计算机科学 ›› 2012, Vol. 39 ›› Issue (11): 233-236.

• 人工智能 • 上一篇    下一篇

基于多分类支持向量数据描述的噪声源识别研究

高志华,贵可荣   

  1. (海军工程大学计算机工程系 武汉430033)
  • 出版日期:2018-11-16 发布日期:2018-11-16

Study on Acoustic Sources Identification Based on Multi-SVDD

  • Online:2018-11-16 Published:2018-11-16

摘要: 提出了基于multi-SVDD(multi-support vector data description)的水下航行器噪声源识别方法,从而避免了 传统噪声源识别方法无法识别突变噪声源的不足。利用功率谱特征提取方法处理采样到的机械振动噪声信号,将 SVDI〕扩展到多类分类来识别多类噪声源。实验表明,该方法能够有效识别水下航行器的各类典型噪声源,并能及时 发现突变噪声源。

关键词: 支持向量数据描述,多类分类,噪声源识别

Abstract: Traditional acoustic sources identification ways have low recognition rate on abrupt acoustic sources. A new method based on multi-support vector data description to the underwater vehicles acoustic sources identification was proposed.

Key words: Support vector data description, Multi-classification, Acoustic sources identification

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!