检索结果-内蒙古大学图书馆

18th International Conference on intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2022

作者： Wang, Chao Guo, Baolong Li, Cheng Institute of Intelligent Control and Image Engineering Xidian University Xi’an China

ISBN: (纸本)9789819906048

Speckle noise usually deteriorate the synthetic aperture radar (SAR) imaging system severely, which results in great difficulties to the post-processing. In this paper, we propose a novel despeckling method based on Fisher-Tippett (FT) distribution and nonconvex total variation (NTV) model to tackle the problem. First, we introduce a FT distribution-based Bayesian framework to develop speckle noise removal models. Secondly, we propose a new nonconvex TV model which is more appropriate to preserve edges/textures than the conventional model. Meanwhile, we give a simple method to solve the nonconvex TV model. Thirdly, a new iterative regularization scheme-based despeckling algorithm is proposed, in which the NTV model filtered residual is added back to the despeckling image. Experiments conducted on both simulated and real SAR images demonstrate that the proposed method can effectively remove speckle while preserving edges and textures compared with some state-of-the-art methods. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Speckle

来源：评论

学校读者我要写书评

暂无评论

Improved ShuffleNetV2 for Garbage image Classification 18th

Improved ShuffleNetV2 for Garbage Image Classification

引用

18th International Conference on intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2022

作者： Zhang, Jinghan Li, Cheng Guo, Baolong Institute of Intelligent Control and Image Engineering Xidian University Xi’an China

ISBN: (纸本)9789819906048

This paper proposes a novel lightweight classification network based on ShuffleNet V2 to promote the accuracy of garbage image classification. Compared with the conventional network, there is a package of optimizations to both ameliorate the classification accuracy and inference speed of the model. Firstly, the optimized network introduces the Leaky ReLU as a substitute for the activation function. It also adopts the squeeze and excitation network to enhance important features. In addition, the flattened layer is applied to downscale the data, and three fully connected layers are used for enhancing the learning capability. Furthermore, the model is pre-trained based on transfer learning, wherein the feature knowledge learned from imageNet datasets is transferred to garbage classification task. Extensive experiments on the garbage image dataset verify the overall performance, which improves the classification accuracy by 6.3% with a 35.4% reduction in time consumption. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Bearing Remaining Useful Life Prediction Combining Trajectory Similarity and Relevance Vector Machine 41

Bearing Remaining Useful Life Prediction Combining Trajector...

引用

第41届中国控制会议

作者： Zhuyi Li Kesen Fan Cong Zhang Sihang Zhang Yiming Wan Key Laboratory of Image Processing and Intelligent Control Ministry of Education Chinaand School of Artificial Intelligence and AutomationHuazhong University of Science and Technology Beijing Institute of Control Engineering

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Bearing remaining useful life(RUL) prediction is critical for safe operation of rotating *** this paper,we propose a combined RUL prediction approach that leverages both trajectory similarity and relevance vector machine(RVM).The similarity based prediction relies on historical degradation trajectories that are highly similar to the online data,hence would perform poorly if all historical trajectories have low similarity with the online *** RVM based prediction relies solely on a regression model learned from the available online data,thus gives an inaccurate prediction when insufficient data are available in the early stage of degradation.A weighted sum of these above two predictions is proposed to address the limitation of each single prediction method,whose weights are determined by solving a non-negative least squares fitting *** further improve RUL prediction accuracy,we distinguish between fast and slow degradation modes,so that each mode uses a different set of historical degradation trajectories and kernel *** doing so,we predict RUL under the identified *** case study using the PHM2012 dataset demonstrates the effectiveness of the proposed RUL prediction approach.

