| 朱可卿,田杰,黄海宁,张扬帆.基于深度学习的船舶辐射噪声识别研究[J].,2018,37(2):238-245 |
| 基于深度学习的船舶辐射噪声识别研究 |
| Ship-radiated noise recognition research based deep learning |
| 投稿时间：2017-04-14 修订日期：2018-02-11 |
| 中文摘要: |
| 为了改善船舶辐射噪声识别系统的性能，进一步提高船舶辐射噪声识别的正确率，本文提出了一种基于深度学习的船舶辐射噪声识别方法。该方法首先提取了船舶辐射噪声的频谱、梅尔倒谱（MFCC）系数等特征，将提取特征后的图像样本分别用于训练卷积神经网络（CNN）和深度置信网络（DBN），再对船舶辐射噪声进行识别。通过与支持向量机（SVM）的识别方法的性能对比，结果证明，深度学习的方法可以有效地提高船舶辐射噪声识别的正确率的结论。 |
| 英文摘要: |
| In order to improve the accuracy and the performance of ship-radiated noise recognition system, this paper introduce a method for ship-radiated noise recognition based deep learning. First, we extract the features of ship-radiated noise, such as spectrum feature, MFCC coefficients, etc. Then we train CNN and DBN with these feature-extracted noise image samples and recognize ship-radiated noise. After that we make a contrast with the performance of classification of SVM.The result shows that deep learning-based method in this paper can improve the accuracy of ship-radiated noise recognition effectively. |
| DOI：10.11684/j.issn.1000-310X.2018.02.009 |
| 中文关键词: 深度学习，卷积神经网络，深度置信网络，船舶辐射噪声识别 |
| 英文关键词: Deep learning, CNN, DBN, ship-radiated noise recognition |
| 基金项目: |
|
| 摘要点击次数: 2311 |
| 全文下载次数: 3201 |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |
