本研究針對船艦聲聲場分類及辨識進行機器學習模型之應用，透過導入船艦噪聲模擬之三種不同船型種類之模擬數據至機器學習方法中的支援向量機內，使用基本支援向量機之多種類分類基本方法、貝葉斯定理以及糾錯輸出碼模型進行三種船型於不同訊雜比狀況下的數據分類分佈區域觀察以及數據點之分類種類預測，並期望能透過船艦噪聲聲場數據處理的更佳化找出更加準確的分類預測模型。
而根據本研究之研究結果可見特徵頻率對應船速於糾錯輸出碼分類模型中之分類預測結果最佳，而透過訊雜比（SNR）之提升，特徵頻率針對各式參數進行數據分類及預測辨識效果上將有一定程度的提升。

This research applies the machine learning models to the classification and identification in ship types with the acoustic data of noise. By importing the simulation data of three different ship types of noise with different signal noise ratio into the support vector machine model of the machine learning theories including multiple classes classification model, Naive Bayes classify model, and Error-correcting output codes model, we are able to classify and predict the ship types. we expect the results to be more precisely with the improvement on the ship acoustic data of noise processing in the future.
The results show that Error-correcting output codes model presents better in the prediction of ship types than other two models with the data of characteristic frequency against speed. Also, by the increasing of signal noise ratio level, it presents better for characteristic frequency against different constant.

Key words: Support Vector Machine, Ship Radiation Sound Field, Machine Learning

[1] Cristianini, N., & Shawe-Taylor, J. (2000). An introduction to support vector machines and other kernel-based learning methods. Cambridge university press.
[2] Fischell, E. M., & Schmidt, H. (2017). Supervised machine learning for estimation of target aspect angle from bistatic acoustic scattering. IEEE Journal of Oceanic Engineering, 42(4), 759-769.
[3] Ge, Q. B., & Wen, C. L. (2008, July). Relative ship positioning based on information fusion in the MITS. In 2008 International Conference on Machine Learning and Cybernetics (Vol. 7, pp. 4068-4073). IEEE.
[4] Hastie, T., Tibshirani, R., & Friedman, J. (2009). The elements of statistical learning: data mining, inference, and prediction. Springer Science & Business Media.
[5] Hu, Q., & Davis, C. (2005). Automatic plankton image recognition with co-occurrence matrices and support vector machine. Marine Ecology Progress Series, 295, 21-31.
[6] Hu, T., & Fei, Y. (2010). QELAR: A machine-learning-based adaptive routing protocol for energy-efficient and lifetime-extended underwater sensor networks. IEEE Transactions on Mobile Computing, 9(6), 796-809.
[7] Kiliç, M. M., & Akgül, Y. S. (2018, May). Ship location estimation from radar and optic images using metric learning. In 2018 26th Signal Processing and Communications Applications Conference (SIU) (pp. 1-4). IEEE.
[8] Kim, J., Song, S., & Yu, S. C. (2017, February). Denoising auto-encoder based image enhancement for high resolution sonar image. In 2017 IEEE Underwater Technology (UT) (pp. 1-5). IEEE.
[9] Kong, E. B., & Dietterich, T. G. (1995). Why Error-Correcting Output Coding Works.
[10] Li, X., Song, Y., Guo, J., Feng, C., Li, G., Yan, T., & He, B. (2017, February). Sensor fault diagnosis of autonomous underwater vehicle based on extreme learning machine. In 2017 IEEE Underwater Technology (UT) (pp. 1-5). IEEE.
[11] Liu, J., He, Y., Liu, Z., & Xiong, Y. (2014, March). Underwater target recognition based on line spectrum and support vector machine. In 2014 International Conference on Mechatronics, Control and Electronic Engineering (MCE-14). Atlantis Press.
[12] Liu, Y. (2006). Using SVM and error-correcting codes for multiclass dialog act classification in meeting corpus. In Ninth International Conference on Spoken Language Processing.
[13] Murphy, K. P. (2006). Naive bayes classifiers. University of British Columbia, 18, 60.
[14] Ogunlana, S. O., Olabode, O., Oluwadare, S. A. A., & Iwasokun, G. B. (2015). Fish classification using support vector machine. African Journal of Computing & ICT, 8(2), 75-82.
[15] Too, G. P. J., Lin, E. S., & Hsieh, Y. H. (2006, May). Source localization based on ray theory and artificial neural network. In OCEANS 2006-Asia Pacific (pp. 1-8). IEEE.
[16] Xinhua, Z., Zhenbo, L., & Chunyu, K. (2003, December). Underwater acoustic targets classification using support vector machine. In International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003 (Vol. 2, pp. 932-935). IEEE.
[17] Xu, F., Zou, Z. J., Yin, J. C., & Cao, J. (2012). Parametric identification and sensitivity Analysis for Autonomous underwater vehicles in diving plane. Journal of Hydrodynamics, 24(5), 744-751.
[18] Xu, F., Zou, Z. J., Yin, J. C., & Cao, J. (2013). Identification modeling of underwater vehicles' nonlinear dynamics based on support vector machines. Ocean Engineering, 67, 68-76.
[19] Yan, Z. (2010, July). Research on ECOC SVMs. In 2010 8th World Congress on Intelligent Control and Automation (pp. 2838-2842). IEEE.
[20] Zhang, W., Wu, Y., Wang, D., Wang, Y., Wang, Y., & Zhang, L. (2018, July). Underwater Target Feature Extraction and Classification Based on Gammatone Filter and Machine Learning. In 2018 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR) (pp. 42-47). IEEE.
[21] 徐偉哲. (2019). 結合抗爆震及減振潛艦裝備之避震墊數值分析. 成功大學系統及船舶機電工程學系學位論文, 1-91.
[22] 曾宇淩. (2016). 應用適應性時間反轉法於聲源定位與訊號還原之研究. 成功大學系統及船舶機電工程學系學位論文, 1-100.