检索结果-内蒙古大学图书馆

7th IEEE International Conference on Electronic Information and Communication Technology, ICEICT 2024

作者： Ni, Jincheng Zhao, Jin Wu, Xianliang Wu, Ping AnHui University Key Lab of Intelligent Computing & Signal Processing Ministry of Education Hefei China

ISBN: (纸本)9798350384437

This article presents a Symplectic Geometric Mode Decomposition (SGMD) method incorporating K-means clustering, coupled with wavelet denoising, for mitigating noise in Linear Frequency Modulation (LFM) signals. This method substitutes the original component recombination approach in SGMD with the K-means clustering algorithm, thus rendering the signal grouping more logically coherent. In the experiment, we compare the method proposed in this article with other denoising methods. The experimental findings demonstrate substantial advantages of the proposed method in mitigating noise in LFM signals, thereby enhancing both signal-to-Noise Ratio (SNR) and signal quality. The research outcomes underscore the feasibility and substantial potential of this method in mitigating noise in signals. In subsequent studies, additional investigation into its applicability across diverse domains can be pursued alongside the refinement of clustering and denoising algorithms. © 2024 IEEE.

关键词： Wavelet decomposition

来源：评论

学校读者我要写书评

暂无评论

Meta-path and Meta-schema Hierarchical Aggregation for Heterogeneous Graph Neural Networks 10

Meta-path and Meta-schema Hierarchical Aggregation for Heter...

引用

10th IEEE Smart World Congress, SWC 2024

作者： Wu, Ling Gao, Pingping Guo, Kun Fujian Key Laboratory of Network Computing and Intelligent Information Processing China

ISBN: (纸本)9798331520861

With deep learning's advancement in recent years, heterogeneous graph neural networks (HGNNs) have drawn a lot of interest. They are a group of deep learning models specifically designed for handling heterogeneous graph data, in which nodes and edges are of various types and all nodes are assumed to have either direct or indirect associations. A metaschema, which serves as a thorough and unified blueprint for the heterogeneous graph, elegantly connects varied node types to other heterogeneous nodes via multiple heterogeneous edges with rich sematincs. However, many existing methods that utilize meta-schema to mine heterogeneous information often focus on the different meta-relationships inside the schema, limiting the meta-schema to describing only the local relational semantics. To better utilize meta-schema for efficiently integrating different heterogeneous information, we organize them into a hierarchical structure(i.e., hierarchical meta-schema), with all types of nodes distributed across different layers. The layers are interconnected through heterogeneous relationships. The target type is placed at the final layer and others are arranged hierarchically in the front according to the heterogeneous relationships defined in the meta-schema. During information aggregation, according to the hierarchical meta-schema, the information of each layer is gradually aggregated to the target type on the final layer from far to near via the attention mechanism. Moreover, metapaths regularly begin and end with the same type and help to define complex structures and semantic. Therefore, we also consider the semantic information of neighbors based on metapaths within the proposed hierarchical meta-schema to enhance the complex semantics among nodes of the same-type that may be lacking in the meta-schema. Finally, we proposed a meta-path and meta-schema hierarchical aggregation for heterogeneous graph neural network model, named HGNN-MMHA. And we may allow the meta-schema to not

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered Optimal Nonlinear Systems Control Based on State Observer and Neural Network

引用

Journal of Systems Science & Complexity 2023年第1期36卷 222-238页

作者： CHENG Songsong LI Haoyun GUO Yuchao PAN Tianhong FAN Yuan Anhui Engineering Laboratory of Human-Robot Integration System and Intelligent Equipment School of Electrical Engineering and AutomationAnhui UniversityHefei 230601China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Electrical Engineering and AutomationAnhui UniversityHefei 230601China

This paper develops a novel event-triggered optimal control approach based on state observer and neural network(NN)for nonlinear continuous-time ***,the authors propose an online algorithm with critic and actor NNs to solve the optimal control problem and provide an event-triggered method to reduce communication and computation ***,the authors design weight estimation for critic and actor NNs based on gradient descent method and achieve uniformly ultimate boundednesss(UUB)estimation ***,by using bounded NN weight estimation and dead-zone operator,the authors propose a triggering condition,prove the asymptotic stability of closed-loop system from Lyapunov stability perspective,and exclude the Zeno ***,the authors provide a numerical example to illustrate the effectiveness of the proposed method.

关键词： Event-triggered control neural network optimal control state observer

来源：评论

学校读者我要写书评

暂无评论

The application of optimized phase to generate holographic stereogram for a dual-view 3D display 3

The application of optimized phase to generate holographic s...

