检索结果-内蒙古大学图书馆

Robust Representation Learning Based on Deep Mutual Information for Scene Classification Against Adversarial Perturbations

引用

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2025年 18卷 11963-11978页

作者： Li, Linjuan Xie, Gang Zhang, Haoxue Xie, Xinlin Li, Heng Taiyuan University of Science and Technology School of Electronic Information Engineering Taiyuan030024 China Shanxi Key Laboratory of Advanced Control and Equipment Intelligence Taiyuan030024 China The Hong Kong Polytechnic University Department of Building and Real Estate Hong Kong

Remote sensing scene classification enables data-driven decisions for various applications, such as environmental monitoring, urban planning, and disaster management. However, deep learning models used for scene classification are highly vulnerable to adversarial samples, resulting in incorrect predictions and posing significant risks. While most current methods focus on improving adversarial robustness, they face a trade-off that compromises accuracy on clean, unperturbed images. To address this challenge, we utilized information theory by incorporating a mutual information (MI) representation (MIR) module, which allows the model to capture high-quality, robust features. Furthermore, a domain adversarial training (AdvT) strategy is applied to promote the learning of domain-invariant features, reducing the effect of distribution differences between clean images and adversarial samples. We propose a novel algorithm that accurately differentiates between clean and adversarial scenes by introducing the MI and domain adaptation-guided network (MIDANet). Extensive experiments demonstrate the effectiveness of our approach against adversarial attacks, revealing a positive correlation between adversarial perturbations and image information entropy, and a negative correlation with robust accuracy (RAcc). © 2008-2012 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Rapid Detection of Deformable Mirrors Based on Phase Measuring Deflectometry 10

Rapid Detection of Deformable Mirrors Based on Phase Measuri...

引用

10th Symposium on Novel optoelectronic Detection technology and Applications

作者： Li, Zhaoyang Wang, Shanshan Zhou, Shuhong Zhang, Nansheng Fu, Tao Hao, Qun National Key Laboratory on Near-Surface Detection Beijing100072 China School of Optics and Photonics Beijing Institute of Technology Beijing100081 China Shanghai Aerospace Control Technology Institute Shanghai201109 China School of Opto-Electronic Engineering Changchun University of Science and Technology Changchun130022 China

ISBN: (数字)9781510688155

ISBN: (纸本)9781510688148

Deformable mirrors play a critical role in adaptive optics systems, and as the precision demands of optical systems continue to rise, the accurate detection of deformable mirror shape and performance becomes essential to the overall system's effectiveness. Improved detection methods can significantly enhance the design quality and manufacturing precision of deformable mirrors. In this paper, we introduce a phase measuring deflectmetry that directly measures slope variations to detect the surface deformation of deformable mirrors. To further enhance measurement accuracy, monitoring stations are integrated into the system. We conducted measurements on a 100mm-diameter deformable mirror, and through comparisons of simulation and experimental results, we verified that the system provides high measurement accuracy and real-time monitoring of dynamic error influences. This system is well-suited for long-term monitoring of surface changes in deformable mirrors. © 2025 SPIE.

关键词： Adaptive optics

来源：评论

学校读者我要写书评

暂无评论

Wave guiding and mode coupling at the Dirac point in photonic crystal fibers

引用

Journal of the Optical Society of America A: Optics and Image Science, and Vision 2025年第2期42卷 113-119页

作者： Xie, Kang Jiang, Haiming Xia, Hongyan Hu, Zhijia Zhang, Junxi Mao, Qiuping State Key Laboratory of Precision Electronic Manufacturing Technology and Equipment School of Electromechanical Engineering Guangdong University of Technology Guangzhou510006 China Department of Applied Sciences Northumbria University Newcastle upon TyneNE1 8T United Kingdom School of Physics and Materials Science Anhui University Anhui Hefei230601 China School of Instrument Science and Opto-Electronics Engineering Hefei University of Technology Anhui Hefei230009 China College of Artificial Intelligence Hangzhou Dianzi University Zhejiang Hangzhou310018 China

This work provides an alternative confirmation of Dirac localization in the photonic crystal fiber proposed in Light Sci. Appl. 4, e304 (2015). In weakly guiding fibers, Maxwell equations can be reduced to the wave equation, which can then be further reduced to the Helmholtz equation for time-harmonic waves. The Dirac point in the band structure of the Helmholtz equation in periodic media is analyzed. Wave localization at the Dirac point is numerically demonstrated, which confirms the finding of Light Sci. Appl. 4, e304 (2015). Coupling of Dirac modes is numerically simulated, and the results show remote coupling is feasible. Coupling strength is shown to decrease in an algebraic form with distance. This feature of coupling can be attributed to the massless property of Dirac quasiparticles, which is a precise analog of Klein tunneling of massless relativistic electrons in graphene. © 2025 Optica Publishing Group. All rights, including for text and data mining (TDM), Artificial intelligence (AI) training, and similar technologies, are reserved.

