检索结果-内蒙古大学图书馆

International Conference of Electrical, Electronic and Networked Energy systems, EENES 2024

作者： Qin, Xu Wang, Wei School of Electronic and Information Engineering Tiangong University Tianjin China Tianjin Key Laboratory of Optoelectronic Detection Technology and System Tianjin China Engineering Research Center of Ministry of Education for High Power Semiconductor Lighting Application System Tianjin China

ISBN: (纸本)9789819620456

The vigorous development of new energy vehicles has brought new opportunities and challenges to related industries. In order to gain greater competitive advantages, major automobile manufacturers have begun to focus on using motor current ripple signals directly to achieve various functions in a cheaper and more integrated way. However, the current ripple signal generated when the motor rotates is mixed with a lot of noise. If it is to be put into practical application, it needs to be denoised first, such as the improved wavelet threshold denoising method studied in this paper. First, the denoising principle and the shortcomings of the traditional method are introduced, and the design of the improved method is given on this basis. Subsequently, verification is conducted using simulated signals and actual current ripple signals, with SNR (Signal to Noise Ratio) and RMSE (Root Mean Square Error) used as quantitative evaluation criteria for comparing and analyzing the results. Finally, the experiments have confirmed that the improved threshold method proposed in this paper outperforms traditional methods in noise removal, proving its significance and value for further research. © Beijing Paike Culture Commu. Co., Ltd. 2025.

关键词： Noise abatement

来源：评论

学校读者我要写书评

暂无评论

Improved ADRC PMSM Control system Based on Compensation Function Observer

Improved ADRC PMSM Control System Based on Compensation Func...

引用

International Conference of Electrical, Electronic and Networked Energy systems, EENES 2024

作者： Wu, Chuangyi Wang, Wei School of Electronic and Information Engineering Tiangong University Tianjin China Tianjin Key Laboratory of Optoelectronic Detection Technology and System Tianjin China Engineering Research Center of Ministry of Education for High Power Semiconductor Lighting Application System Tianjin China

ISBN: (纸本)9789819620791

The Adaptive Disturbance Rejection Control (ADRC) is widely used in nonlinear systems such as Permanent Magnet Synchronous Motors (PMSM) due to its adaptability, strong robustness, and ease of implementation. However, traditional ADRC performs poorly in high-order nonlinear systems, as its performance mainly depends on the nonlinear function representing the total disturbance. To address this issue, this paper proposes an improved ADRC based on the Compensation Function Observer (CFO). The CFO belongs to the type III system, exhibiting significantly improved signal processing performance compared to the type I Extended State Observer (ESO), and it can attenuate the influence of the nonlinear function in the compensation stage. Additionally, in order to alleviate the difficulty of parameter tuning in ADRC, fuzzy control is introduced in the error feedback loop. The feasibility of the proposed method is verified by establishing a Matlab/Simulink simulation model. The simulation results demonstrate that, compared to traditional ADRC, the new ADRC exhibits better response speed and disturbance rejection for common signals. © Beijing Paike Culture Commu. Co., Ltd. 2025.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Analysis of particle scattering characteristics with different transparency based on interferometric particle imaging 15

Analysis of particle scattering characteristics with differe...

引用

15th International Conference on Information Optics and Photonics, CIOP 2024

作者： Sun, Jinlu Wang, Xiaoyang Song, Xiaomin Guo, Zhicheng Chu, Yunpeng Chen, Yiyao Li, Yuqiang Zhang, Cheng Shi, Jia Miao, Changyun School of Electronic and Information Engineering Tiangong University Tianjin300387 China Tianjin Key Laboratory of Optoelectronic Detection Technology and System Tianjin300387 China Life and Health Intelligent Research Institute Tianjin University of Technology Tianjin300384 China

ISBN: (数字)9781510686175

ISBN: (纸本)9781510686168

The scattering characteristics of particles with different transparency are investigated using interferometric particle imaging. Based on optical transfer matrix theory, the interference defocusing images formed by different number of emitting points are simulated. We found that the speckle frequency of the defocusing image will increase when the number of the emitting points increases. The microscopic and interference images of polystyrene, cell and sand particles are obtained and proved that the lower the transparency of the particle, the higher the speckle frequency of the defocusing image. The experimental results showed agreement with the simulation results. This conclusion can be used to judge the transparency of particles and to distinguish particles in mixed particle field. © 2024 SPIE.

关键词： Speckle

来源：评论

学校读者我要写书评

暂无评论

Region Segmentation of Retina OCT Image Layer Based on MS-UNet 22

Region Segmentation of Retina OCT Image Layer Based on MS-UN...

