检索结果-内蒙古大学图书馆

Application of Ultrasonic Doppler Technology Based on wavelet threshold denoising algorithm in Fetal Heart Rate and Central Nervous System Malformation Detection

引用

WORLD NEUROSURGERY 2021年 149卷 380-387页

作者： Yan, Zhiheng Xu, Xiaoyan Wang, Yixuan Li, Tiangang Ma, Bin Yang, Lei Lu, Yan Li, Quanlin Gansu Prov Matern & Child Care Hosp Dept Ultrasound Diag Lanzhou Gansu Peoples R China

This paper discusses the clinical value of standardized early pregnancy ultrasound structure screening in the diagnosis of fetal central nervous system (CNS) malformations. In this paper, 6902 cases (8336 fetuses) of 1113 + 6 weeks of gestation (5468 cases of singleton pregnancy and 1434 cases of twin pregnancy) underwent standardized early pregnancy ultrasound structure screening. While tracking the pregnancy process and clinical outcome, we found that 13 cases of CNS malformations (10 cases of single pregnancy, 3 cases of twin pregnancy) were detected by prenatal ultrasound in 6902 cases (8336 fetuses) 1113 + 6 weeks of gestation including 5 cases of exposed brain malformations. There were 4 cases of children with cerebral sickle disease, 2 cases of forebrain without splitting, 1 case of meningocele, and 1 case of open spina bifida. There were 4 cases with other structural abnormalities and 3 cases with abnormal karyotype. Follow-up results of 13 fetuses indicated that except for 3 cases of twin malformed fetuses who continued to be pregnant after selective reduction, ultrasound results of the remaining fetuses were consistent with autopsy results after the induction of labor. For this reason, it can be concluded that standardized ultrasound structural screening during early pregnancy can detect fetal CNS malformations early and has important clinical value in reducing the birth rate of malformed fetuses and guiding obstetric treatment.

关键词： Congenital malformations Fetus Nervous system malformations Prenatal Ultrasonography wavelet threshold denoising algorithm

来源：评论

学校读者我要写书评

暂无评论

Research on on-board dynamic weighing algorithm based on two-degree-of-freedom 1/4 vehicle model

引用

INTERNATIONAL JOURNAL OF HEAVY VEHICLE SYSTEMS 2021年第6期28卷 792-807页

作者： Fu, Hongxun Zhang, Yu Gang, Xianyue Qiao, Huanbo Wang, Yan Ku, Laiyun Shandong Univ Technol Sch Transportat & Vehicle Engn 12 Zhangzhou Rd Zhangdian 255049 Zibo Peoples R China

The moving vehicle will be disturbed in many aspects, resulting in the dynamic weighing accuracy of the airborne weighing system being significantly lower than the static accuracy. In order to improve the dynamic weighing accuracy of the system, this paper designs a dynamic weighing algorithm based on wavelet threshold denoising and BP neural network. Firstly, a two-degree-of-freedom 1/4 vehicle model was built to obtain the vehicle dynamic distance data. Then, the wavelet threshold denoising algorithm was used to denoise the dynamic distance data. Finally, the BP neural network was constructed with the signal of vehicle speed, acceleration signal and denoised weight signal as the input layer to reduce the impact of the speed and acceleration on the weight signal. The results show that after the processing of dynamic weighing algorithm, the dynamic weighing error of vehicle is less than 2%, and the algorithm meets the accuracy requirements, and has high universality.

关键词： on-board weighing system two-degree-of-freedom 1 4 vehicle model dynamic weighing algorithm wavelet threshold denoising algorithm BP neural network

来源：评论

学校读者我要写书评

暂无评论

Short-term Traffic Flow Prediction Based on Improved Deep Echo State Network 40

Short-term Traffic Flow Prediction Based on Improved Deep Ec...

引用

40th Chinese Control Conference (CCC)

作者： Li, Changwu Ren, Xiao Zhang, Qingyong Xia, Huiwen Chen, Jiahua Gao, Yutong Wuhan Univ Technol Sch Automat Wuhan 430070 Peoples R China Chongqing Univ Sch Big Data & Software Engn Chongqing 401331 Peoples R China

ISBN: (纸本)9789881563804

In order to improve the processing capability of deep echo networks for short-time traffic flow prediction problems, an improved deep echo state network (IDESN) is proposed in this paper. The improved deep echo state network algorithm firstly improves the activation function in the traditional echo state network and uses a particle swarm algorithm to optimize the parameters in the new activation function. Secondly, the circular greedy algorithm is used to find the hyperparameters of the improved deep echo state network. Finally, the wavelet threshold denoising algorithm is used to denoise the traffic flow sequences. In this paper, three short-term traffic flow datasets are used for testing. The results show that the MSE values of the three datasets are reduced by 57.13%, 57.80% and 51.59%, respectively, compared with the original deep echo state network as well as the improved deep echo state network has higher accuracy.

关键词： Short-term traffic flow prediction Deep echo state network Cyclic greedy algorithm Activation function wavelet threshold denoising algorithm

来源：评论

学校读者我要写书评

暂无评论

Improving new wavelet threshold by artificial fish swarm and its application for denoising 14

Improving new wavelet threshold by artificial fish swarm and...

