Page 185 - 《应用声学》2025年第1期

第 44 卷 第 1 期 聂磊鑫等： 高斯过程辅助的船舶辐射噪声分类算法 181

3-D Mel-spectrogram and data augmentation[J]. Applied Applied Acoustics, 2016, 113: 64–69.
Acoustics, 2021, 178: 107989. [18] Nie L X, Li C, Wang H B, et al. Open-set recognition
[13] 李理, 李向欣, 殷敬伟. 基于生成对抗网络的舰船辐射噪声分 for deep neural networks-based underwater acoustic tar-
类方法研究 [J]. 电子与信息学报, 2022, 44(6): 1974–1983. get classification[C]//OCEANS 2021: San Diego–Porto.
Li Li, Li Xiangxin, Yin Jingwei. Research on classification September 20-23, 2021. San Diego, CA, USA. IEEE, 2021:
algorithm of ship radiated noise data based on generative 1–5.
adversarial network[J]. Journal of Electronics & Informa- [19] 倪俊帅, 赵梅, 胡长青. 基于 DNN 和改进 K-means 的船舶辐
tion Technology, 2022, 44(6): 1974–1983. 射噪声开集识别方法 [J]. 声学技术, 2022, 41(3): 382–387.
[14] de Castro Vargas Fernandes J, de Moura N N Jr, de Seixas Ni Junshuai, Zhao Mei, Hu Changqing. DNN and im-
J M. Deep learning models for passive sonar signal classi- proved K-means based ship noise open set recognition[J].
fication of military data[J]. Remote Sensing, 2022, 14(11): Technical Acoustics, 2022, 41(3): 382–387.
2648. [20] Zhang H, Cissé M, Dauphin Y N, et al. mixup: Beyond
[15] Mohri M, Rostamizadeh A, Talwalkar A. Foundations of empirical risk minimization[C]//6th International Confer-
machine learning[M]. Cambridge, MA: MIT Press, 2018. ence on Learning Representations. Vancouver, Canada,
[16] Rasmussen C E, Williams C K I. Gaussian processes 2018: 1–13.
for machine learning[M]. Cambridge, Mass.: MIT Press, [21] He K, Zhang X, Ren S, et al. Deep residual learn-
2006. ing for image recognition[C]//Proceedings of the IEEE
[17] Santos-Domínguez D, Torres-Guijarro S, Cardenal-López Conference on Computer Vision and Pattern Recognition
A, et al. ShipsEar: An underwater vessel noise database[J]. (CVPR). Las Vegas, NV, USA: IEEE, 2016: 770–778.