引用

3rd International computing Imaging Conference, CITA 2023

作者： He, Daofeng Wang, Bin Wang, Anlin Cheng, Hong Shen, Chuan Zhang, Cheng Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei230601 China

ISBN: (纸本)9781510671409

Holographic stereogram, as a marriage of holography and multi-view display technique, benefits of these two 3D display technologies. Recent research about the dual-view holographic stereogram 3D display technology shows an attractive way to present the visual information. However, due to the utilization of the random phase to smooth the spatial frequency spectrum, the troublesome of the quality of reconstructed images from holographic stereograms are those images containing speckle noise. In this paper, inspiring by the works about the computer-generated holograms, we introduced an optimized phase for the generation of dual-view holographic stereogram based on integral imaging to get a better suppression effect of speckle noise. The key goal is to determine the complex amplitude employed to calculate the holographic stereogram. Firstly, the pickup process of multiple parallax images corresponding to the left-view field and right-view field are finished by the virtual cameras. Then, the optimized phase is generated by the full-support iterative process, whose phase range is limited in the first time. Next, instead of the random phase, it is combined with corresponding parallax image to yield the complex amplitude. Holographic stereogram plane is segmented into many element holograms and each of them is generated by the Fourier transforming of the above complex amplitude. The phase of each complex element holograms is retained to generated the phase-only holographic stereogram, which have higher diffraction efficiency and no conjugate image than amplitude type holographic stereogram. Finally, the two set of holograms are combined together to reconstruct the corresponding dual-view. The optimized phase as the initial phase is demonstrated by simulations, the comparison of the simulated reconstructions shows that the method of this paper could improve the reproduction quality of the dual-view holographic stereogram, that extended its applicability and practicality. © 20

关键词： Holograms

来源：评论

学校读者我要写书评

暂无评论

Parallel Coupled Microstrip Wideband Bandpass Filter Loaded with CSRR and SRR Structures

Parallel Coupled Microstrip Wideband Bandpass Filter Loaded ...

引用

2023 International Applied Computational Electromagnetics Society Symposium, ACES-China 2023

作者： Yu, Zijian Song, Xiaodi Li, Chen Anhui University Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Hefei230601 China

ISBN: (纸本)9781733509657

This paper presents a parallel coupled line bandpass filter for X-band applications, which has low insertion loss, broadband and easy processing. By loading the CSRR (Complementary Split Ring Resonator) and SRR (Split Ring Resonator) structures, three additional transmission zeros are added to improve the out-of-band rejection performance of the filter. Moreover, the rectangular DGS structure below the triple-parallel coupling line reduces the insertion loss of the filter. The simulation results show that the filter center frequency is 9.5GHz, the insertion loss is 0.8dB, S11 © 2023 Applied Computational Electromagnetics Society (ACES).

关键词： Bandpass filters

来源：评论

学校读者我要写书评

暂无评论

A Bandstop Filter Based on Modified Defected Ground Structure with Compact Size

A Bandstop Filter Based on Modified Defected Ground Structur...

引用

2023 International Applied Computational Electromagnetics Society Symposium, ACES-China 2023

作者： Zhang, Boyan Li, Minquan Xiao, Shuang Li, Chen Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Hefei230601 China

ISBN: (纸本)9781733509657

This paper reports a compact size bandstop filter using Defected Ground Structure (DGS). The proposed filter consists of squared shaped defect and U-shaped defect sticked on the ground plane. This design is based on a parallel LC circuit model and designed to work at 1 GHz. The filter is implemented on a FR-4 dielectric plate and its size is 0.049λg× 0.049λg (where λg is the wavelength in waveguide). © 2023 Applied Computational Electromagnetics Society (ACES).

关键词： Notch filters

来源：评论

学校读者我要写书评

暂无评论

Design of a Miniaturised Wide-Stopband SIW Filter

Design of a Miniaturised Wide-Stopband SIW Filter

引用

2023 International Applied Computational Electromagnetics Society Symposium, ACES-China 2023

作者： Li, Chen Li, Minquan Qu, Xin Xiao, Shuang Anhui University Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Hefei230601 China

ISBN: (纸本)9781733509657

In this paper, we propose a miniaturized wide-stopband SIW dual-band filter. SIW limits the propagation of electromagnetic waves and thus enables the miniaturization of the filter. A passband below the waveguide cutoff frequency is generated by etching the CSRR structure on the surface of the SIW, while a modified CSRR-DGS structure is etched on the backside of the SIW structure, and the other passband is generated by coupling the CSRR etched on the surface of the SIW to the ground. In addition, the CSRR-DGS structure broadens the stopband without increasing the filter size. Through the circuit equivalent analysis and parameter optimization of the filter structure, the final simulation results are as follows: the filter has a passband of 3.5 GHz (WIMAX) and 5.2 GHz (WLAN), the 3dB bandwidths of the two bands are 130MHz and 180MHz respectively, the insertion loss is 0.5 dB and 0.65 dB, and the size is $0.18λ{\mathrm{g}}× 0.27λ{\mathrm{g}}$. Overall, it achieves high performance and also has a wide range of applications. © 2023 Applied Computational Electromagnetics Society (ACES).