引用

8th International Conference on Computing and Artificial Intelligence, ICCAI 2022

作者： Wu, Jun Liu, Shuang Xiao, Zhitao Zhang, Fang Geng, Lei School of Electronics and Information Engineering Tianjin Key Laboratory of Optoelectronic Detection Technology and System TianGong University Tianjin300387 China School of Life Sciences Tianjin Key Laboratory of Optoelectronic Detection Technology and System TianGong University Tianjin300387 China

ISBN: (纸本)9781450396110

The accurate segmentation of the retinal layer is a key link in the analysis of retinal OCT images. If the various tissue layers of the retina can be accurately segmented from the OCT image, it will help doctors make a more accurate and rapid diagnosis. Aiming at the high complexity of the features of each layer of the retinal OCT image and the low accuracy of the existing segmentation methods, this paper designs an improved U-Net model, MS-UNet (Multiscale Skip-UNet), which realizes the precise segmentation of seven retinal layers. To prevent problems such as over-fitting and gradient dispersion, this method uses the residual structure of deep over-parameterized convolution for feature extraction firstly. Then uses the multiscale skip structure to introduce global context information, and performs edge contour maintenance operations on the feature tensor. Finally, through a series of upsampling operations, the effective segmentation of each layer region is achieved. The experimental results proved that the method proposed in this paper improves MIoU by 1.39% compared with the method based on the original U-Net model. Compared with other semantic segmentation methods, this method effectively avoids the problems of layer edge blur and loss of details and has better segmentation performance. © 2022 ACM.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Shape recognition and size measurement of particles in hybrid particle field based on interference technology

引用

optoelectronics Letters 2024年

作者：孙金露邱岳武宇航赵丹苗长云 Tianjin Key Laboratory of Optoelectronic Detection Technology and System School of Electronic and Information Engineering Tiangong University

An algorithm that can implement particle shape recognition and size measurement in hybrid particle field is proposed. Based on the defocused images obtained by the interferometric particle imaging system， shape recognition of particles can be realized through ResNet50. 2D Fourier transform and 2D autocorrelation transform are used to obtained the size of spherical and non-spherical particles， respectively. The shape and size of the particle in hybrid particle field are determined. Numerical simulation and experiment results suggest that the method has good accuracy in measuring the particle size of hybrid particle field.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Full Duplex High Speed Data Transmission Based on Partially Coupled Coils in Wireless Power Transmission systems

引用

Progress In Electromagnetics Research C 2022年 119卷 81-96页

作者： Li, Jianxiong Yang, Wenlong School of Electronic and Information Engineering Tiangong University Tianjin ChinaTianjin Key Laboratory of Optoelectronic Detection Technology and Systems Tianjin China.

For full duplex communication, a signal parallel transfer method based on partial power transmission couplers is proposed in this paper. The power transfer uses a serial LC compensation structure topology, and the data transmission channel adopts a double coupling resonant circuit. In terms of power transmission, some power coupling inductors and power compensation capacitors form a power resonance network with a high frequency trap function, which can isolate the influence of signal transmission. Therefore, there is no need for an additional trap, which reduces power loss and the space occupied by the structure. In terms of signal transmission, the partial coupling coil method can increase the coupling frequency and data transfer rate. In addition, the signal transmission circuit has the characteristics of dual resonance frequencies. The forward and reverse signals modulate the carrier at different resonance frequencies to realize full duplex communication. Finally, the simulation results prove that the scheme is practicable for full duplex communication and parallel transmission of power achieving an output power of 1.4 KW, and the highest transmission rate can reach 1 Mbps. © 2022, Electromagnetics Academy. All rights reserved.

关键词： Resonant circuits

来源：评论

学校读者我要写书评

暂无评论

Trustworthy deep learning for encrypted traffic classification

引用

Soft Computing 2025年第2期29卷 645-662页

作者： Li, Zheng Liu, Yanbei Zhang, Changqing Shan, Wanjin Zhang, Haifeng Zhu, Xiaoming School of Electronic and Information Engineering Tiangong University Tianjin300387 China School of Life Sciences Tiangong University Tianjin300387 China Tianjin Key Laboratory of Optoelectronic Detection Technology and Systems Tianjin300387 China College of Intelligence and Computing Tianjin University Tianjin300072 China Science and Technology on Communication Networks Laboratory Shijiazhuang050081 China The 54th Research Institute of China Electronics Technology Group Corporation Shijiazhuang050081 China

Network traffic classification refers to the identification of collected network traffic data of various applications, which is widely used in research fields such as network resource allocation, traffic scheduling and intrusion detection systems. With the widespread application of encryption technology in the network, encrypted traffic classification has become a hot research topic. At present, most existing methods only focus on the accuracy of network traffic classification. Yet, few work studies the reliability of the classification model, which plays an important role in network regulation and network security. In this paper, we propose a novel traffic classification method based on trustworthy deep learning model, which can effectively improve the reliability of encrypted traffic classification models by correcting the confidence of model output. Specifically, we firstly perform data preprocessing on the original network traffic, and then adopt a ConvNet for feature learning and a ClassifyNet for traffic classification in the initial stage. At the same time, we utilize a trustworthy confidence criterion to design a ConfidNet trained according to the probability of the true class. The ConfidNet can provide a reliable confidence measure for the prediction of the classification model. Finally, we demonstrate the effectiveness of our framework through comprehensive experiments on two benchmark datasets ISCX VPN-nonVPN and USTC-TFC2016, and show that our method can improve the reliability of the classification model and has a good ability to identify misclassified samples compared with state-of-the-art methods. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

NerveStitcher2.0: Evolution of Stitching Algorithm for Corneal Confocal Microscope Images with Optical Flow 8

NerveStitcher2.0: Evolution of Stitching Algorithm for Corne...