关键词： Photonic crystal fibers

来源：评论

学校读者我要写书评

暂无评论

3D bioprinting of a dermal scaffold for full-thickness skin tissue regeneration

引用

Bio-Design and Manufacturing 2025年第1期8卷 68-84,I0039-I0041页

作者： Lu Han Zixian Liu Meng Li Zhizhong Shen Jianming Wang Shengbo Sang Shanxi Key Laboratory of Micro Nano Sensors&Artificial Intelligence Perception College of Electronic Information and Optical EngineeringTaiyuan University of TechnologyTaiyuan 030024China Key Laboratory of Advanced Transducers and Intelligent Control System of the Ministry of Education Taiyuan University of TechnologyTaiyuan 030024China Shanxi-Zheda Institute of Advanced Materials and Chemical Engineering Taiyuan 030024China Shanxi Research Institute of 6D Artificial Intelligence Biomedical Science Taiyuan 030031China General Hospital of TISCO Taiyuan 030809China

Dermal substitutes have provided a template for the regeneration and reconstruction of the ***,the healed skin tissue often exhibits abnormal morphology and functionality,including scarring and *** this study,a composite bioink composed of methacrylated gelatin(GelMA)and chitosan oligosaccharide(COS)was proposed for printing a dermal scaffold using digital light processing(DLP)*** GelMA/COS bioink exhibited suitable porosity,swelling,degradation rate,and mechanical *** inclusion of COS demonstrated antibacterial effects against both Gram positive and Gram-negative bacteria,while simultaneously fostering the proliferation of human dermal fibroblasts(HDFs).Additionally,the application of COS could effectively reduce the expression levels of fibrosis-related genes,such as collagen I,collagen III,and fibronectin *** three-dimensionally printed cell-laden dermal scaffold exhibited excellent shape fidelity and high cellular viability,facilitating the extension of HDFs along the scaffold and the simultaneous secretion of extracellular matrix ***,the HDF-laden dermal scaffold transplanted into full-thickness skin defect sites in nude mice was shown to accelerate wound closure,reduce inflammation,and improve wound ***,the DLP-printed dermal scaffold provides an appealing approach for effectively treating full-thickness skin defects in clinical settings.

关键词： 3D printing Dermal scaffold Photo-cross-linking Skin tissue regeneration

来源：评论

学校读者我要写书评

暂无评论

Single-Loop Deadbeat Predictive control Framework for Uncertain SPMSM Drives With Disturbance Observation

引用

IEEE Transactions on Transportation Electrification 2025年

作者： Jiang, Fuxi Wang, Siqi Guo, Yuhao Cheng, Zhe Ye, Jie Cheng, Shanmei Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Wuhan430074 China Huazhong University of Science and Technology School of Optical and Electronic Information Wuhan430074 China

To mitigate the detrimental effects of parameter perturbations and external load torque on the accuracy of speed and current tracking control in surface-mounted permanent magnet synchronous motor (SPMSM) drive systems, while avoiding the complexities inherent in traditional speed-current series control architectures, this paper presents a single-loop deadbeat predictive control (SDPC) framework that incorporates online disturbance observation. The control input voltage vector is directly computed using an SDPC controller in conjunction with a set of discrete-time disturbance observers (DDOBs). This proposed methodology offers two notable advantages over existing research: (i) it substantially reduces the number of adjustable controller parameters, requiring only the tuning of the observer bandwidth and the speed scaling gain, which enhances its practicality for engineering applications;and (ii) the disturbance estimation and compensation mechanism utilizing DDOBs significantly improves the robustness of the SPMSM system. Furthermore, the SDPC framework ensures that the system maintains satisfactory transient and steady-state tracking performance in response to reference signals. Experimental comparisons validate both the effectiveness and superiority of the proposed method. © 2015 IEEE.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

Hierarchical finite-time optimization regulation of multiple autonomous surface vehicles for time-varying target cooperative tracking

