All Issue

2025 Vol.44, Issue 6 Preview Page

Research Article

Analysis of segment length impact on ship classification model performance using underwater acoustic signals

수중 음향 신호의 세그먼트 길이가 선박 분류 모델 성능에 미치는 영향 분석

Gyuri Lee1
,
Soobin Yim1
,
SeokHwan Choi1
,
Yun Jang1*
이 규리1
,
임 수빈1
,
최 석환1
,
장 윤1*
1세종대학교 인공지능융합학과 지능형드론 융합전공
*Corresponding Author
30 November 2025. pp. 600-607
PDF XML Citation
Abstract

Underwater acoustic classification plays a key role in maritime vessel detection and marine species identification. This study experimentally analyzes the impact of segment length in input data on the performance of underwater vessel classification models. Using two representative underwater acoustic datasets, ShipsEar and DeepShip, collected in real marine environments, input signals were segmented into durations ranging from 1 s to 11 s. Mel-Frequency Cepstral Coefficient (MFCC) were extracted from each segment and used to train convolutional neural networks for classification. The experimental results show that segment length significantly affects performance metrics such as precision, recall, F1-score, and False Alarm Rate (FAR), and that the optimal segment length varies depending on the structural characteristics of each dataset. This study provides empirical evidence that arbitrary segment length settings can influence classification performance, and offers a practical guideline for preprocessing underwater acoustic data.

Keywords
Underwater acoustic classification
Underwater acoustic target recognition
Segment length
Passive sonar

수중 음향 분류는 해양 선박 식별, 해양 생물분류 분야에서 핵심 기술로 활용되고 있다. 본 연구에서는 수중 선박 음향 분류에서 입력 데이터의 세그먼트 길이가 분류 성능에 미치는 영향을 실험적으로 분석하였다. 실제 해양 환경에서 수집된 ShipsEar과 DeepShip 데이터셋을 대상으로, 1 s부터 11 s까지 다양한 세그먼트 길이로 데이터를 분할하고, Mel-Frequency Cepstral Coefficient(MFCC) 기반 특징을 추출한 뒤 합성곱 신경망을 이용해 분류 성능을 비교하였다. 실험 결과, 세그먼트 길이에 따라 정밀도, 재현율, F1-score, False Alarm Rate(FAR) 평가 지표에서 유의미한 차이가 발생하였으며, 데이터셋의 구조적 특성에 따라 최적의 길이가 상이하게 나타났다. 본 연구는 기존에 임의로 설정되던 세그먼트 길이가 분류 성능에 미치는 영향을 실증적으로 검토하였으며, 수중 음향 데이터 전처리 과정에 활용할 수 있는 실험적 기준을 제시한다.

키워드
수중 음향 분류
수중 음향 표적 식별
세그먼트 길이
수동 소나
References
1

C. Erbe, S. A. Marley, R. P. Schoeman, J. N. Smith, L. E. Trigg, and C. B. Embling, “The effects of ship noise on marine mammals—a review,” Front. Mar. Sci. 6, 606 (2019).

10.3389/fmars.2019.00606
2

C. Chen and J. Fu, “Recognition method of underwater target radiated noise based on convolutional neural network,” Acoust. Technol. 38, 424 (2019).

3

X. Ke, F. Yuan, and E. Cheng, “Underwater acoustic target recognition based on supervised feature- separation algorithm,” Sensors, 18, 4318 (2018).

10.3390/s1812431830544540PMC6308667
4

F. Hong, C. Liu, L. Guo, F. Chen, and H. Feng, “Underwater acoustic target recognition with a residual network and the optimized feature extraction method,” Appl. Sci. 11, 1442 (2021).

10.3390/app11041442
5

X. Luo, L. Chen, H. Zhou, and H. Cao, “A survey of underwater acoustic target recognition methods based on machine learning,” J. Mar. Sci. Eng. 11, 384 (2023).

10.3390/jmse11020384
6

D. Santos-Domínguez, S. Torres-Guijarro, A. Cardenal-López, and A. Pena-Gimenez, “ShipsEar: An underwater vessel noise database,” Appl. Acoust. 113, 64-69 (2016).

10.1016/j.apacoust.2016.06.008
7

M. Irfan, J. Zheng, S. Ali, M. Iqbal, Z. Masood, and U. Hamid, “DeepShip: An underwater acoustic benchmark dataset and a separable convolution based autoencoder for classification,” Expert Syst. Appl. 183, 115270 (2021).

10.1016/j.eswa.2021.115270
8

A. Mohammadi, T. Kelhe, D. Carreiro, A. Van Dine, and J. Peeples, “Cross-domain knowledge transfer for underwater acoustic classification using pre-trained models,” Proc. IEEE OCEANS Brest, 1-6 (2025).