关键词： Bearing degeneration remaining useful life prediction relevance vector machine trajectory similarity

来源：评论

学校读者我要写书评

暂无评论

Contour Extraction via Contextual Modulation

引用

Chinese Journal of Electronics 2023年第2期18卷 329-331页

作者： Wentao Huang Licheng Jiao Yuelei Xu Ye Sun Jianhua Jia Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education Institute of Intelligent Information Processing Xidian University Xi'an China Department of Avionics Engineering Engineering College of Air Force Engineering University Xi'an China

Contour extraction is an important task in image processing and computer vision. The contextual modulation is a universal phenomenon in the primary visual cortex (V1). A biologically motivated computational model is presented for contour extraction in this paper. Two mechanisms of contextual modulation, surround suppression and collinear facilitation, are integrated in this model. We obtain good results via this model to extract contours from images with noise and texture backgrounds. This work provides a biologically motivated approach with great potential for computer vision.

关键词： Visualization Computer vision Computational modeling Biological system modeling image processing Modulation Organizations

来源：评论

学校读者我要写书评

暂无评论

Thermal constraint control of reversible solid oxide cell for optimal system efficiency

引用

International Journal of Hydrogen Energy 2025年 134卷 198-211页

作者： Xu, Yuanwu Yin, Jie Wang, Jingjing Wu, Xiao-long Peng, Jingxuan Tang, Ruifeng Zou, Suhang Fu, Xiaowei Li, Xi School of Artificial Intelligence and Automation Wuhan University of Science and Technology Hubei Wuhan430081 China School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control of Education Ministry Huazhong University of Science and Technology Hubei Wuhan430074 China School of Information Engineering Nanchang University Jiangxi Nanchang330031 China School of Electrical and Electronic Engineering Nanyang Technological University 639798 Singapore China-Poland Belt and Road Joint Laboratory on Measurement and Control Technology Huazhong University of Science and Technology Hubei Wuhan430074 China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen518055 China

Reversible solid oxide cell (RSOC) demonstrates considerable promise in multimodal energy conversion architectures, particularly as a technology for hydrogen-based energy storage systems. Nevertheless, under dynamic operating regimes with time-varying current inputs, realizing time-efficient and reliable transitions to steady-state operation remains difficult. This difficulty arises from the intricate coupling of thermal, electrical, and gaseous processes within the RSOC system. This study aims to address these challenges by developing a 5 kW mathematical model of the RSOC system. The proposed model enables systematic investigation of thermal safety issues arising during current switching operations while introducing a thermal constraint control strategy to enhance both system efficiency and thermal safety performance. This efficiency-driven study employs the Grid Search algorithm to identify optimal steady-state operating points for the RSOC system, ensuring strict adherence to safety constraints across varying current inputs. Furthermore, by integrating the pre-identified optimal operating points as feedforward control with Model Predictive control (MPC)-based feedback correction, this hybrid strategy effectively mitigates stack temperature gradient overshoot while synchronously ensuring optimal system efficiency throughout current transition processes. Under simulated variable current inputs, the proposed RSOC system model and control strategy demonstrate the capability to constrain stack temperature gradient overshoot within 2.3K while enhancing transient efficiency by 5 %–8 %, achieving a peak system efficiency of 85 %. It provides a novel methodology for safe and efficient working with intermittent renewable energy. © 2025 Hydrogen Energy Publications LLC

关键词： Thermal variables control

来源：评论

学校读者我要写书评

暂无评论

Interval Type-2 Fuzzy Hierarchical Adaptive Cruise Following-control for intelligent Vehicles

引用

IEEE/CAA Journal of Automatica Sinica 2022年第9期9卷 1658-1672页

作者： Hong Mo Yinghui Meng Fei-Yue Wang Dongrui Wu the College of Electric and Information Engineering Changsha University of Science and TechnologyChangsha 410114China the State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190 Qingdao Academy of Intelligent Industries Qingda 266109 the Center of China Economic and Social Security University of Chinese Academy of SciencesBeijing 100190China the Ministry of Education Key Laboratory on Image Information Processing and Intelligent Control the School of Artificial Intelligence and AutomationHuazhong University of Science and TechnologyWuhan 430074China