引用

Kongzhi yu Juece/control and Decision 2025年第1期40卷 279-284页

作者： Ge, Ming-Feng Li, Yi-Fan Liu, Zhi-Wei Gu, Zhi-Wei Chen, Qian School of Mechanical Engineering and Electronic Information China University of Geosciences Wuhan430074 China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Key Laboratory of Imaging Processing and Intelligent Control Ministry of Education Huazhong University of Science and Technology Wuhan430074 China

We propose a novel hierarchical finite-time optimization regulation algorithm for multiple autonomous surface vehicles (ASVs) to achieve cooperative tracking of a time-varying target. An objective function reflecting the energy consumption of the multiple ASVs system in the tracking process is designed, and a finite-time optimal estimator (FTOE) is developed to minimize the objective function in the case that ASVs form a specified formation while following the desired trajectory. Meanwhile, the target trajectory can be variable instead of constant. In the finite-time local controller (FTLC), the sailing states of the multiple ASVs system can be stabilized to the vicinity of the multiple various predefined time-varying trajectories in finite time in a way that minimizes the objective function by tracking the FTOE. The proof of the finite-time stability is provided and the settling time is calculated. Finally, simulation results demonstrate the effectiveness of the proposed hierarchical algorithm. © 2025 Northeast University. All rights reserved.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

ROLO-SLAM: Rotation-Optimized LiDAR-Only SLAM in Uneven Terrain with Ground Vehicle

arXiv

引用

arXiv 2025年

作者： Wang, Yinchuan Ren, Bin Zhang, Xiang Wang, Pengyu Wang, Chaoqun Song, Rui Li, Yibin Meng, Max Q.-H. School of Control Science and Engineering Shandong University Jinan China Shenzhen Key Laboratory of Robotics Perception and Intelligence The Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China

LiDAR-based SLAM is recognized as one effective method to offer localization guidance in rough environments. However, off-the-shelf LiDAR-based SLAM methods suffer from significant pose estimation drifts, particularly components relevant to the vertical direction, when passing to uneven terrains. This deficiency typically leads to a conspicuously distorted global map. In this article, a LiDAR-based SLAM method is presented to improve the accuracy of pose estimations for ground vehicles in rough terrains, which is termed Rotation-Optimized LiDAR-Only (ROLO) SLAM. The method exploits a forward location prediction to coarsely eliminate the location difference of consecutive scans, thereby enabling separate and accurate determination of the location and orientation at the front-end. Furthermore, we adopt a parallel-capable spatial voxelization for correspondence-matching. We develop a spherical alignment-guided rotation registration within each voxel to estimate the rotation of vehicle. By incorporating geometric alignment, we introduce the motion constraint into the optimization formulation to enhance the rapid and effective estimation of LiDAR's translation. Subsequently, we extract several keyframes to construct the submap and exploit an alignment from the current scan to the submap for precise pose estimation. Meanwhile, a global-scale factor graph is established to aid in the reduction of cumulative errors. In various scenes, diverse experiments have been conducted to evaluate our method. The results demonstrate that ROLO-SLAM excels in pose estimation of ground vehicles and outperforms existing state-of-the-art LiDAR SLAM frameworks. Copyright © 2025, The Authors. All rights reserved.

关键词： Magnetic levitation vehicles

来源：评论

学校读者我要写书评

暂无评论

Decoupling Representation Learning for Remote Sensing Semantic Segmentation

IEEE Journal on Miniaturization for Air and Space Systems

引用

IEEE Journal on Miniaturization for Air and Space Systems 2025年

作者： He, Yun Li, LinJuan Xie, Gang Zhang, Haoxue Chen, Feng Liu, Sida Taiyuan University of Science and Technology School of Electronic Information Engineering Taiyuan030024 China Shanxi Key Laboratory Of Advanced Control and Industrial Intelligence Taiyuan030024 China Shanxi Institute of Surveying Mapping and Geoinformation Taiyuan030024 China

