A New Method of Ship Type Identification Based on Underwater Radiated Noise Signals

Round 1

Reviewer 1 Report (Previous Reviewer 2)

The authors did a great job in following the suggestions and the paper is ready for being published in my opinion.

Author Response

Dear Reviewer:
        Thank you very much for your approval of the thesis! I am grateful for your suggestions during the revision process!

Reviewer 2 Report (Previous Reviewer 3)

The authors fulfilled all the requests and the paper is now complete and ready to be accepted.

In the introduction, I would only suggest a minor missing in the description of the increasing airborne noise studies is that they are consequences/reaction of scientific literature to the increasing citizens' complaints born on the subject: Licitra, Gaetano, et al. "Port noise impact and citizens’ complaints evaluation in RUMBLE and MON ACUMEN INTERREG projects." Proceedings of the 26th International Congress on Sound and Vibration, Montreal, QC, Canada. 2019; Murphy, E., & King, E. A. (2014). An assessment of residential exposure to environmental noise at a shipping port. Environment international, 63, 207-215.

Author Response

Dear Reviewer:

        Thank you very much for your approval of the paper. Regarding your comments, the following changes have been made in the second paragraph of Introduction:” Airborne noise can be detrimental to the health of navigators and people living in the vicinity of ports, people are more conscious of the safety of their living environment and are more concerned and protesting about the dangers of airborne noise [4, 5], so there is a need to monitor the airborne noise generated by ships in operation. By studying the type of vessel, it is possible to map the noise generated by the movement of the vessel and avoid noise complaints; calculating the sound power level and power spectrum when the vessel is sailing at low speed, it is possible to measure the continuous noise of the vessel and correctly estimate the noise impact [6]; through acoustic measurements, it is possible to understand the correlation between parameters such as minimum distance, speed and draft and the noise emissions from the vessel [7]; for the prevention and management of noise in ports , the development of a number of procedures and databases [8-10] allows for a refined classification of port noise sources and the identification of responsible sources from control.”

Thank you so much!

This manuscript is a resubmission of an earlier submission. The following is a list of the peer review reports and author responses from that submission.

Round 1

Reviewer 1 Report

Broad comments. The authors have made a concise overview of the topic and a brief reference to existing literature. They have indicated the main task of the paper among its motivation. Finally, they have pointed out the key message and the potential benefits of their work. As a general drawback, I could say that there is no reference to similar approaches (e.g. [1]) where wavelet transformation and AI methods have been used for nboard signal analysis.

[1] Paraskevopoulos, D., Spandonidis, C., & Giannopoulos, F. (2023). Hybrid Wavelet–CNN Fault Diagnosis Method for Ships’ Power Systems. Signals, 4(1), 150-166.

Specific comments. In general, the text is well structured and has clearly defined topics. Some comments for improvement:

2. The main novelty of the work and the outcome should be better emphasized in the introduction.

3.  Figures 7 and 8 could be refined to have better resolution. In addition, the authors could consider replacing figure 1 with relevant flowcharts.

4.  More or less all fundamental theory details that are needed are discussed and a review of the problem under evaluation is sufficient. It would be beneficial to clarify the reasoning and the behind the selection of the method used.

5. Besides the authors could confirm if parametric testing was performed to test the sensitivity of the method.

6. is it possible that the high values of accuracy are the result of overfitting? How do the authors ensure that is not?

7. Conclusions should highlight the work done and give a summary of both the novelty and the impact of the work. To that end, authors are encouraged to enhance relevant sections with discussion relevant to the limitations and restrictions they see towards the application of the method in the real world.

Author Response

1. The novelty and achievement of the article are emphasized in the introduction and conclusion
2. Readjusted the picture, added some details and increased the resolution
3. I am very sorry that I did not understand the meaning of "replacing Figure 1 with flow chart". I would be very honored if I could have your guidance next time
4. The necessity of selecting EEMD method is emphasized
5. The sensitivity of the method is verified by using data sets and self-testing data
6. The high-precision value is the result of software calculation. As for how to guarantee it, I think I need to think about more convincing algorithms

Reviewer 2 Report

The submitted paper self-declare to report a new method for ship identification based on noise signals. However, there are many aspects to be evaluated before claiming so.
First of all, the background research performed by the authors seems too narrow and limited. Then, there is a big confusion in the reader about what kind of noise the title deals with: is it underwater or airborne? Only in the methodology comes clear.

Then, a procedure needs an evaluation and validation before making it a real procedure. So, please compare the results with some other procedure or change title/writing toward a more generic approach open to future studies and developments.

Other comments are reported to the authors.

English should be improved. Errors and typos occurs.

Ref 1 is misplaced.

“With the continuous development of science and technology, the field of human exploration and activities began to extend to oceans.” I think this sentence is quite useless as a start.