10.1109/OCEANS58557.2025.11104545
9

J. Ritu, E. Barnes, R. Martell, A. Van Dine, and J. Peeples, “Histogram layer time delay neural networks for passive sonar classification,” Proc. IEEE Workshop Appl. Signal Process. Audio Acoust. 1-5 (2023).

10.1109/WASPAA58266.2023.10248102
10

C. Yan, S. Yan, T. Yao, Y. Yu, G. Pan, L. Liu, and J. Bai, “A light weight network based on multi-scale asymmetric convolutional neural networks with attention mechanism for ship-radiated noise classification,” J. Mar. Sci. Eng. 12, 130 (2024).

10.3390/jmse12010130
11

S. Shen, H. Yang, J. Li, G. Xu, and M. Sheng, “Auditory inspired convolutional neural networks for ship type classification with raw hydrophone data,” Entropy, 20, 990 (2018).

10.3390/e2012099033266713PMC7512589
12

P. Matias, D. Folgado, H. Gamboa, and A. Carreiro, “Time series segmentation using neural networks with cross-domain transfer learning,” Electronics, 10, 1805 (2021).

10.3390/electronics10151805
13

A. Pezeshki, M. R. Azimi-Sadjadi, L. L. Scharf, and M. Robinson, “Underwater target classification using canonical correlations,” Proc. IEEE Oceans, 948-955 (2003).

10.1109/JOE.2007.907926
14

A. Pezeshki, M. R. Azimi-Sadjadi, and L. L. Scharf, “Undersea target classification using canonical correlation analysis,” IEEE J. Ocean. Eng. 32, 948-955 (2007).

10.1109/JOE.2007.907926
15

B. Beckler, A. Pfau, M. Orescanin, S. Atchley, N. Villemez, J. E. Joseph, C. W. Miller, and T. Margolina, “Multilabel classification of heterogeneous underwater soundscapes with Bayesian deep learning,” IEEE J. Ocean. Eng. 47, 1143-1154 (2022).

10.1109/JOE.2022.3177850
16

L. Zhang, D. Wu, X. Han, and Z. Zhu, “Feature extraction of underwater target signal using mel frequency cepstrum coefficients based on acoustic vector sensor,” J. Sens. 2016, 1-11 (2016).

10.1155/2016/7864213
17

M. Sahidullah and G. Saha, “Design, analysis and experimental evaluation of block based transformation in MFCC computation for speaker recognition,” Speech Commun. 54, 543-565 (2012).

10.1016/j.specom.2011.11.004
18

Y. LeCun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard, and L. D. Jackel, “Backpropagation applied to handwritten zip code recognition,” Neural Comput. 1, 541-551 (1989).

10.1162/neco.1989.1.4.541
19

Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-based learning applied to document recognition,” Proc. IEEE, 86, 2278-2324 (1998).

10.1109/5.726791
20

W. Dai, C. Dai, S. Qu, J. Li, and S. Das, “Very deep convolutional neural networks for raw waveforms,” Proc. IEEE ICASSP, 421-425 (2017).

10.1109/ICASSP.2017.7952190
21

Y. Wang, H. Zhang, and W. Huang, “Fast ship radiated noise recognition using three-dimensional mel-spectrograms with an additive attention based transformer,” Front. Mar. Sci. 10, 1280708 (2023).

10.3389/fmars.2023.1280708
22

L. Zhufeng, L. Xiaofang, W. Na, and Z. Qingyang, “Present status and challenges of underwater acoustic target recognition technology: A review,” Front. Phys. 10, 1044890 (2022).

10.3389/fphy.2022.1044890
Information
  • Publisher :The Acoustical Society of Korea
  • Publisher(Ko) :한국음향학회
  • Journal Title :The Journal of the Acoustical Society of Korea
  • Journal Title(Ko) :한국음향학회지
  • Volume : 44
  • No :6
  • Pages :600-607
  • Received Date : 2025-07-24
  • Revised Date : 2025-10-13
  • Accepted Date : 2025-11-17
  • DOI :https://doi.org/10.7776/ASK.2025.44.6.600
Journal Informaiton The Journal of the Acoustical Society of Korea The Journal of the Acoustical Society of Korea
E-Book
  • scopus_JASK
  • ESCI_JASK
  • Google scholar_JASK
  • NRF
  • KOFST
  • KISTI Current Status
  • KISTI Cited-by
  • crosscheck
  • orcid
  • ccl
Journal Informaiton Journal Informaiton - close