(Luận án tiến sĩ) nghiên cứu giải pháp nâng cao chất lượng phân loại tín hiệu thủy âm tại vùng biển nước nông ứng dụng trí tuệ nhân tạo

MINISTRY OF EDUCATION AND TRAINING MINISTRY OF DEFENSE ACADEMY OF MILITARY SCIENCE AND TECHNOLOGY BACH NHAT HOANG RESEARCHING ON SOLUTION OF IMPROVING THE QUALITY OF UNDERWATER SIGNAL CLASSIFICATION IN SHALLOW WATERS APPLYING ARITIFICIAL INTELLIGENCE SUMMARY OF PhD THESIS IN ENGINEERING HANOI – 2023 m MINISTRY OF EDUCATION AND TRAINING MINISTRY OF DEFENSE ACADEMY OF MILITARY SCIENCE AND TECHNOLOGY BACH NHAT HOANG RESEARCHING ON SOLUTION OF IMPROVING THE QUALITY OF UNDERWATER SIGNAL CLASSIFICATION IN SHALLOW WATERS APPLYING ARITIFICIAL INTELLIGENCE Specialization: Electronic Engineering Code: 52 02 03 SUMMARY OF PhD THESIS IN ENGINEERING SCIENTIFIC SUPERVISORS: Assoc, Prof Dr Nguyen Van Duc Dr Vu Le Ha HANOI – 2023 m i DECLARATION I hereby declare that this is my own research work under the guidance of my supervisors The statistics and results presented in this thesis are completely honest and have not been published in any other works References are fully cited Hanoi, April 12nd, 2023 Author Bach Nhat Hoang m ii ACKNOWLEDGEMENT During the process of conducting research and completing this thesis, the PhD student has received valuable guidance, supports and comments, as well as sincere encouragements from scientists, teachers, colleagues and family members First of all, the PhD student would like to express his gratitude to Assoc Prof Dr Nguyen Van Duc and Dr Vu Le Ha for their enthusiastic guidance and support in the entire process of conducting research and completing the thesis Also, the PhD student would like to show his sincere thanks to the Board of Management of the Academy Military of Science and Technology, the Training Department and the Institute of Electronics for giving the PhD student all the favorable conditions to study, research and complete the thesis Additionally, the PhD student sincerely thank the teachers, scientists, and colleagues at the Academy Military of Science and Technology, the Institute of Electronics, and Hanoi University of Science and Technology, etc for instructing and providing valuable suggestions to the PhD student throughout the process of conducting this thesis Last but not least, the PhD student is thankful for the encouragement, support, sharing and sacrifice of his family that help the PhD student to overcome difficulties and achieve the research results in this thesis Author Bach Nhat Hoang m iii TABLE OF CONTENTS LIST OF ABBREVIATIONS vii LIST OF TABLES xi LIST OF FIGURES xi INTRODUCTION CHAPTER 1.OVERVIEW ON THE CLASSIFICATION OF BIOTIC AND ABIOTIC UNDERWATER SIGNALS IN SHALLOW WATERS 1.1 Biotic-Abiotic underwater signals and uderwater signal classification system in shallow waters 1.1.1 1.2 1.3 1.4 7 The ocean and acoustic propagation characteristics in shallow waters 1.1.2 Biotic and Abiotic sound sources 11 1.1.3 Underwater signal detection system based on sonar principle 13 Classical approaches in underwater signal classification 19 1.2.1 Time-frequency domain transformation 19 1.2.2 LOFAR algorithm 22 1.2.3 CMS algorithm 23 1.2.4 DEMON algorithm 24 Modern approaches in underwater signal classification 26 1.3.1 Restricted Boltzmann Machine 27 1.3.2 Auto-Encoder 28 1.3.3 Convolution Neural Network 29 The current state of research in underwater signal classification and limitation 30 1.4.1 The sole use of artificial intelligence 32 1.4.2 The use of pre-processing combined with artificial intelligence 35 1.4.3 The use of transfer learning 38 1.4.4 Limitations 39 m iv 1.5 1.6 Research directions of the thesis and actual underwater datasets 40 1.5.1 Research directions of the thesis 41 1.5.2 Actual underwater datasets used in the thesis 43 Chapter conclusion 48 CHAPTER 2.CLASSIFICATION OF PROPELLER SHIP SIGNALS USING THE SOLUTION OF PROPOSED SPECTRAL AMPLITUDE VARIATION COMBINED WITH A CUSTOMIZED CONVOLUTION NEURAL NETWORK 2.1 2.2 2.3 49 The formation process of the propeller ship signals during movement 49 2.1.1 Signals generated from moving propeller ships 49 2.1.2 Cavitation phenomenon 51 Proposal of spectral amplitude variation pre-processing 52 2.2.1 