关键词： Wireless local area networks (WLAN)

来源：评论

学校读者我要写书评

暂无评论

Iterative phase hologram generation with adaptive weighted constraints for color holographic display 13

Iterative phase hologram generation with adaptive weighted c...

引用

Holography, Diffractive Optics, and Applications XIII 2023

作者： Ding, YuXin Wang, Bin Wang, AnLin Shen, Chuan Cheng, Hong Zhang, Cheng Wei, Sui Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei230601 China

ISBN: (纸本)9781510667853

Compared with monochromatic holographic displays, color holographic displays have rich depth and color information, which can give observers a more pleasant visual effect. Inspiring by the adaptive weighted GS method, we introduced an optimized iterative method based on exponential weighted constraint to calculate phase-only holograms of color images. After channel separation of the target image to obtain each component image, the input complex amplitude is formed with quadratic phase and iterated. During the iteration, subtract the amplitude of the reconstructed image from the amplitude of the target image to construct an exponential constraint. This exponential constraint is applied to the signal area of the image plane. After calculating the three-channel phase hologram, a color holographic reconstruction can be obtained using the time multiplexing method. Simulated and optical experiments verify the effectiveness of this method. © 2023 SPIE.

关键词： Holograms

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Object Detection in SAR images via Gaussian Flow Class-Balanced Differential Aggregation 2

Few-Shot Object Detection in SAR images via Gaussian Flow Cl...

引用

2nd IEEE International Conference on signal, Information and Data processing, ICSIDP 2024

作者： Zhao, Po Chen, Jie Zhang, Chaochen Ma, Ke Anhui University Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Electronics and Information Engineering Hefei230601 China

ISBN: (纸本)9798331515669

Currently, few-shot object detection (FSOD) methods for synthetic aperture radar (SAR) images are severely understudied. The high confidentiality and scarcity of SAR data, coupled with the susceptibility of targets in SAR images to significant changes in orientation, make existing models sensitive to variations in novel class examples. This sensitivity leads to challenges in extracting class prototypes and accurately estimating class centers for novel classes. To solve the above issues, we propose a few-shot object detection algorithm for SAR images via Gaussian Flow Class-Balanced Differential Aggregation. Specifically, we first design a class-balanced difference feature aggregation module to solve the problems of difficult class distribution estimation and inaccurate class center estimation of novel classes in SAR images. Second, the contextual information perception module is designed to extract the most representative support features into fine-grained prototypes and aggregate them with the query features using the matching paradigm to solve the imbalance between foreground targets and background in SAR images. Finally, experimental results on MSAR-AIR dataset indicate that our model realizes the best detection properties on SAR images compared to existing models. © 2024 IEEE.

关键词： few-shot learning object detection synthetic aperture radar variational feature learning

来源：评论

学校读者我要写书评

暂无评论

Non-intrusive Load Monitoring Based Data-Free Incremental Electrical Appliance Identification 8th

Non-intrusive Load Monitoring Based Data-Free Incremental El...

引用

8th International Conference on Energy and Environmental Science, ICEES 2024

作者： Zhou, Rui Fang, Xiaohan The Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Electrical Engineering and Automation Anhui University Hefei230601 China

ISBN: (纸本)9783031639005

In the realm of modern energy management systems, Non-Intrusive Load Monitoring (NILM) technology provides an innovative solution for power suppliers. It allows for remote monitoring and analysis of users’ electricity consumption patterns without requiring direct access to each device. This technology works by collecting comprehensive energy data at the user’s meter entry point and using algorithms to differentiate and identify the energy consumption characteristics of each device. However, with the increasing number of smart devices used by residential and commercial users, traditional NILM methods face the challenge of dealing with more complex and diverse electricity usage patterns. To address these challenges, we propose a novel incremental NILM framework. This framework has the ability to independently learn new load categories without load data, which is crucial for adapting in real-time to the changing variety of load devices, while also effectively addressing user privacy concerns. We introduce a VI-SCRM for extracting V-I trajectory features, incorporating a reconstruction convolution module. This method reduces the redundancy of V-I trajectory features and eliminates insignificant features, thereby improving algorithm efficiency. Additionally, this approach streamlines the model training process and prevents the model from ‘forgetting’ previously acquired knowledge. By implementing this framework in NILM, the system can continually adjust to new types of devices. Our experimental results confirm the effectiveness of this approach and highlight its potential advantages in practical applications. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Convolution

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：