| 张扬,杨建华,侯宏.基于EK-NN的水声目标识别算法研究[J].声学技术,2016,35(1):15~19 |
| 基于EK-NN的水声目标识别算法研究 |
| K-NN based underwater acoustic target recognition algorithm |
| 投稿时间：2015-05-06 修订日期：2015-09-15 |
| DOI：10.16300/j.cnki.1000-3630.2016.01.004 |
| 中文关键词: 水声目标识别 证据理论 证据K类近邻算法(EK-NN) 特征向量 组合规则 |
| 英文关键词: underwater acoustic target recognition evidence theory Evidence K-Nearest Neighbor(EK-NN) feature vector combination rule |
| 基金项目: |
|
| 摘要点击次数: 1414 |
| 全文下载次数: 1445 |
| 中文摘要: |
| 针对水声目标信号复杂、样本获取难度大且富含不确定信息的问题,研究了一种新的证据K类近邻识别算法(Evidence K Nearest Neighbor, EK-NN).首先在水声目标的各类训练样本中,根据特征距离大小选取待识别目标的K近邻,并构造其基本置信指派函数.然后使用证据理论中的Dempster-Shafer(D-S)规则对各类别下的近邻证据进行组合,最后再应用冲突置信的比例分配规则5(Redistribute Conflicting mass proportionally rule5, PCR5)将所有类别的组合证据进行融合,并根据融合结果和所设立的分类规则来判断目标的类别属性.根据水声目标实测数据,将新算法与其他几种常见的水声目标识别算法进行了对比分析,结果表明新算法能有效提高识别的准确率. |
| 英文摘要: |
| In underwater acoustic target recognition, the target signal is usually complex and the samples which are difficult to obtain also have some uncertain information. In order to effectively solve these problems, a new underwater acoustic target recognition algorithm based on evidence theory (EK-NN) is presented. In this new method, the basic belief assignments (bba's) are determined by using the feature distances between the object and its K nearest neighbors in each class of the training set, and then the bba's in each class are combined with Dempster-Shafer (D-S) rule. Finally the combined results in each class are fused by Redistribute conflicting mass proportionally rule5 (PCR5), and the object can be recognized by the fusion result and the classification rule presented in this paper. Several experiments based on real underwater acoustic data sets are made to test the effectiveness of EK-NN in comparison with some other methods. The results indicate that EK-NN can effectively improve the recognition accuracy. |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |
|
|
|