Drawbacks of the DEMON algorithm 52 2.2.2 Mathematical analysis of the proposed algorithm 54 2.2.3 Structure of the proposed algorithm 57 2.2.4 Evaluation of the proposed algorithm on actual ship data 60 2.2.5 Evaluation of the proposed algorithm on actual diver breath data 66 Proposal of a customized convolution neural network 69 2.3.1 Reasons for choosing convolution neural network 69 2.3.2 Proposed network configuration 70 2.3.3 Evaluation of the proposed convolution neural network complexity 2.4 74 Classification results using the combination of two proposed solutions on propeller signals 2.4.1 Classification results of DEMON-Hilbert combined with LeNet and VGG19 as control results 2.4.2 76 77 Classification results of the proposed spectral amplitude variation algorithm with LeNet and VGG19 m 78 v 2.4.3 Classification results of DEMON-Hilbert and the proposed spectral amplitude variation algorithm combined with the proposed CNN 80 Evaluation of the proposed network 83 Chapter conclusion 85 2.4.4 2.5 CHAPTER 3.CLASSIFICATION OF MARINE MAMMAL AND PROPELLER SHIP SIGNALS USING THE PROPOSED SOLUTION OF CUBIC SPLINES INTERPOLATION COMBINED WITH PROBABILITY DISTRIBUTION IN THE HIDDEN SPACE DOMAIN 88 3.1 Marine mammals communication signal structure 88 3.2 Proposal of the cubic-splines interpolation pre-processing 89 3.2.1 Theoretical basis for using cubic-splines interpolation 90 3.2.2 Interpolations on the frequency domain and proposed solutions 91 3.2.3 Structure of the proposed algorithm 3.2.4 Evaluation of the proposed algorithm on actual marine mammal data 3.3 95 97 Proposal of probability distribution in the hidden space for Siamese triple loss network 101 3.3.1 Structure of Siamese triple loss network 101 3.3.2 Structure of Rep-VGG model 102 3.3.3 Proposed solution using probability distribution in the hidden space 103 3.3.4 3.4 Proposed solution using SNN-VAE model 105 Classification results using the combination of two proposed solutions on marine mammal and propeller signals 108 3.4.1 Classification results of the proposed SNN-VAE on propeller signals 108 3.4.2 Classification results of the proposed cubic-splines interpolation and SNN-VAE on marine mammal signals 113 3.4.3 Classification results of the proposed cubic-splines interpolation and SNN-VAE on marine mammal and propeller signals 119 m vi 3.5 Chapter conclusion 125 CONCLUSION 127 LIST OF SCIENTIFIC PUBLICATION 130 REFERENCES 132 m vii LIST OF ABBREVIATIONS Ak The last convolution layer feature map c Speed of sound underwater (m/s) C Number of input channels E Orthogonal function E(z) Vector mean of random variable z f Signal frequency (Hz) F Window size of convolution network F (x) Spatial Signal sequence I Input spectrogram size L Total global average weight L Loss function of Siamese network nk (t) Cavitation noise N0 /2 Power spectral density of white noise b O The size of the network P Padding R Set of real numbers s(t) Noise generated from propeller blades S Stride Sa Salinity (per thousand) t Time of signal (second) Tk Propeller signal period Tp Temperature of enviroment (Celcius) V(z) Vector variance of random variable z x(t) Signal at the receiver zh The depth of the water (meter) αkc Weight of filter k when classifying class c γ Scale parameter on the time axis υ Position parameter on the time axis m viii Ψλ,τ Wavelets families function [.]∗ Complex conjugation := ⟨⟩ Equals function in the frequency domain ≈ Approximately σk2 Power spectral density λ Signal variance [∗] Convolution multiplication τ Signal delay ≜ Equals function by definition mathematic µB The mean of a subset ϵ Random bias of convolutional networks ACT Anisotropic chirplet transforms ADCNN Auditory perception inspired deep convolutional neural network AE Auto-encoder AG Array gain AV Amplitude variation BN Batch Norm BOC-NOAA Best of CUT-National Oceanic and Atmospheric Administration CMS Cyclic modulation Spectrum CNN Convolution neural network CSDM Cross-spectral density matrices CSI Cubic-splines interpolation CWT Continuos wavelet transform DL Deep learning DEMON Demodulation of envelope modulation on noise DT Detection threshold DWT Discrete wavelet transform ELM Extreme learning machine FC