引用

14th IEEE International Conference on Electronic Measurement and Instruments (ICEMI)

作者： Duan Minxia Liu Xin Dong Zengshou Pang Jun Taiyuan Univ Sci & Technol Dept Elect Informat Engn Taiyuan 030024 Peoples R China

ISBN: (数字)9781728105109

ISBN: (纸本)9781728105109

Vibration signal is the main measurement signal of mechanical component fault diagnosis, and the presence of noise affects the feature extraction of the signal and the final fault diagnosis, so the test signal in practice needs to be denoised. The use of wavelet transform does not filter out the noise in the signal very well. This is because the hard threshold function is not continuous and some useful information is filtered out. There is a deviation in the soft threshold function and the noise in the signal cannot be completely filtered out. And the traditional threshold is fixed. In order to solve the problem of threshold function and threshold, this paper proposes a new threshold function, and uses artificial fish swarm algorithm to get the optimal threshold. Finally, the superiority and practicability of the method are verified by the unsteady test signal and the bearing dataset of Case Western Reserve University. From the final noise reduction result, the method can achieve better performance in noise reduction than other existing methods. The signal-to-noise ratio obtained by this method is 13%similar to 16% higher than other methods. The root mean square error is 10%similar to 41% lower than other methods.

关键词： wavelet threshold denoising algorithm artificial fish swarm algorithm threshold signal-to-noise ratio root mean square error

来源：评论

学校读者我要写书评

暂无评论

Short-term Traffic Flow Prediction Based on Improved Deep Echo State Network

Short-term Traffic Flow Prediction Based on Improved Deep Ec...

引用

第40届中国控制会议

作者： Changwu Li Xiao Ren Qingyong Zhang Huiwen Xia Jiahua Chen Yutong Gao School of Automation Wuhan University of Technology School of Big Data & Software Engineering Chongqing University

In order to improve the processing capability of deep echo networks for short-time traffic flow prediction problems,an improved deep echo state network（IDESN） is proposed in this *** improved deep echo state network algorithm firstly improves the activation function in the traditional echo state network and uses a particle swarm algorithm to optimize the parameters in the new activation ***,the circular greedy algorithm is used to find the hyperparameters of the improved deep echo state ***,the wavelet threshold denoising algorithm is used to denoise the traffic flow *** this paper,three short-term traffic flow datasets are used for *** results show that the MSE values of the three datasets are reduced by 57.13%,57.80% and 51.59%,respectively,compared with the original deep echo state network as well as the improved deep echo state network has higher accuracy.

关键词： Short-term traffic flow prediction Deep echo state network Cyclic greedy algorithm Activation function wavelet threshold denoising algorithm

来源：评论

学校读者我要写书评

暂无评论

Intelligent Terminal Data Compression Method Based on Edge Computing 2020

Intelligent Terminal Data Compression Method Based on Edge C...

引用

Proceedings of the 3rd International Conference on Information Technologies and Electrical Engineering

作者： Zijing Zhao Jingya Lu Delong Dong Jizhe Lu Guang Yang Xin Chen State Grid Tianjin Electric Power Company Tianjin China Metrology Institute China Electric Power Research Institute Beijing China

ISBN: (纸本)9781450388665

With the rapid economic and social development, China has basically achieved full coverage of smart meters. Power companies have accumulated massive amounts of smart meter measurement data, which increases the workload of data analysis and processing on the server side, and also greatly increases the pressure on the channel. In order to achieve efficient compression of metering data and reduce pressure on data analysis and processing, this paper proposes an intelligent terminal data compression method based on edge computing. Under the framework of edge computing, this method uses the empirical mode decomposition algorithm to decompose the original distribution information data, based on the wavelet threshold denoising algorithm to reduce the noise of the components, and uses the set partitioning in hierarchical trees algorithm to compress the cleaned data. Finally, an example analysis verifies the effectiveness and optimization effect of the proposed method. It reduces the pressure of the intelligent measurement system on the data transmission of the communication channel, and at the same time achieves the purpose of effectively cleaning and compressing the measurement data.

关键词： Data cleaning Edge computing Data compression wavelet threshold denoising algorithm Empirical modal decomposition

来源：评论

学校读者我要写书评

暂无评论

Online Ash Fouling Prediction for Boiler Heating Surfaces based on wavelet Analysis and Support Vector Regression

引用

ENERGIES 2020年第1期13卷

作者： Tong, Shuiguang Zhang, Xiang Tong, Zheming Wu, Yanling Tang, Ning Zhong, Wei Zhejiang Univ State Key Lab Fluid Power & Mechatron Syst Hangzhou 310027 Peoples R China Zhejiang Univ Sch Mech Engn Hangzhou 310027 Peoples R China Zhejiang Univ Sch Energy Engn Hangzhou 310027 Peoples R China

Depending on its operating conditions, traditional soot blowing is activated for a fixed time. However, low-frequency soot blowing can cause heat transfer efficiency to decrease. High-frequency soot blowing not only wastes high-pressure steam, but also abrades surface pipes, reducing the working life of a heat exchange device. Therefore, it is necessary to design an online ash fouling monitoring system to perform soot blowing that is dependent on the status of ash accumulation. This study presents an online monitoring model of ash-layer thermal resistance that reflects the degree of ash fouling. A wavelet threshold denoising algorithm was applied to smooth the thermal resistance of the ash layer calculated by the heat balance mechanism model. Thus, the variation in thermal resistance becomes more visible, which is more conducive to optimizing the operation of soot blowing. The designed Support Vector Regression (SVR) model could achieve the online prediction of thermal resistance denoising for low-temperature superheaters. Experimental analysis indicates that the prediction accuracy was 98.5% during the testing phase. By using the method proposed in this study, online monitoring of heating surfaces during the ash fouling process can be realized without adding complicated and expensive equipment.

关键词： utility boiler thermal resistance wavelet threshold denoising algorithm support vector regression (SVR)

来源：评论

学校读者我要写书评

暂无评论

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

请选择保存的检索档案：

请选择收藏分类：

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

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

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：