检索结果-南通市图书馆

第十一届中国卫星导航年会

作者： Xin Zhang Guomei Zhang Hua Wang Guobing Li School of Information and Communications Engineering Xi’an Jiaotong University State Key Laboratory of Geo-information Engineering Xi’an Research Institute of Surveying and Mapping

Under the complex war environment based on Global Navigation Satellite Systems(GNSS), suppression interference and spoofing interference would be used in combination by enemy. Thus, the difficulty of

关键词： GNSS Suppression Interference Spoofing Interference classification and recognition Back Propagation Neural Network

来源： cnki会议 cnki会议 cnki会议评论

在线全文

学校读者我要写书评

暂无评论

A novel feature extraction method for ship-radiated noise

引用

Defence Technology（防务技术） 2022年第4期18卷 604-617页

作者： Hong Yang Lu-lu Li Guo-hui Li Qian-ru Guan School of Electronic Engineering Xi’an University of Posts and TelecommunicationsXi’anShaanxi710121China

To improve the feature extraction of ship-radiated noise in a complex ocean environment,a novel feature extraction method for ship-radiated noise based on complete ensemble empirical mode decomposition with adaptive selective noise(CEEMDASN) and refined composite multiscale fluctuation-based dispersion entropy(RCMFDE) is *** is proposed in this paper which takes into account the high frequency intermittent components when decomposing the *** addition,RCMFDE is also proposed in this paper which refines the preprocessing process of the original signal based on composite multi-scale ***,the original signal is decomposed into several intrinsic mode functions(IMFs)by *** distribution ratio(EDR) and average energy distribution ratio(AEDR) of all IMF components are ***,the IMF with the minimum difference between EDR and AEDR(MEDR)is selected as characteristic *** RCMFDE of characteristic IMF is estimated as the feature vectors of ship-radiated ***,these feature vectors are sent to self-organizing map(SOM) for classifying and *** proposed method is applied to the feature extraction of ship-radiated *** result shows its effectiveness and universality.

关键词： Complete ensemble empirical mode decomposition with adaptive noise Ship-radiated noise Feature extraction classification and recognition

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

classification of Universal Applied Datasets Based on Convolutional Neural Networks

Classification of Universal Applied Datasets Based on Convol...

引用

第37届中国控制会议

作者： Xingwen Zhao Feng Ye Lijun Hang School of Automation Hang Zhou Dianzi University

This work focuses on the design of convolutional neural network to achieve precise classification of universal dataset in specific applications. The paper presented a high-resolution application-oriented image dataset with universal characteristics. The dataset includes a total of 20000 images of 12 categories, currently covering the most common categories of digital products, transportation, and animals. Aiming at the dataset, the methods of rotation, translation and flip, were adopted for data augmentation to enrich the diversity of dataset and to prevent the over-fitting problem. A total of eight-weight neural network was designed, including five convolutional neural networks and three full-connection layers. This paper uses the design of overlapping maximum pooling layer to better reflect the details of the information and to minimize the data loss of the pictures. The convolution kernel size of 3 * 3 was finally determined for feature extraction, which had been shown to be effective in alleviating the under-fitting problem in the early stage. It was proved that the Rectified Linear Units with a low initial learning rate of Stochastic Gradient Descent strategy would get better accuracy. And l2 regularization as well as dropout was used to optimize the model, which effectively prevented the over-fitting problem occurring in the latter part of the model training. The proposed optimal method and network configuration help to obtain an average accuracy of 94% on the dataset, and can precisely classify the transportation as well as digital products in specific applications, and also achieve the classification of the most common animal categories.

关键词： convolution neural network universal dataset classification and recognition

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：