Underwater Target Recognition Based on Multi-Decision LOFAR Spectrum Enhancement: A Deep-Learning Approach

Underwater target recognition is an important supporting technology for the development of marine resources, which is mainly limited by the purity of feature extraction and the universality of recognition schemes. The low-frequency analysis and recording (LOFAR) spectrum is one of the key features of the underwater target, which can be used for feature extraction. However, the complex underwater environment noise and the extremely low signal-to-noise ratio of the target signal lead to breakpoints in the LOFAR spectrum, which seriously hinders the underwater target recognition. To overcome this issue and to further improve the recognition performance, we adopted a deep-learning approach for underwater target recognition, and a novel LOFAR spectrum enhancement (LSE)-based underwater target-recognition scheme was proposed, which consists of preprocessing, offline training, and online testing. In preprocessing, we specifically design a LOFAR spectrum enhancement based on multi-step decision algorithm to recover the breakpoints in LOFAR spectrum. In offline training, the enhanced LOFAR spectrum is adopted as the input of convolutional neural network (CNN) and a LOFAR-based CNN (LOFAR-CNN) for online recognition is developed. Taking advantage of the powerful capability of CNN in feature extraction, the recognition accuracy can be further improved by the proposed LOFAR-CNN. Finally, extensive simulation results demonstrate that the LOFAR-CNN network can achieve a recognition accuracy of 95.22%, which outperforms the state-of-the-art methods.

[1]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  D. Hubel,et al.  Receptive fields, binocular interaction and functional architecture in the cat's visual cortex , 1962, The Journal of physiology.

[3]  Tao Jiang,et al.  Deep learning for wireless physical layer: Opportunities and challenges , 2017, China Communications.

[4]  Wei Jie Wang,et al.  Feature Extraction for Rolling Element Bearing Faults Using Resonance Sparse Signal Decomposition , 2017, Experimental Techniques.

[5]  Derrick Wing Kwan Ng,et al.  Location-Aware Predictive Beamforming for UAV Communications: A Deep Learning Approach , 2020, IEEE Wireless Communications Letters.

[6]  Zhe Chen,et al.  A New Feature Extraction Method for Ship-Radiated Noise Based on Improved CEEMDAN, Normalized Mutual Information and Multiscale Improved Permutation Entropy , 2019, Entropy.

[7]  Hao Wu,et al.  Deep learning-based framework for expansion, recognition and classification of underwater acoustic signal , 2019, J. Exp. Theor. Artif. Intell..

[8]  K. P. Ramachandran,et al.  Rolling element bearing faults diagnosis based on autocorrelation of optimized: wavelet de-noising technique , 2009 .

[9]  Derrick Wing Kwan Ng,et al.  Deep Residual Learning for Channel Estimation in Intelligent Reflecting Surface-Assisted Multi-User Communications , 2021 .

[10]  Ying-Chang Liang,et al.  Activity Pattern Aware Spectrum Sensing: A CNN-Based Deep Learning Approach , 2019, IEEE Communications Letters.

[11]  Fei Yuan,et al.  Underwater Acoustic Target Recognition Based on Supervised Feature-Separation Algorithm , 2018, Sensors.

[12]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Ying-Chang Liang,et al.  Deep CM-CNN for Spectrum Sensing in Cognitive Radio , 2019, IEEE Journal on Selected Areas in Communications.

[14]  Chang Liu,et al.  Unsupervised Deep Spectrum Sensing: A Variational Auto-Encoder Based Approach , 2020, IEEE Transactions on Vehicular Technology.

[15]  Hamidou Tembine,et al.  Underwater Wireless Sensor Networks: A Survey on Enabling Technologies, Localization Protocols, and Internet of Underwater Things , 2019, IEEE Access.

[16]  Derrick Wing Kwan Ng,et al.  Deep Transfer Learning for Signal Detection in Ambient Backscatter Communications , 2020, IEEE Transactions on Wireless Communications.

[17]  Derrick Wing Kwan Ng,et al.  Learning-Based Predictive Beamforming for UAV Communications With Jittering , 2020, IEEE Wireless Communications Letters.

[18]  Jin Chen,et al.  Feature extraction of rolling bearing’s early weak fault based on EEMD and tunable Q-factor wavelet transform , 2014 .

[19]  Lawrence D. Jackel,et al.  Handwritten Digit Recognition with a Back-Propagation Network , 1989, NIPS.

[20]  Haixin Sun,et al.  Resonance-Based Time-Frequency Manifold for Feature Extraction of Ship-Radiated Noise , 2018, Sensors.

[21]  En Cheng,et al.  Integrated optimization of underwater acoustic ship-radiated noise recognition based on two-dimensional feature fusion , 2020 .

[22]  Gang Hu,et al.  Deep Learning Methods for Underwater Target Feature Extraction and Recognition , 2018, Comput. Intell. Neurosci..

[23]  En Cheng,et al.  Joint Representation and Recognition for Ship-Radiated Noise Based on Multimodal Deep Learning , 2019, Journal of Marine Science and Engineering.

[24]  Jean Paul Haton,et al.  Lofargram line tracking by multistage decision process , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[25]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Derrick Wing Kwan Ng,et al.  Deep Residual Learning-Assisted Channel Estimation in Ambient Backscatter Communications , 2020, IEEE Wireless Communications Letters.

[27]  Bo Fu,et al.  Deep learning feature extraction for target recognition and classification in underwater sonar images , 2017, 2017 IEEE 56th Annual Conference on Decision and Control (CDC).

[28]  Guanghao Jin,et al.  Expansion of restricted sample for underwater acoustic signal based on generative adversarial networks , 2019, International Conference on Graphic and Image Processing.

[29]  Sergey Ioffe,et al.  Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning , 2016, AAAI.

[30]  Sheng Shen,et al.  A Deep Convolutional Neural Network Inspired by Auditory Perception for Underwater Acoustic Target Recognition , 2019, Sensors.

[31]  Michael Elad,et al.  Submitted to Ieee Transactions on Image Processing Image Decomposition via the Combination of Sparse Representations and a Variational Approach , 2022 .

[32]  Xuanheng Li,et al.  Deep Learning-Based Spectrum Sensing in Cognitive Radio: A CNN-LSTM Approach , 2020, IEEE Communications Letters.

[33]  Chen Wang,et al.  Competitive Deep-Belief Networks for Underwater Acoustic Target Recognition , 2018, Sensors.

[34]  Peter F. Driessen,et al.  Deep learning for hydrophone big data , 2017, 2017 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (PACRIM).

[35]  Sheng Shen,et al.  Compression of a Deep Competitive Network Based on Mutual Information for Underwater Acoustic Targets Recognition , 2018, Entropy.

[36]  Mark J. Shensa,et al.  The discrete wavelet transform: wedding the a trous and Mallat algorithms , 1992, IEEE Trans. Signal Process..