引用

8th International Conference on Biomedical Imaging, Signal Processing, ICBSP 2023

作者： Qiao, Yu Li, Guangxu Li, Fangting Zhang, Chen TianGong University China Tianjin Optoelectronic Detection Technology and System Laboratory China Peking University People's Hospital China Tianjin Medical University Eye Hospital China

ISBN: (纸本)9798400716584

The NerveStitcher demonstrated that a set of in vivo confocal microscopy (IVCM) images can be merged under a framework of graph convolutional neural network. However, the high similarity of the nerval structure on IVCM image results in mis-stitching when the internal images in sequence happen to drop. Particularly on large gap between a pair of adjacent images, NerveStitcher sometimes cannot detected. In this paper, we advance the concept of global optical flow of IVCM image pair and intergrate it to the existing framework. The large improvements in algorithm robustness are caused by that we make a trade of global displacement of the images sequence according to optical flow, and the local corresponding of key points. We firstly analyze the global shifts in pixel intensity and position between consecutive images, which allows us to determine the motion of each pixel. The displacement vector in the optical flow is then used to calculate the displacement distance of the image. After obtaining the displacement distance of each image using the optical flow, we then use NerveStitcher to stitch the same image sequence. By using a feature point matching algorithm, we can calculate the displacement distance of matching feature points in the two images. We then subtract the displacement distances obtained by the two methods and locate and modify the incorrect stitching results based on the difference value range. Experimental results showed that the improved algorithm, named NerveStitcher2.0, decreases the estimation error by more than 25%. The implemented code is available at https://***/better-77/nervestitcher2.0. © 2023 ACM.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Shape reconstruction and size measurement of spherical particles based on single particle interference imaging and deep learning

引用

Optics Express 2025年第13期33卷 26887-26898页

作者： Jinlu Sun Xiaoyang Wang Zhicheng Guo Yunpeng Chu Yuqiang Li Cheng Zhang Changyun Miao School of Electronic and Information Engineering Tiangong University Tianjin 300387 China Tianjin Key Laboratory of Optoelectronic Detection Technology and System Tianjin 300387 China

An algorithm for shape reconstruction and size measurement of spherical particles is proposed by combining interferometric particle imaging (IPI) with deep learning. Simulated and experimental interferometric defocus images of spherical particles are obtained from the optical transfer matrix theory and the IPI system. The Respe-Unet++, which adds Residual blocks (Res) and the Patch Expand (PE) module to U-net++, is proposed to reconstruct images containing shape and size information. The method is validated through simulation and experiments. The results indicate that Respe-Unet++ achieves a relative error of 0.00278% and a standard deviation of 0.071 in particle size measurement, with a measurement speed of 53.38 FPS. The analysis of incomplete images shows a relative error of 0.13% at a ratio of 10%. Compared to other U-net-based architectures, the Respe-Unet++ demonstrates superior performance in size measurement.

关键词： Aperture synthesis Deep learning Fourier transforms Image sensors Imaging systems Machine learning

来源：评论

学校读者我要写书评

暂无评论

Vision DualGNN: Semantic Graph Is Not Only You Need 27th

Vision DualGNN: Semantic Graph Is Not Only You Need

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Zheng, Xiaolong Wang, Jianming Xiao, Zhitao Sun, Yukuan School of Software Tiangong University Tianjin China Tianjin Key Laboratory of Autonomous Intelligence Technology and Systems Tiangong University Tianjin China Tianjin Key Laboratory of Optoelectronic Detection Technology and Systems Tiangong University Tianjin China Center for Engineering Intership and Training Tiangong University Tianjin China

ISBN: (纸本)9783031781063

Graph Neural Networks (GNNs) have shown great potential in visual tasks, yet they face challenges in effectively constructing and processing graphs. Vision GNN (ViG) was developed to tackle these issues by segmenting images into patches treated as nodes, with edges formed by connecting the nearest semantic neighbors. However, relying solely on semantic information for graph construction confines itself to a dispersed distribution of object neighbors, leading to inadequate graph processing. To address this issue, we propose Vision DualGNN(VDG), a novel dual graph neural network architecture that leverages both spatial and semantic information to construct and process graph representation of images. We apply a node encoder that transforms image patches into expressive node features. Additionally, we implement a dual-stream GNN that operates on both a spatial graph and a semantic graph. The spatial graph serves as a constraint for the semantic graph, enhancing the node features with spatial awareness. To verify the validity of our architecture, we have conducted our experiments on the ImageNet and CIFAR-100 datasets. And achieved state-of-the-art performance compared to other baseline models. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： dualgnn graph convolution semantic graph spatial graph

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：