intelligent vehicles can effectively improve traffic congestion and road traffic *** cruise followingcontrol(ACFC)is a vital part of intelligent *** this paper,a new hierarchical vehicle-following control strategy is presented by synthesizing the variable time headway model,type-2 fuzzy control,feedforward+fuzzy proportion integration(PI)feedback(F+FPIF)control,and inverse longitudinal dynamics model of ***,a traditional variable time headway model is improved considering the acceleration of the lead ***,an interval type-2 fuzzy logic controller(IT2 FLC)is designed for the upper structure of the ACFC system to simulate the driver's operating *** reduce the nonlinear influence and improve the tracking accuracy for the desired acceleration,the control strategy of F+FPIF is given for the lower control ***,the lower control method proposed in this paper is compared with the fuzzy PI control and the traditional method(no lower controller for tracking desired acceleration)***,the proportion integration differentiation(PID),linear quadratic regulator(LQR),subsection function control(SFC)and type-1 fuzzy logic control(T1 FLC)are respectively compared with the IT2 FLC in control performance under different ***,the simulation results show the effectiveness of IT2 FLC for the upper structure and F+FPIF control for the lower structure.

关键词： Adaptive cruise following-control(ACFC) feedforward+fuzzy proportion integration(PI)feedback(F+FPIF) type-2 fuzzy control variable time headway

来源：评论

学校读者我要写书评

暂无评论

Virtual electromagnetic environment modeling based data augmentation for drone signal identification

引用

Journal of Information and Intelligence 2023年第4期1卷 308-320页

作者： Hanshuo Zhang Tao Li Yongzhao Li Zhijin Wen School of Telecommunications Engineering Xidian UniversityXi'an 710071China Laboratory of Electromagnetic Space Cognition and Intelligent Control Beijing 100191China Guangzhou Institute of Technology Xidian UniversityGuangzhou 510000China

Radio frequency(RF)-based drone identification technologies have the advantages of long effective distances and low environmental dependence,which has become indispensable for drone surveillance ***,since drones operate in unlicensed frequency bands,a large number of co-frequency devices exist in these bands,which brings a great challenge to traditional signal identification *** learning techniques provide a new approach to complete endto-end signal identification by directly learning the distribution of RF *** such scenarios,due to the complexity and high dynamics of the electromagnetic environments,a massive amount of data that can reflect the various propagation conditions of drone signals is necessary for a robust neural network(NN)for identifying *** reality,signal acquisition and labeling that meet the above requirements are too costly to ***,we propose a virtual electromagnetic environment modeling based data augmentation(DA)method to improve the diversity of drone signal *** DA method focuses on simulating the spectrograms of drone signals transmitted in real-world environments and randomly generates extra training data in each training ***,considering the limited processing capability of RF receivers,we modify the original YOLOv5s model to a more lightweight *** losing the identification performance,more hardware-friendly designs are applied and the number of parameters decreases about *** performance evaluation,we utilized a universal software radio peripheral(USRP)X310 platform to collect RF signals of four drones in an anechoic chamber and a practical wireless *** results reveal that the NN trained with augmented data performs as well as that trained with practical data in the complex electromagnetic environment.

关键词： Drone signal identification Data augmentation Virtual electromagnetic environment modeling You Only Look Once Spectrogram

来源：评论

学校读者我要写书评

暂无评论

Temperature Gradient Analyses of a Tubular Solid Oxide Fuel Cell Fueled by Methanol

引用

Transactions of Tianjin university 2023年第1期29卷 14-30页

作者： Qidong Xu Meiting Guo Lingchao Xia Zheng Li Qijiao He Dongqi Zhao Keqing Zheng Meng Ni Department of Building and Real Estate Research Institute for Sustainable Urban Development(RISUD)&Research Institute for Smart Energy(RISE)The Hong Kong Polytechnic UniversityHong Kong 999077China School of Artifi cial Intelligence and Automation Key Laboratory of Image Processing and Intelligent ControlHuazhong University of Science and TechnologyWuhan 430074China School of Low-Carbon Energy and Power Engineering China University of Mining and TechnologyXuzhou 221116China