Fully connected FCNN Fully connected neural network FT Fourier Transform FFT Fast fourier transform m 132 REFERENCES Vietnamese [1] Nguyen Van Duc, Development of active sonar positioning system using ceramic materials and underwater equipment, Hanoi University of Science and Technology, 2022 [2] Do Viet Ha, Researching channel characteristic model for shallow water, Technical PhD Thesis, Hanoi University of Science and Technology, 2017 [3] Bach Nhat Hong, Research and apply a number of ultrasonic sensors to design and manufacture a system to detect and measure the parameters of airborne objects and underwater communication equipment for socialeconomic, security and defense purposes Military Academy of Science Technology, 2006 [4] Pham Van Huan, The Fundamentals of Ocean Acoustics, The Publisher of the National University of Hanoi, 2005 [5] Vu Hai Lang, The research on design and prototyping of underwater communication devices for use in combat training of Special Forces, Military Academy of Science Technology, 2019 [6] Nguyen Xuan Long, Research on adaptive field processing algorithm for passive sonar locating targets in shallow waters of Vietnam, Technical PhD Thesis, Military Academy of Science and Technology, 2017 [7] Bui Ngoc My, The textbook of fundamental theory of underwater acoustics, The Publisher of The Science and Technology, 2017 [8] Tran Phu Ninh, Research on passive sonar signal processing to improve the quality of detecting underwater targets in complex conditions, Technical PhD Thesis, Military Technical Institute, 2018 [9] Tecotec, Portable underwater signal acquisition and analysis system, Introductory report, 2019 m 133 English [10] Douglas Abraham, Underwater Acoustic Signal Processing: Modeling, Detection, and Estimation, Springer, 2019 [11] Jae-Kyun Ahn et al., “LOFAR/DEMON grams compression method for passive sonars”, The Journal of the Acoustical Society of Korea, Vol 39; (1), 2020, 38–46 [12] Michael A Ainslie, Principles of sonar performance modelling, Springer, 2010 [13] Batuhan Aktas et al., “Propeller cavitation noise investigations of a research vessel using medium size cavitation tunnel tests and full-scale trials”, Ocean engineering, Vol 120, 2016, 122–135 [14] Ann Allen et al., “A convolutional neural network for automated detection of humpback whale song in a diverse, long-term passive acoustic dataset”, Frontiers in Marine Science, Vol 8, 2021, 607321 [15] Trevor Bailey et al., “Signal detection in underwater sound using wavelets”, Journal of the American Statistical Association, Vol 93; (441), 1998, 73– 83 [16] Rabi Bastia & M Radhakrishna, Basin evolution and petroleum prospectivity of the continental margins of India, Newnes, 2012 [17] Jacob Benesty, Mohan Sondhi, Yiteng Huang, et al., Springer handbook of speech processing, Springer, 2008 [18] Paul Bentley & JTE McDonnell, “Wavelet transforms: an introduction”, Electronics & communication engineering journal, Vol 6; (4), 1994, 175– 186 [19] Paul Bierly, Scott Gallagher & John-Christopher Spender, “Innovation and learning in high-reliability organizations: A case study of United States and Russian Nuclear Attack Submarines, 1970–2000”, IEEE Transactions on Engineering Management, Vol 55; (3), 2008, 393–408 [20] Boualem Boashash, Time-frequency signal analysis and processing: a comprehensive reference, Academic press, 2015 m 134 [21] Lionel Camus et al., “Autonomous surface and underwater vehicles reveal new discoveries in the Arctic Ocean”, 2019, 1–8 [22] JCSH Cao, “Study of forecasting solar irradiance using neural networks with preprocessing sample data by wavelet analysis”, Energy, Vol 31; (15), 2006, 3435–3445 [23] Georges L Chahine et al., “Modeling of surface cleaning by cavitation bubble dynamics and collapse”, Ultrasonics sonochemistry, Vol 29, 2016, 528–549 [24] Jie Chen et al., “Underwater target recognition based on multi-decision LOFAR spectrum enhancement: A deep-learning approach”, Future Internet, Vol 13; (10), 2021, 265 [25] Hamza Cherif, SM Debbal & Fethi Bereksi-Reguig, “Choice of the wavelet analyzing in the phonocardiogram signal analysis using the discrete and the packet wavelet transform”, Expert Systems with Applications, Vol 