检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Zeng, Chuxi Xia, Zhipnig Wang, Zhuo Zhou, Yihuan Zeng, Linghong Yin, Zishan Li, Xi Huang, Haizhou Qi, Xiaolan Deng, Zhonghua School of Artificial Intelligence and Automation Key Laboratory of Image Processing Intelligent Control of Education Ministry Huazhong University of Science and Technology Wuhan430074 China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen518055 China Huazhong University of Science and Technology China

Accurate wind speed prediction is essential for the integration of wind turbines into microgrids. This paper proposes a combined prediction model, firstly, the key parameters of the variational modal decomposition (VMD) is optimized by whale optimization algorithm (WOA), and the original wind speed sequence is decomposed by using the WOA-VMD to obtain the intrinsic mode functions (IMFs) with different frequencies;secondly, the Pearson correlation coefficient is performed between IMFs and the original wind speed sequence, classifying the IMFs into two groups according to their correlation coefficients, the IMFs with strong correlation are predicted using the temporal convolutional network (TCN), and the IMFs with weak correlation are predicted using the gate recurrent unit (GRU);finally, the prediction results of each component are superimposed to obtain the final prediction results. The combined model is applied to real data from six wind farms in China with different climatic conditions and geographic locations, and different comparison models are established for validation. The experimental results show that the combined WOA-VMD-GRU-TCN prediction model can significantly improve the prediction accuracy, reduce the wind speed sequence error, and have better robustness than other methods. © 2024, The Authors. All rights reserved.

关键词： Intrinsic mode functions

来源：评论

学校读者我要写书评

暂无评论

SAR Target Recognition Using Simulated Data by an Ensemble Multi-scale Deep Domain Adaptation Recognition Framework

SAR Target Recognition Using Simulated Data by an Ensemble M...

引用

2021 CIE International Conference on Radar, Radar 2021

作者： Sun, Yuanshuang Wang, Yinghua Hu, Liping Liu, Hongwei Xidian University National Laboratory of Radar Signal Processing Xi'an China Beijing Institute of Environmental Features Science and Technology on Electromagnetic Scattering Laboratory Beijing China

ISBN: (纸本)9781665498142

Obtaining lots of synthetic aperture radar (SAR) data for automatic target recognition (ATR) can be unrealistic in many situations. Relatively speaking, electromagnetic simulated SAR data is easier to acquire. However, there is an apparent distribution gap between the electromagnetic simulated data and the real data. It is not suitable to use the simulated data for recognition directly, and thus the way to apply the simulated SAR data for recognition is worth considering. In this paper, we focus on a challenging recognition problem of training solely on simulated data and testing on real data. Firstly, a multi-scale feature extraction module is used for robust feature extraction, which aims to make the extracted feature more generalized for both simulated data and real data. Secondly, the idea of domain adaptation is considered to learn a representation trained to jointly optimize for classification and domain invariance. Thirdly, an ensembling technique is applied, and an ensemble multi-scale deep domain adaptation recognition framework is proposed. The Moving and Stationary Target Acquisition and Recognition (MSTAR) benchmark data set and an electromagnetic simulated SAR data set are used for verification, and experimental results illustrate the effectiveness of our methods. © 2021 IEEE.

关键词： deep learning domain adaptation SAR target recognition simulated data Synthetic aperture radar (SAR)

来源：评论

学校读者我要写书评

暂无评论

Simulated Data for SAR Tomographic Reconstruction in Urban Areas

Simulated Data for SAR Tomographic Reconstruction in Urban A...

引用

Earth Observation and Geo-Spatial Information (ICEOGI), International Conference on

作者： Ishak Daoud Saoussen Belhadj-Aissa Faiza Hocine Assia Kourgli Department of Telecommunication Image Processing and radiation Lab University of Science and Technology Houari Boumediene Algiers Algeria Jet Propulsion Laboratory California Institute of Technology Pasadena California USA

The evaluation of SAR tomographic reconstruction models requires an examination of their robustness with respect to various parameters. Typically, a simple simulation of reflectivity profiles with different scatters at different elevations and SNRs is used to evaluate the robustness of any reconstruction model. However, these simulation setups do not account for most of the geometric acquisition variables present in the reconstruction of real data. Most of the data used for SAR tomographic reconstruction in urban areas are acquired using high-resolution X-band sensors because of their weak penetration, which aids in recovering the geometry of the target. In this work, we propose simulating an urban area acquisition scene that considers the primary acquisition parameters of high-resolution X-band sensors. By doing so, one can simulate various measurements for different building shapes and elevations, providing a more comprehensive evaluation of the reconstruction methods. In this simulation, the geometry of SAR tomography is respected by considering different geometry distortions such as layover, foreshortening, and shadowing. The simulation is evaluated by implementing different reconstruction methods to the simulated data. Results obtained show that sparse reconstruction methods such as 11 and 12 norms and SL1MMER are more suitable to evaluate the reconstruction due to the high-resolution acquisitions. On the other hand, we used other conventional reconstruction models such as SVD-Weiner and MUSIC for assessment purposes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evolutionary attraction–repulsion algorithm embedded with LLM for UAV task allocation

引用

Advanced Engineering Informatics 2025年 66卷

作者： Wu, Bowen Xiao, Renbin School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Institute of Artificial Intelligence Huazhong University of Science and Technology Wuhan430074 China Key Laboratory of Image Processing and Intelligent Control Ministry of Education Wuhan430074 China

Labor division provides an adaptive and scalable technique for unmanned systems. However, its designing process usually relies heavily on the manually crafted paradigms, leading to inefficiencies and insufficient performance. To overcome these challenges, this paper introduce an evolutionary approach to labor division algorithm design. Drawing inspiration from the regulatory behaviors observed in natural lion populations, we propose a bipolar feedback-guided attraction–repulsion mechanism. A formal model is developed to encapsulate this mechanism, and we provide an in-depth analysis of the algorithm's evolution through the framework of systems science. In addition, we leverage prompt engineering techniques to integrate a large language model (LLM) with our proposed mechanism, facilitating a bidirectional enhancement between the two. This integration culminates in the development of the ARE-LLM framework, a robust and adaptive solution for designing labor division algorithms. To demonstrate the practical applicability of our approach, we apply the ARE-LLM framework to the UAV-based task allocation problem for enemy air defense suppression. The experimental results indicate that our method outperforms several advanced approaches. In a scenario involving 50 UAVs tasked with completing 300 assignments, the total distance traveled is only 9 % of that required by the ALPDA algorithm, while the processing time is reduced to 8 % of that used by ALPDA. © 2025 Elsevier Ltd

关键词： Target drones

来源：评论

学校读者我要写书评

暂无评论

Efficient Fault Detection in Nonlinear Industrial Process: A Reduced Kernel PCA-Based Spectral Clustering Approach

Efficient Fault Detection in Nonlinear Industrial Process: A...

引用

Artificial Intelligence, Applications, Innovation and Ethics (AI2E), International Conference for

作者： Khadija Attouri Majdi Mansouri Mansour Hajji Kais Bouzrara Laboratory of Advanced Materials and Nanotechnologies Higher Institute of Applied Sciences and Technology of Kasserine Kairouan University Tunisia Department of Electrical and Computer Engineering College of Engineering Sultan Qaboos University Muscat Oman Research Laboratory of Automation Signal Processing and Image National Engineering School of Monastir Tunisia

ISBN: (数字)9798331513733

ISBN: (纸本)9798331513740

The challenges posed by nonlinearities in industrial systems necessitate innovative techniques that outperform the limitations of traditional methods such as principal component analysis (PCA). While Kernel Principal Component Analysis (KPCA) offers a robust solution to handle nonlinear data, its computational requirements are a significant issue, especially for large-sized datasets. In this work, we propose a novel technique, namely, reduced kernel principal component analysis-based spectral clustering (RKPCA SpC ), to monitor and detect faults in the benchmark Tennessee Eastman process. The suggested approach addresses the complexity associated with KPCA by reducing data size during the model training phase. This reduction involves retaining only the principal components, preserving informative features, and selecting pertinent samples without compromising the original data's content. The efficacy of the proposed method is evaluated through key performance metrics, including false alarm rate (FAR), missed detection rate (MDR), detection time delay (DTD), and computation time (CT). Additionally, gained execution time (GET), gained storage space (GSP), and loss function (LF) are considered, providing a comprehensive assessment of the developed paradigms' effectiveness. The results demonstrate the promising capabilities of our proposed scheme.

关键词： Training Measurement Technological innovation Fault detection Delay effects Computational modeling Complexity theory Kernel Monitoring Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Formulation of Optimization Problems with Radiation Field Phases as Design Variables for Pattern Synthesis of Linear Antenna Arrays

引用

China Communications 2022年第12期19卷 86-100页

作者： Fei Zhao Jun He Sanyou Zeng Changhe Li Qinghui Xu Zhigao Zeng School of Mechanical Engineering and Electronic Information China University of GeosciencesWuhan 430074China Science and Technology on Blind Signal Processing Laboratory Southwest Electronics and Telecommunication Technology Research InstituteChengdu 610041China School of Automation China University of GeosciencesWuhan 430074China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan 430074China College of Computer Hunan University of TechnologyZhuzhou CityHunan Province412007China

Pattern synthesise of antenna arrays is usually complicated optimization problems,while evolutionary algorithms(EAs)are promising in solving these *** paper does not propose a new EA,but does construct a new form of optimization *** new optimization formulation has two differences from the common *** is the objective function is the field error between the desired and the designed,not the usual amplitude error between the desired and the *** difference is beneficial to decrease complexity in some *** second difference is that the design variables are changed as phases of desired radiation field within shaped-region,instead of excitation *** difference leads to the reduction of the number of design variables.A series of synthesis experiments including equally and unequally spaced linear arrays with different pattern shape requirements are applied,and the effectiveness and advantages of the proposed new optimization problems are *** results show that the proposing a new optimization formulation with less complexity is as significant as proposing a new algorithm.

关键词： pattern synthesis evolutionary algorithms linear antenna arrays

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Models Comparison in binary context for DDoS Attack Detection in Software-Defined Network

Deep Learning Models Comparison in binary context for DDoS A...

引用

International Conference on Advanced Technologies for signal and image processing (ATSIP)

作者： Ameur Salem Zaidoun Zied Lachiri Laboratory of Signal Image and Information Technologies at National Engineering School of Tunis University of Tunis El Manar Tunis Tunisia Department of Computer Science Technology Higher Institute of Technological Studies Siliana Tunisia

ISBN: (数字)9798350351484

ISBN: (纸本)9798350351491

Software-defined Networks (SDN) are continually evolving, but they also face numerous security challenges, particularly from Denial of Service (DoS) attacks and their more distributed variant, Distributed Denial of Service (DDoS) attacks. This paper will be focused on showcasing and giving an efficient comparison and classification of Artificial Intelligence (AI) based solutions, mainly Deep Learning (DL) tools, by the experimentation of a set of them on one selected dataset to pick up the most efficient demarcation tool. The main goal here is to separate normal from abnormal traffic without any distinction of different identified attack types using binary classification. Simple and hybrid models will be deployed in supervised mode on a chosen dataset, which is CIC-DDoS2019, that has been optimized for more efficient training. The accuracy results recorded in this case reached ${9 9. 8 \%}$.

关键词： Deep learning Training Accuracy Denial-of-service attack Data models Security Software defined networking

来源：评论

学校读者我要写书评

暂无评论

Optimizing Binary Sequence Excitation signals for Rapid Impedance Spectrum Measurement in Proton Exchange Membrane Fuel Cells

Optimizing Binary Sequence Excitation Signals for Rapid Impe...

引用

第43届中国控制会议

作者： Jingzhi Lei Chuang Sheng Jingjing Wang Liansong Yu Xi Li School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control of Education MinistryHuazhong University of Science and Technology State Grid Electric Power Research Institute Wuhan Nanrui Limited Liability Company Shenzhen Huazhong University of Science and Technology Research Institute

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

With the increasing demand for efficient and reliable renewable energy sources,Proton Exchange Membrane Fuel Cells(PEMFCs) have emerged as a promising *** experiments demonstrate that Electrochemical Impedance Spectroscopy(EIS) effectively differentiates various states of *** broadband signals as testing excitations significantly reduces EIS measurement time,facilitating real-time monitoring of PEMFCs' health under dynamic *** signal design requires maintaining adequate amplitude across frequency components for noise resistance while minimizing signal peak value to reduce operational *** paper introduces an EIS simulation environment,leveraging PEMFCs' impedance and electrochemical noise *** focuses on optimizing the excitation signal's amplitude-frequency distribution using discrete interval binary *** results indicate that our method achieves minimal perturbation amplitude while preserving measurement accuracy in amplitude-frequency signal design.