Avoid any brands.

I would suggest to separate chapter “The algorithms” from “Results”.

Author Response

1. The section "Underwater acoustic target Recognition Method" is added to the research background
2. Modify "Ship noise" to "Ship radiated noise" to show that it is underwater noise
3. The position of references has been adjusted
4. Change Algorithm to Part 2 and Result to Part 3
5. The first method "MSAM principle high and low frequency energy difference" is compared with "traditional method high and low frequency energy difference"

Reviewer 3 Report

The submitted work is dealing with an interesting topic, but the validity of the work still needs to be proven. Furthermore, there are many concepts to be expanded, writing to be revised and parts to be fixed that pend me says that the paper must be deeply revised.

 

Reference are too Chinese centric.

Avoid the use of “we” in scientific writing and check some typos or wrong formatting. E.g. “basis” In the first line of abstract. English is too colloquial and must be revised.

The possible needs of the submitted work should be better explained. This needs also more references, from an applicative point of view.

In the introduction, while only discovering later that the paper is dealing with underwater acoustics, I still believe that a paragraphs mentioning noise emitted outside is important and is finally receiving lot of attentions. A period like the following would help: “In the recent years some authors finally investigated airborne sound emitted by moving ships (Bernardini, M.; et al. Noise Assessment of Small Vessels for Action Planning in Canal Cities. Environments 2019, 6, 31.; Fredianelli, L.; et al., Pass-by characterization of noise emitted by different categories of seagoing ships in ports. Sustainability. 2020, 12(5), 1740; Nastasi, Marco, et al. "Parameters affecting noise emitted by ships moving in port areas." Sustainability 12.20 (2020): 8742; Badino, Aglaia, et al. "Airborne noise emissions from ships: Experimental characterization of the source and propagation over land." Applied Acoustics 104 (2016): 158-171; Borelli, Davide. "Maritime Airborne Noise: Ships and Harbours." International Journal of Acoustics and Vibration, vol. 24, no. 4, Dec. 2019, p. 631.; Schiavoni, Samuele, et al. "Airborne Sound Power Levels and Spectra of Noise Sources in Port Areas." International Journal of Environmental Research and Public Health 19.17 (2022): 10996; Fredianelli, Luca, et al. "Source characterization guidelines for noise mapping of port areas." Heliyon 8.3 (2022): e09021; Fredianelli, Luca, et al. "Classification of noise sources for port area noise mapping." Environments 8.2 (2021): 12. Di Bella, Antonino, and Francesca Remigi. "Prediction of noise of moored ships." Proceedings of Meetings on Acoustics ICA2013. Vol. 19. No. 1. Acoustical Society of America, 2013. VUKIĆ, L., PERONJA, I., & MANDIĆ, N. (2022). Significance and Current Regulations of External Airborne Noise from Ships. WIT Transactions on The Built Environment, 212, 139-148.  Vukić, L., Peronja, I., & Glavinović, R. (2022). Multi-Faceted Analysis of Airborne Noise Impact in the Port of Split (I). Journal of Marine Science and Engineering, 10(10), 1564.)”

Figures have bad quality. Sometimes, they even have no labels and units.

Eq 7. “=” looks like in a footnote format.

Always put a space between digits and units.

Please evaluate and report uncertainties.

Last chapter should be named conclusions.

Author Response

1. The references have been modified
2. Corrected some typos and wrong formats in the article
3. The necessity of the article is explained in the introduction and conclusion
4. Pictures and figures were modified and units were added
5. The last chapter is named Conclusion
6. Leave a space between numbers and units

Round 2

Reviewer 2 Report

The adjustments provided by the authors are not sufficient and the status of the paper remains as previously.

I kindly suggest the authors to work harder on fixing the previous issues.

Ship radiated noise is not enoug to differntiate beteween airborne sounds and underwater ones.

Author Response

1. The authors recognize the reviewer's concern about whether the noise is underwater or aerial and have redefined it in the title and introduction. It is clearly stated that the subject of this paper is underwater radiated noise. In "1. Introduction" it is stated that "Ships played an important role in marine development and exploration. divided into airborne noise and underwater radiated noise, both of which have an impact on the marine environment."

 

2. With regard to the evaluation and validation of the procedure, two feature extraction methods are proposed in this paper, namely the "MSAM-based high-low frequency energy difference method" and the "sensitive IMF variance mean method". The difference between the two methods lies in the different scales of the high and low frequencies. The results are presented in this paper to verify the reliability of the proposed method. The results of the comparison between the two are presented to verify the reliability of the proposed method. The validity of the method is demonstrated by the application of the "sensitive IMF variance averaging method" to the noise collected by fishing vessels. At the end of the paper, the relationship between the distance and the feature extraction method is also investigated to verify the effectiveness of the method.

