. DOI

Qi P., Yin G., Zhang L. Underwater acoustic target recognition using RCRNN and wavelet-auditory feature. Multimed. Tools Appl. 2024;83:47295–47317. doi: 10.1007/s11042-023-17406-2. DOI

Xu W., Han X., Zhao Y., Wang L., Jia C., Feng S., Han J., Zhang L. Research on Underwater Acoustic Target Recognition Based on a 3D Fusion Feature Joint Neural Network. J. Mar. Sci. Eng. 2024;12:2063. doi: 10.3390/jmse12112063. DOI

Cao Y., Yan J., Sun K., Luo X. Hydroacoustic Target Detection Based on Improved GFCC and Lightweight Neural Network; Proceedings of the 2023 42nd Chinese Control Conference (CCC); Tianjin, China. 24–26 July 2024; pp. 6239–6243. DOI