37; (2), 2010, 913–918 [26] Davide Chicco, “Siamese neural networks: An overview”, Artificial Neural Networks, 2021, 73–94 [27] Donald Childers, David Skinner & Robert Kemerait, “The cepstrum: A guide to processing”, Proceedings of the IEEE, Vol 65; (10), 1977, 1428– 1443 [28] Jongkwon Choi, Youngmin Choo & Keunhwa Lee, “Acoustic classification of surface and underwater vessels in the ocean using supervised machine learning”, Sensors, Vol 19; (16), 2019, 3492 [29] Antonio Codarin et al., “Effects of ambient and boat noise on hearing and communication in three fish species living in a marine protected area (Miramare, Italy)”, Marine pollution bulletin, Vol 58; (12), 2009, 1880– 1887 [30] Leon Cohen, “Time-frequency distribution-a review”, A Instantaneous Frequency and Analytic Signal, Proc IEEE, Vol 77; (7), 1989, 968 m 135 [31] Andrew M Cole & Lieutenant Commander, “Automated open circuit scuba diver detection with low cost passive sonar and machine learning”, PhD thesis, Massachusetts Institute of Technology, 2019 [32] National Research Council et al., Ocean noise and marine mammals, 2003 [33] Arnab Das, Arun Kumar & Rajendar Bahl, “Marine vessel classification based on passive sonar data: the cepstrum-based approach”, IET Radar, Sonar & Navigation, Vol 7; (1), 2013, 87–93 [34] NN De Moura, JM De Seixas & Ricardo Ramos, “Passive sonar signal detection and classification based on independent component analysis”, in: Sonar Systems, InTech Makati, Philippines, 2011, 93–103 [35] Tamer Demiralp et al., “Wavelet analysis of oddball P300”, International journal of psychophysiology, Vol 39; (2-3), 2001, 221–227 [36] Jia Deng et al., “Imagenet: A large-scale hierarchical image database”, 2009, 248–255 [37] Xiaohan Ding et al., “Repvgg: Making vgg-style convnets great again”, 2021, 13733–13742 [38] Van-Sang Doan, Thien Huynh-The & Dong-Seong Kim, “Underwater acoustic target classification based on dense convolutional neural network”, IEEE Geoscience and Remote Sensing Letters, 2020 [39] Lucas Domingos et al., “A survey of underwater acoustic data classification methods using deep learning for shoreline surveillance”, Sensors, Vol 22; (6), 2022, 2181 [40] Michael Doneus et al., “Airborne laser bathymetry for documentation of submerged archaeological sites in shallow water”, Vol vol 40, 2015, 99– 107 [41] Clément Dorffer et al., “Modal estimation in underwater acoustics by data-driven structured sparse decompositions”, 2021, 286–290 [42] Emmanuel Dufourq et al., “Passive acoustic monitoring of animal populations with transfer learning”, Ecological Informatics, Vol 70, 2022, 101688 m 136 [43] WT Ellison et al., “A new context-based approach to assess marine mammal behavioral responses to anthropogenic sounds”, Conservation Biology, Vol 26; (1), 2012, 21–28 [44] Eric Ferguson et al., “Convolutional neural networks for passive monitoring of a shallow water environment using a single sensor”, 2017, 2657– 2661 [45] William Gardner, “Exploitation of spectral redundancy in cyclostationary signals”, IEEE Signal processing magazine, Vol 8; (2), 1991, 14–36 [46] Qiang Ge et al., “Side-scan sonar image classification based on style transfer and pre-trained convolutional neural networks”, Electronics, Vol 10; (15), 2021, 1823 [47] JP Ghose, Basic ship propulsion, Allied publishers, 2004 [48] Cyprien Gille, Frederic Guyard & Michel Barlaud, “Semi-supervised classification using a supervised autoencoder for biomedical applications”, arXiv preprint arXiv:2208.10315, 2022 [49] Kaliappan Gopalan, “Robust watermarking of music signals by cepstrum modification”, 2005, 4413–4416 [50] W Hackmann, “Seek and Strike: Sonar, anti-submarine warfare and the Royal Navy 1914-1954”, Majesty’s Stationery Office, 1984 [51] Xanadu C Halkias, Sébastien Paris & Hervé Glotin, “Classification of mysticete sounds using machine learning techniques”, The Journal of the Acoustical Society of America, Vol 134; (5), 2013, 3496–3505 [52] Muhammad Abdur Rehman Hashmi & Rana Hammad Raza, “Novel DEMON Spectra Analysis Techniques and Empirical Knowledge Based Reference Criterion for Acoustic Signal Classification”, Journal of Electrical Engineering & Technology, 2022, 1–18 [53] Dear CDR