关键词： Proton exchange membrane fuel cell Electrochemical impedance spectroscopy Electrochemical noise Excitation signal optimization

来源：评论

学校读者我要写书评

暂无评论

Rethinking the Up-Sampling Operations in CNN-Based Generative Network for Generalizable Deepfake Detection

Rethinking the Up-Sampling Operations in CNN-Based Generativ...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Chuangchuang Tan Huan Liu Yao Zhao Shikui Wei Guanghua Gu Ping Liu Yunchao Wei Institute of Information Science Beijing Jiaotong University Beijing Key Laboratory of Advanced Information Science and Network Technology School of Information Science and Engineering Yanshan University Hebei Key Laboratory of Information Transmission and Signal Processing CSE department University of Nevada Reno USA

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Recently, the proliferation of highly realistic synthetic images, facilitated through a variety of GANs and Diffusions, has significantly heightened the susceptibility to misuse. While the primary focus of deepfake detection has traditionally centered on the design of detection algorithms, an investigative inquiry into the generator architectures has remained conspicuously absent in recent years. This paper contributes to this lacuna by rethinking the architectures of CNN-based generator, thereby establishing a generalized representation of synthetic artifacts. Our findings illuminate that the up-sampling operator can, beyond frequency-based artifacts, produce generalized forgery artifacts. In particular, the local interdependence among image pixels caused by upsampling operators is significantly demon-strated in synthetic images generated by GAN or diffusion. Building upon this observation, we introduce the concept of Neighboring Pixel Relationships(NPR) as a means to capture and characterize the generalized structural artifacts stemming from up-sampling operations. A comprehensive analysis is conducted on an open-world dataset, comprising samples generated by 28 distinct generative models. This analysis culminates in the establishment of a novel state-of-the-art performance, showcasing a remarkable 12.8% im-provement over existing methods. The code is available at https://***/chuangchuangtan/NPR-DeepfakeDetection.

关键词： Deepfakes Computer vision Frequency-domain analysis Computer architecture Detectors Generative adversarial networks Generators

来源：评论

学校读者我要写书评

暂无评论

Learning on Gradients: Generalized Artifacts Representation for GAN-Generated images Detection

Learning on Gradients: Generalized Artifacts Representation ...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Chuangchuang Tan Yao Zhao Shikui Wei Guanghua Gu Yunchao Wei Institute of Information Science Beijing Jiaotong University Beijing Key Laboratory of Advanced Information Science and Network Technology School of Information Science and Engineering Yanshan University Hebei Key Laboratory of Information Transmission and Signal Processing

Recently, there has been a significant advancement in image generation technology, known as GAN. It can easily generate realistic fake images, leading to an increased risk of abuse. However, most image detectors suffer from sharp performance drops in unseen domains. The key of fake image detection is to develop a generalized representation to describe the artifacts produced by generation models. In this work, we introduce a novel detection framework, named Learning on Gradients (LGrad), designed for identifying GAN-generated images, with the aim of constructing a generalized detector with cross-model and cross-data. Specifically, a pretrained CNN model is employed as a transformation model to convert images into gradients. Subsequently, we leverage these gradients to present the generalized artifacts, which are fed into the classifier to ascertain the authenticity of the images. In our framework, we turn the data-dependent problem into a transformation-model-dependent problem. To the best of our knowledge, this is the first study to utilize gradients as the representation of artifacts in GAN-generated images. Extensive experiments demonstrate the effectiveness and robustness of gradients as generalized artifact representations. Our detector achieves a new state-of-the-art performance with a remarkable gain of 11.4%. The code is released at https://***/chuangchuangtan/LGrad.

关键词：

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：