 

3. With regard to English expression and grammar, as the text itself is still highly uncertain, we would like to ask for professional help in touching up the text once its structure and content have been determined, and we hope you will understand.

Reviewer 3 Report

No significant changes have been applied to the paper. The few done looks like performed in a fast and not detailed way.

The confusion to readers is still present, the refernces have not been added. Please read back the previous round of revisions.

Author Response

1. With regard to the need to explain the submitted work from an application point of view, the authors have included in the Introduction the need for underwater radiated noise from ships in terms of application: “Underwater radiated noise signal from ships includes information on the tonnage and type of ship [4], and special types of ships need to reduce radiated noise in order to per-form their tasks, such as fishing vessels in order to reduce the risk to marine life [5]. Detection and tracking based on the sound of the ship facilitates the identification of noise sources for underwater environmental monitoring systems and the control of marine traffic [6-8].“

 

2. The main contributions of this study are further specified in the Introduction: “The main contributions of this study are as follows: 1) A method for ship type identification using underwater noise is investigated. As noise travels much further underwater than in air, the method is of practical value for ship monitoring. 2) EEMD has the feature of adaptive decomposition, which overcomes the limitation of parameter selection and window function selection; 3) based on the traditional high-low frequency energy difference method, the high-low frequency energy difference method based on the MSAM principle has better performance; 4) on the merit of sensitive IMF, the sensitive IMF variance mean method is proposed; 5) the distance for feature extraction is investigated effect of recognition methods.”

 

3. Ship noise is divided into airborne noise and underwater radiated noise, both of which are important for environmental protection and monitoring. However, the focus of this paper is on ship type identification and monitoring, while ship noise propagates much further underwater than in air, and the signal-to-noise ratio of hydroacoustic signals at greater depths is higher than that of signals in air, so the research will focus on underwater noise signals.

 

4. The authors have accepted the reviewers' suggestions to add and update references, adding five and replacing six to make them more comprehensive, representative and innovative.

 

5. With regard to English expression and grammar, as the article itself is still subject to considerable uncertainty, the author would like to ask for professional help in touching up the article once its structure and content have been determined, and hopes to receive your understanding.

Round 3

Reviewer 2 Report

Even with the new review round, the paper does not seems properly put in the right context with respect to the scientific background. Without that, the novelty of the work can't emerge and readers cannot understand why the authors would have investigated the argument.

Please expand also the conclusions and possible implications.

Author Response

Dear reviewer, regarding the scientific background, I would like to make the following remarks as my reply:

First, on the issue of underwater acoustic channel, underwater acoustic signal propagation in the seabed will be affected by seabed reflection, ocean reverberation, sea water medium, transmission loss and other related factors, so the issue of underwater acoustic channel is relatively complex, which needs to be studied as a special subject. Therefore, we here regard the transmission channel of ship radiated noise signal as the same. The related problems of underwater acoustic channel are not considered;

Second, through investigation and research, it is found that the operating distance of sonar is correlated with the season and depth, etc. In practical application, the passive detection distance is generally less than 10 kilometers, while the active detection distance can reach 20 kilometers. In this paper, due to the limitation of acquisition conditions, it is difficult to obtain ship radiated noise signal at the above distance, so ship radiated noise in Deepship data set is selected, and the farthest distance is 2km. From a military point of view, the study has some limitations, but from environmental protection and port planning, the distance study is sufficient.

Thirdly, for classification and recognition of ship radiated noise, the main purpose of this paper is to propose a feature extraction method to verify the accuracy of relevant methods. In the future, this method can be combined with neural network and other contents to realize simple and convenient type recognition, or even ship class recognition or individual recognition under the same type.

The above instructions are indicated in the conclusion.

Reviewer 3 Report

The suggestion about introduction and references part was surely not followed by the authors. They declared to have improved it, but I see  no references at all about noise emitted by vessel outside water, and a mention to the argument at all. I truly believe it is important to give that argument a couple lines.

Author Response

Dear reviewer, thank you for pointing out the problems about air and ship noise. Now we have added the relevant literature about air and ship noise, and also explained the content of air borne noise in the introduction:”Airborne noise can have an impact on human health and the monitoring of airborne noise generated by ship operations is required for acoustic comfort and port planning. By studying different types of ships operating at different speeds in ports, it is possible to map the noise generated by ship movements and avoid noise complaints [1, 2]; calculating the sound power levels and power spectra of ships at low speeds, it is possible to measure the continuous noise of five types of ships and correctly estimate the noise impact [3]; acoustic measurements make it possible to understand the relationship between parameters such as minimum distance, speed and draught and correlation of ship noise emissions [4]; for the prevention and management of port noise, procedures and databases have been developed [5-7], which allow for a refined classification of port noise sources and the identification of responsible sources from control.”