Havel, “SURTASS LFA Sonar SEIS/SOEIS Program Manager US Navy 4350 Fairfax Drive, Suite 600 Arlington, VA 22203”, 2018 m 137 [54] AD Hawkins & Knud Rasmussen, “The calls of gadoid fish”, Journal of the Marine Biological Association of the United Kingdom, Vol 58; (4), 1978, 891–911 [55] Kaiming He et al., “Deep residual learning for image recognition”, 2016, 770–778 [56] Gene Helfman et al., The diversity of fishes: biology, evolution, and ecology, John Wiley & Sons, 2009 [57] AP Hilar, Sonar: detector of submerged submarines, Office of the Chief of Naval Operations, 1946 [58] Nguyen Chu Hoi & Vu Hai Dang, “Building a regional network and management regime of marine protected areas in the South China Sea for sustainable development”, Journal of International Wildlife Law & Policy, Vol 18; (2), 2015, 128–138 [59] Hsieh Hou, “Cubic splines for image interpolation and digital filtering”, IEEE Transactions on acoustics, speech, and signal processing, Vol 26; (6), 1978, 508–517 [60] Gang Hu, Kejun Wang & Liangliang Liu, “Underwater Acoustic Target Recognition Based on Depthwise Separable Convolution Neural Networks”, Sensors, Vol 21; (4), 2021, 1429 [61] Gang Hu et al., “Deep learning methods for underwater target feature extraction and recognition”, Computational intelligence and neuroscience, Vol 2018, 2018 [62] Guang-Bin Huang, Qin-Yu Zhu & Chee-Kheong Siew, “Extreme learning machine: theory and applications”, Neurocomputing, Vol 70; (1-3), 2006, 489–501 [63] Guanying Huo, Ziyin Wu & Jiabiao Li, “Underwater object classification in sidescan sonar images using deep transfer learning and semisynthetic training data”, IEEE access, Vol 8, 2020, 47407–47418 m 138 [64] Forrest Iandola et al., “SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size”, arXiv preprint arXiv:1602.07360, 2016 [65] Ali K Ibrahim et al., “An approach for automatic classification of grouper vocalizations with passive acoustic monitoring”, The Journal of the Acoustical Society of America, Vol 143; (2), 2018, 666–676 [66] Muhammad Irfan et al., “DeepShip: An underwater acoustic benchmark dataset and a separable convolution based autoencoder for classification”, Expert Systems with Applications, Vol 183, 2021, 115270 [67] Aleksandar Ivic, The Riemann zeta-function: theory and applications, Courier Corporation, 2012 [68] Kajsa Johansson, “Impact of anthropogenic noise on fish behaviour and ecology”, 2011 [69] Kyong-Il Kim et al., “A method for underwater acoustic signal classification using convolutional neural network combined with discrete wavelet transform”, International Journal of Wavelets, Multiresolution and Information Processing, Vol 19; (04), 2021, 2050092 [70] Daniel Kohlsdorf, Denise Herzing & Thad Starner, “An auto encoder for audio dolphin communication”, 2020, 1–7 [71] Hamed Komari & Hassan Farsi, “Passive sonar target detection using statistical classifier and adaptive threshold”, Applied Sciences, Vol 8; (1), 2018, 61 [72] Vladimir Korenbaum et al., “Underwater Noises of Open-Circuit Scuba Diver”, Archives of Acoustics, 2020, 349–357 [73] Anton Kummert, “Fuzzy technology implemented in sonar systems”, IEEE Journal of Oceanic Engineering, Vol 18; (4), 1993, 483–490 [74] William Kuperman & Philippe Roux, Underwater acoustics, 2007, 149– 204 m 139 [75] F Ladich & HY Yan, “Correlation between auditory sensitivity and vocalization in anabantoid fishes”, Journal of Comparative Physiology A, Vol 182; (6), 1998, 737–746 [76] Werner Lauterborn, Cavitation and Inhomogeneities in Underwater Acoustics: Proceedings of the First International Conference, Gă ottingen, Fed Rep of Germany, July 9–11, 1979, Springer Science & Business Media, 2012 [77] Hoang Thanh Le et al., “Deep gabor neural network for automatic detection of mine-like objects in sonar imagery”, IEEE Access, Vol 8, 2020, 94126–94139 [78] Yann LeCun, Yoshua Bengio, et al., “Convolutional networks for images, speech, and time series”, The handbook of brain theory and neural networks, Vol 3361; (10), 1995, 1995 [79] Yann LeCun et al., “Handwritten digit recognition with a back-propagation network”, Advances in neural information processing systems, Vol 2, 1989 [80] Chang-Hsing Lee et al., “Automatic music genre