Thermal management in solid oxide fuel cells(SOFC)is a critical issue due to non-uniform electrochemical reactions and convective fl ows within the ***,a 2D mathematical model is established herein to investigate the thermal responses of a tubular methanol-fueled *** show that unlike the low-temperature condition of 873 K,where the peak temperature gradient occurs at the cell center,it appears near the fuel inlet at 1073 K because of the rapid temperature rise induced by the elevated current *** the large heat convection capacity,excessive air could not eff ectively eliminate the harmful temperature gradient caused by the large current ***,optimal control of the current density by properly selecting the operating potential could generate a local thermal neutral ***,the maximum axial temperature gradient could be reduced by about 18%at 973 K and 20%at 1073 K when the air with a 5 K higher temperature is ***,despite the higher electrochemical performance observed,the cell with a counter-fl ow arrange-ment featured by a larger hot area and higher maximum temperature gradients is not preferable for a ceramic SOFC system considering thermal ***,this study could provide insightful thermal information for the operating condition selection,structure design,and stability assessment of realistic SOFCs combined with their internal reforming process.

关键词： Solid oxide fuel cell Modeling Methanol fuel Temperature gradient Internal reforming

来源：评论

学校读者我要写书评

暂无评论

Global Convergence Guarantees of (A)GIST for a Family of Nonconvex Sparse Learning Problems

引用

IEEE Transactions on Cybernetics 2022年第5期52卷 3276-3288页

作者： Zhang, Hengmin Qian, Feng Shang, Fanhua Du, Wenli Qian, Jianjun Yang, Jian East China University of Science and Technology Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education School of Information Science and Engineering Shanghai200237 China Shanghai Institute of Intelligent Science and Technology Tongji University Shanghai200092 China Xidian University Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial Intelligence Xi'an710071 China Peng Cheng Laboratory Shenzhen518066 China Nanjing University of Science and Technology Pca Laboratory Key Lab. of Intelligent Percept. and Syst. for High-Dimensional Information of Ministry of Education Nanjing210094 China Nanjing University of Science and Technology Jiangsu Key Laboratory of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing210094 China

In recent years, most of the studies have shown that the generalized iterated shrinkage thresholdings (GISTs) have become the commonly used first-order optimization algorithms in sparse learning problems. The nonconvex relaxations of the \ell _{0} -norm usually achieve better performance than the convex case (e.g., \ell _{1} -norm) since the former can achieve a nearly unbiased solver. To increase the calculation efficiency, this work further provides an accelerated GIST version, that is, AGIST, through the extrapolation-based acceleration technique, which can contribute to reduce the number of iterations when solving a family of nonconvex sparse learning problems. Besides, we present the algorithmic analysis, including both local and global convergence guarantees, as well as other intermediate results for the GIST and AGIST, denoted as (A)GIST, by virtue of the Kurdyka-Lojasiewica (KL) property and some milder assumptions. Numerical experiments on both synthetic data and real-world databases can demonstrate that the convergence results of objective function accord to the theoretical properties and nonconvex sparse learning methods can achieve superior performance over some convex ones. © 2013 IEEE.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Line Prediction and Transform for Intra Coding

引用

Chinese Journal of Electronics 2023年第3期20卷 516-520页

作者： Jie JIANG Baolong GUO Changcai LAI Wei MO Institute of Intelligence Control and Image Engineering Xidian University Xi'an China Advanced Research Department Huawei Hisilicon Technologies Shenzhen China China Electronics Standardization Institute Beijing China

A new intra coding method based on one dimensional line prediction with different transform is presented. The H.264/ AVC design includes a multidirectional spatial prediction method to reduce spatial redundancy by using neighboring samples as a predictor for all the samples in a block of data to be encoded. In the proposed intra coding method, the spatial prediction is performed line-based in horizontal or vertical direction instead of in the block-based manner used in the current H.264/AVC standard, while the block structure is either retained or one dimensional based for the residual difference transform and entropy coding process. Experimental results on CIF (352 × 288) and 720P (1280 × 720) sequences show that the new line based intra coding framework reduces the bit rate by approximately 7% and up to 12% at the same PSNR in comparison with H.264/ AVC baseline profile.

关键词： Electric potential Quantization (signal) Bit rate Redundancy Transforms Prediction methods Prediction algorithms

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：