Semantic segmentation plays a pivotal role in the interpretation of remote sensing entities. However, the complexity of the environments, diversity of objects, and richness of details make semantic segmentation even more challenging. Existing methods have limitations in inter-class edge continuity and intra-class completeness within segmentation results. To address these issues, a feature decoupling guided Network is developed for learning the discriminative representation. In which the feature decoupling module separates encoded features into homogeneous information for primary object features and distinct information for object boundaries. Another, the semantic-aware integration unit is employed to strengthen semantic consistency during decomposition. To facilitate practical application, we created the Taiyuan Land Cover (TYLC) dataset for semantic segmentation to analyze land resource utilization. Extensive experiments on the TYLC dataset achieved a mean intersection over the union of 54.2%, the mean F1 score of 67.7%, and the mean recall of 66.6%. Quantitative results demonstrate the algorithm’s superiority, and visualizations indicate that the segmentation output has excellent completeness and edge continuity. © 2025 IEEE. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Surrogate-Assisted Multiobjective Gene Selection for Cell Classification from Large-Scale Single-Cell RNA Sequencing Data

引用

IEEE Transactions on Evolutionary Computation 2025年

作者： Lin, Jianqing He, Cheng Jiang, Hanjing Huang, Yabing Jin, Yaochu Huazhong University of Science and Technology Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China School of Artificial Intelligence and Automation Wuhan430074 China Huazhong University of Science and Technology State Key Laboratory of Advanced Electromagnetic Technology School of Electrical and Electronic Engineering Wuhan430074 China Renmin Hospital Department of Pathology Wuhan University Wuhan430060 China Westlake University Trustworth and General Artificial Intelligence Laboratory School of Engineering Hangzhou310030 China

Accurate cell classification is crucial but expensive for large-scale single-cell RNA sequencing (scRNA-seq) analysis. Gene selection (GS) emerges as a pivotal technique in identifying gene subsets of scRNA-seq for classification accuracy improvement and gene scale reduction. Nevertheless, the rising scale of scRNA-seq data presents challenges to existing GS methods regarding performance and computational time. Thus, we propose a surrogate-assisted evolutionary algorithm for multiobjective GS to address these deficiencies. An innovative two-phase initialization method is proposed to select sparse solutions to provide preliminary insights into gene contributions. Then, a binary competitive swarm optimizer is proposed for effective global search, where a local search method is embedded to eliminate irrelevant genes for efficiency consideration. Additionally, a surrogate model is adopted to forecast classification accuracy efficiently and substitutes part of the computationally expensive classification process. Experiments are conducted on eight large-scale scRNA-seq datasets with more than 20,000 genes. The effectiveness of the proposed GS method for scRNA-seq cell classification compared with eight state-of-the-art methods is validated. Gene expression analysis results of selected genes further validated the significance of the genes selected by the proposed method in the classification of scRNA-seq data. © 1997-2012 IEEE.

关键词： Gene expression

来源：评论

学校读者我要写书评

暂无评论

Approximately Invertible Neural Network for Learned Image Compression

引用

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society 2025年 PP卷 PP页

作者： Yanbo Gao Shuai Li Meng Fu Chong Lv Zhiyuan Yang Xun Cai Hui Yuan Mao Ye School of Software Shandong University Jinan China Shandong University-WeiHai Research Institute of Industrial Technology Shandong University Weihai China School of Control Science and Engineering Shandong University Jinan China Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China University of Electronic Science and Technology of China Chengdu Sichuan China

Learned image compression has attracted considerable interests in recent years. An analysis transform and a synthesis transform, which can be regarded as coupled transforms, are used to encode an image to latent feature and decode the feature after quantization to reconstruct the image. Inspired by the success of invertible neural networks in generative modeling, invertible modules can be used to construct the coupled analysis and synthesis transforms. Considering the noise introduced in the feature quantization invalidates the invertible process, this paper proposes an Approximately Invertible Neural Network (A-INN) framework for learned image compression. It formulates the rate-distortion optimization in lossy image compression when using INN with quantization, which differentiates from using INN for generative modelling. Generally speaking, A-INN can be used as the theoretical foundation for any INN based lossy compression method. Based on this formulation, A-INN with a progressive denoising module (PDM) is developed to effectively reduce the quantization noise in the decoding. Moreover, a Cascaded Feature Recovery Module (CFRM) is designed to learn high-dimensional feature recovery from low-dimensional ones to further reduce the noise in feature channel compression. In addition, a Frequency-enhanced Decomposition and Synthesis Module (FDSM) is developed by explicitly enhancing the high-frequency components in an image to address the loss of highfrequency information inherent in neural network based image compression, thereby enhancing the reconstructed image quality. Extensive experiments demonstrate that the proposed A-INN framework achieves better or comparable compression efficiency than the conventional image compression approach and state-of-the-art learned image compression methods.

关键词： Image coding Transforms Decoding Neural networks Quantization (signal) Image reconstruction Noise Entropy Optimization Transform coding

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：