classification based on modulation spectral analysis of spectral and cepstral features”, IEEE Transactions on Multimedia, Vol 11; (4), 2009, 670–682 [81] Jan van Leeuwen & Jan Leeuwen, Algorithms and complexity, Elsevier, 1990 [82] Qihu Li, “Digital sonar design in underwater acoustics”, Digital Sonar Design in Underwater Acoustics: Principles and Applications, 2012 [83] Dali Liu et al., “Design and performance evaluation of a deep neural network for spectrum recognition of underwater targets”, Computational Intelligence and Neuroscience, Vol 2020, 2020 [84] Hao Liu, Hezhen Yang & Fushun Liu, “Damage localization of marine risers using time series of vibration signals”, Journal of Ocean University of China, Vol 13; (5), 2014, 777–781 m 140 [85] Xiaoxiao Liu, Qingyang Xu & Ning Wang, “A survey on deep neural network-based image captioning”, The Visual Computer, Vol 35; (3), 2019, 445–470 [86] Xinwei Luo, Yulin Feng & Minghong Zhang, “An underwater acoustic target recognition method based on combined feature with automatic coding and reconstruction”, IEEE Access, Vol 9, 2021, 63841–63854 [87] David MacLennan & John Simmonds, Fisheries acoustics, Springer Science & Business Media, 2013 [88] Neil Macmillan & Douglas Creelman, Detection theory: A user’s guide, Psychology press, 2004 [89] Pedro Magalhães et al., “ALMA 2015: Sea trial of an underwater target localization technique using Hausdorff distance”, 2018, 1–6 [90] Carlos Mateo & Juan Antonio Talavera, “Short-time Fourier transform with the window size fixed in the frequency domain (STFT-FD): Implementation”, SoftwareX, Vol 8, 2018, 5–8 [91] Kara McMahon et al., “Horizontal Lloyd mirror patterns from straight and curved nonlinear internal waves”, The Journal of the Acoustical Society of America, Vol 131; (2), 2012, 1689–1700 [92] Patrick Miller et al., “Whale songs lengthen in response to sonar”, Nature, Vol 405; (6789), 2000, 903–903 [93] Natanael Nunes de Moura & José Manoel de Seixas, “Novelty detection in passive sonar systems using support vector machines”, 2015, 1–6 [94] Daniel T Murphy et al., “Residual Learning for Marine Mammal Classification”, IEEE Access, Vol 10, 2022, 118409–118418 [95] John Murphy, “An overview of convolutional neural network architectures for deep learning”, Microway Inc, 2016, 1–22 [96] Van Duc Nguyen & Matthias Patzold, “A method to estimate the path gains and propagation delays of underwater acoustic channels using the arrival phase information of the multipath components”, AEU-International Journal of Electronics and Communications, Vol 73, 2017, 129–138 m 141 [97] Van Duc et al Nguyen, “Modeling of Doppler power spectrum for underwater acoustic channels”, Journal of Communications and Networks, Vol 19; (3), 2017, 270–281 [98] Richard Nielsen, Sonar signal processing, Artech House, Inc., 1991 [99] Alan V Oppenheim & Ronald W Schafer, “From frequency to quefrency: A history of the cepstrum”, IEEE signal processing Magazine, Vol 21; (5), 2004, 95–106 [100] Johannes Orn, “Vibration guideline for large diesel engines”, 2014 [101] Andrew Oxenham, “How we hear: The perception and neural coding of sound”, Annual review of psychology, Vol 69, 2018, 27 [102] Sinno Jialin Pan & Qiang Yang, “A survey on transfer learning”, IEEE Transactions on knowledge and data engineering, Vol 22; (10), 2009, 1345–1359 [103] Hossein Peyvandi, Behnam Fazaeefar & Hamidreza Amindavar, “Determining class of underwater vehicles in passive sonar using hidden Markov model with Hausdorff similarity measure”, 1998, 258–261 [104] Hossein Peyvandi et al., “SONAR systems and underwater signal processing: classic and modern approaches”, SONAR systems, 2011, 173–206 [105] Tony Pitcher, The behaviour of teleost fishes, Springer Science & Business Media, 2012 [106] Alexander Pollara, Alexander Sutin & Hady Salloum, “Improvement of the Detection of Envelope Modulation on Noise (DEMON) and its application to small boats”, 2016, 1–10 [107] Ricardo Ramos-Aguilar et al., “Feature extraction from EEG spectrograms for epileptic seizure detection”, Pattern Recognition Letters, Vol 133, 2020, 202–209 m 142 [108] Joy S Reidenberg & Jeffrey T Laitman, “Discovery of a low frequency sound source in Mysticeti (baleen whales): anatomical establishment of a vocal fold homolog”, The Anatomical Record: Advances in Integrative Anatomy and Evolutionary Biology: Advances in Integrative Anatomy and Evolutionary Biology, Vol 290; (6), 2007, 745–759 [109] , Research center for Telecommunication Technologies-Universida de Vigo, 2020, url: http://atlanttic.uvigo.es/underwaternoise [110] Sam Ridgway & Donald Carder, “Nasal pressure and sound production in an echolocating white whale, Delphinapterus leucas”, in: Animal sonar, Springer, 1988, 53–60 [111] Murray Rosenblatt, “A central limit theorem and a strong mixing condition”, Proceedings of the National Academy of Sciences of the United States of America, Vol 42; (1), 1956, 43 [112] Olga Russakovsky et al., “Imagenet large scale visual recognition challenge”, International journal of computer vision, Vol 115; (3), 2015, 211– 252 [113] DJAVIDNIA Samuel, “European Maritime Safety Agency-SOUNDS: STATUS OF UNDERWATER NOISE FROM SHIPPING”, 2021 [114] David Santos-Domínguez et al., “ShipsEar: An underwater vessel noise database”, Applied Acoustics, Vol 113, 2016, 64–69 [115] Laela Sayigh et al., “The Watkins marine mammal sound database: an online, freely accessible resource”, Vol vol 27; (1), 2016, 040013 [116] Zachary Schakner & Daniel Blumstein, “Behavioral biology of marine mammal deterrents: a review and prospectus”, Biological Conservation, Vol 167, 2013, 380–389 [117] Damián Scherlis et al., “A unified electrostatic and cavitation model for first-principles molecular dynamics in solution”, The Journal of chemical physics, Vol 124; (7), 2006, 074103 m 143 [118] Romane Scherrer et al., “Boat Detection in Marina Using Time-Delay Analysis and Deep Learning”, International Journal of Data Warehousing and Mining (IJDWM), Vol 18; (2), 2022, 1–16 [119] Mary Sears & Daniel Merriman, Oceanography: The Past: Proceedings of the Third International Congress on the History of Oceanography, Held September 22-26, 1980 at the Woods Hole Oceanographic Institution, Woods Hole, Massachusetts, USA on the Occasion of the Fiftieth Anniversary of the Founding of the Institution, Springer Science & Business Media, 2012 [120] Ramprasaath R Selvaraju et al., “Grad-cam: Visual explanations from deep networks via gradient-based localization”, 2017, 618–626 [121] Mehdi Shadlou Jahromi et al., “Feature extraction in fractional Fourier domain for classification of passive sonar signals”, Journal of Signal Processing Systems, Vol 91; (5), 2019, 511–520 [122] Sheng Shen, Honghui Yang & Junhao Li, “Improved auditory inspired convolutional neural networks for ship type classification”, 2019, 1–4 [123] Sheng Shen et al., “Auditory inspired convolutional neural networks for ship type classification with raw hydrophone data”, Entropy, Vol 20; (12), 2018, 990 [124] Yvan Simard, R Lepage & Cédric Gervaise, “Anthropogenic sound exposure of marine mammals from seaways: Estimates for Lower St Lawrence Seaway, eastern Canada”, Applied Acoustics, Vol 71; (11), 2010, 1093– 1098 [125] Karen Simonyan & Andrew Zisserman, “Very deep convolutional networks for large-scale image recognition”, arXiv preprint arXiv:1409.1556, 2014 [126] G Slamnoiu et al., “DEMON-type algorithms for determination of hydroacoustic signatures of surface ships and of divers”, Vol vol 145; (8), 2016, 082013 m 144 [127] Stergios Stergiopoulos & Geoffrey Edelson, Theory and Implementation of Advanced Signal Processing for Active and Passive Sonar Systems, CRC Press, 2017 [128] Stanley Smith Stevens, John Volkmann & Edwin Broomell Newman, “A scale for the measurement of the psychological magnitude pitch”, The journal of the acoustical society of america, Vol 8; (3), 1937, 185–190 [129] Christian Szegedy et al., “Inception-v4, inception-resnet and the impact of residual connections on learning”, 2017 [130] Christian et al Szegedy, “Going deeper with convolutions”, 2015, 1–9 [131] Sasha Targ, Diogo Almeida & Kevin Lyman, “Resnet in resnet: Generalizing residual architectures”, arXiv preprint arXiv:1603.08029, 2016 [132] Shengzhao Tian et al., “Deep convolution stack for waveform in underwater acoustic target recognition”, Scientific reports, Vol 11; (1), 2021, 1–14 [133] Wei-Ho Tsai & Hao-Ping Lin, “Background music removal based on cepstrum transformation for popular singer identification”, IEEE transactions on audio, speech, and language processing, Vol 19; (5), 2010, 1196– 1205 [134] Robert Urick, Sound propagation in the sea, Department of Defense], Office of the Secretary of Defense, Defense Advanced, 1979 [135] Vahid Vahidpour, Amir Rastegarnia & Azam Khalili, “An automated approach to passive sonar classification using binary image features”, Journal of Marine Science and Application, Vol 14; (3), 2015, 327–333 [136] Matias Valdenegro-Toro, Alan Preciado-Grijalva & Bilal Wehbe, “Pretrained models for sonar images”, 2021, 1–8 [137] HL Van Trees, “Detection, Estimation and Modulation Theory New York: Wiley”, 1971 [138] Hari Vishnu & Mandar Chitre, “Robust estimation of modulation frequency in impulsive acoustic data”, IEEE Transactions on Aerospace and Electronic Systems, Vol 53; (4), 2017, 1932–1946 m 145 [139] Dezhi Wang et al., “Large-scale whale call classification using deep convolutional neural network architectures”, 2018, 1–5 [140] Xingmei Wang et al., “Underwater acoustic target recognition: a combination of multi-dimensional fusion features and modified deep neural network”, Remote Sensing, Vol 11; (16), 2019, 1888 [141] Jessica Ward et al., “New algorithms for open ocean marine mammal monitoring”, Vol vol 3, 2000, 1749–1752 [142] William Watkins, Kurt Fristrup & Mary Daher, Marine animal Sound database, tech rep., WOODS HOLE OCEANOGRAPHIC INSTITUTION MA, 1991 [143] Alain Weill, Acoustic Waves, Scattering, Springer New York, New York, 2014 [144] Peter Worcester, Discovery of Sound in the Sea (DOSITS) Website Development, tech rep., SCRIPPS INSTITUTION OF OCEANOGRAPHY LA JOLLA CA, 2013 [145] H Wu, Q Song & G Jin, “Underwater acoustic signal analysis: preprocessing and classification by deep learning”, Neural Network World, Vol 30; (2), 2020, 85–96 [146] Yuanchao XU, Zhiming CAI & Xiaopeng KONG, “Classification of Ship Radiated Noise Based on Bi-Logarithmic Scale Spectrum and Convolutional Network”, Journal of Electronics and Information, Vol 44, 2022, 1–9 [147] Xinping Yan et al., “A review of progress and applications of ship shaftless rim-driven thrusters”, Ocean Engineering, Vol 144, 2017, 142–156 [148] Haesang Yang et al., “Underwater acoustic research trends with machine learning: Active SONAR applications”, Journal of Ocean Engineering and Technology, Vol 34; (4), 2020, 277–284 [149] Haesang Yang et al., “Underwater acoustic research trends with machine learning: general background”, Journal of Ocean Engineering and Technology, Vol 34; (2), 2020, 147–154 m 146 [150] Haesang Yang et al., “Underwater acoustic research trends with machine learning: Passive SONAR applications”, Journal of Ocean Engineering and Technology, Vol 34; (3), 2020, 227–236 [151] Honghui Yang et al., “A deep convolutional neural network inspired by auditory perception for underwater acoustic target recognition”, Sensors, Vol 19; (5), 2019, 1104 [152] Tiantian Yang et al., “Vibration characteristics of compression ignition engines fueled with blended petro-diesel and Fischer-Tropsch diesel fuel from coal fuels”, Energies, Vol 11; (8), 2018, 2043 [153] Yongcan Yu et al., “Real-time underwater maritime object detection in side-scan sonar images based on transformer-YOLOv5”, Remote Sensing, Vol 13; (18), 2021, 3555 [154] Wen Zhang et al., “Multi-Features Fusion for Underwater Acoustic Target Recognition based on Convolution Recurrent Neural Networks”, 2022, 342–346 [155] Yufeng Zhang et al., “A comparison of the wavelet and short-time fourier transforms for Doppler spectral analysis”, Medical engineering & physics, Vol 25; (7), 2003, 547–557 [156] Minghang Zhao et al., “Deep residual shrinkage networks for fault diagnosis”, IEEE Transactions on Industrial Informatics, Vol 16; (7), 2019, 4681–4690 [157] Ming Zhong et al., “Detecting, classifying, and counting blue whale calls with Siamese neural networks”, The Journal of the Acoustical Society of America, Vol 149; (5), 2021, 3086–3094 [158] Pingping Zhu et al., “Deep learning feature extraction for target recognition and classification in underwater sonar images”, 2017, 2724–2731 m