检索结果-内蒙古大学图书馆

Learning to Branch in Combinatorial Optimization With Graph Pointer Networks

IEEE/CAA Journal of Automatica Sinica 2024年第1期11卷 157-169页

作者： Rui Wang Zhiming Zhou Kaiwen Li Tao Zhang Ling Wang Xin Xu Xiangke Liao IEEE the Xiangjiang Laboratory and the College of Systems Engineering National University of Defense TechnologyChangsha 410073China the Institute of Automation Chinese Academy of SciencesBeijing 100190China the College of Systems Engineering National University of Defense TechnologyChangsha 410073 the Hunan Key Laboratory of Multi-Energy System Intelligent Interconnection Technology Changsha 410073China the Department of Automation Tsinghua UniversityBeijing 100084China the College of Intelligence Science and Technology National University of Defense TechnologyChangsha 410073China the College of Computer Science and Technology National University of Defense TechnologyChangsha 410073China

Traditional expert-designed branching rules in branch-and-bound(B&B) are static, often failing to adapt to diverse and evolving problem instances. Crafting these rules is labor-intensive, and may not scale well with complex *** the frequent need to solve varied combinatorial optimization problems, leveraging statistical learning to auto-tune B&B algorithms for specific problem classes becomes attractive. This paper proposes a graph pointer network model to learn the branch rules. Graph features, global features and historical features are designated to represent the solver state. The graph neural network processes graph features, while the pointer mechanism assimilates the global and historical features to finally determine the variable on which to branch. The model is trained to imitate the expert strong branching rule by a tailored top-k Kullback-Leibler divergence loss function. Experiments on a series of benchmark problems demonstrate that the proposed approach significantly outperforms the widely used expert-designed branching rules. It also outperforms state-of-the-art machine-learning-based branch-and-bound methods in terms of solving speed and search tree size on all the test instances. In addition, the model can generalize to unseen instances and scale to larger instances.

关键词： Branch-and-bound(B&B) combinatorial optimization deep learning graph neural network imitation learning

来源：评论

学校读者我要写书评

暂无评论

An Image Semantic Communication system Based on GAN and Relative Position-Encoding

引用

IEEE Communications Letters 2025年第6期29卷 1280-1284页

作者： Zhang, Ziqi Tan, Weijie Li, Chunguo Guizhou University College of Big Data and Information Engineering Guiyang550025 China Guizhou University State Key Laboratory of Public Big Data College of Computer Science and Technology Guiyang550025 China Advanced Cryptography and System Security Key Laboratory of Sichuan Province Chengdu610025 China Ministry of Industry and Information Technology Laboratory of Cryptography Application Technology Innovation and Testing Verification Beijing100015 China Southeast University School of Information Science and Engineering Nanjing210096 China

In image semantic communication, the complex wireless channel environment leads to the loss of image details and performance degradation during transmission. To address this issue, we propose an image semantic communication system based on Generative Adversarial Networks (GAN) and Relative Position-Encoding (RPE), named GAN-RpeSC. Specifically, in the system design, we introduce the GAN network at the output of the semantic communication framework to enhance the image restoration. We integrate the RPE module into the Visual Transformer (ViT) module, adding the RPE module to its Multihead Self Attention (MHSA), so that the model can better capture the spatial location information of the image. Experimental results show that the proposed GAN-RpeSC has significant advantages in improving image transmission quality, with a 0.3 dB improvement in peak signal-to-noise ratio (PSNR) compared to the ViT module alone. © 1997-2012 IEEE.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

The blessing of Depth Anything:An almost unsupervised approach to crop segmentation with depth-informed pseudo labeling

引用

植物表型组学（英文） 2025年第1期7卷 49-65页

作者： Songliang Cao Binghui Xu Wei Zhou Letian Zhou Jiafei Zhang Yuhui Zheng Weijuan Hu Zhiguo Han Hao Lu National Key Laboratory of Multispectral Information Intelligent Processing Technology School of Artificial Intelligence and AutomationHuazhong University of Science and TechnologyWuhan430074China PhenoTrait Technology Co. Ltd.Beijing100096China MetaPheno Laboratory Shanghai201114China National Key Laboratory of Multispectral Information Intelligent Processing Technology School of Artificial Intelligence and AutomationHuazhong University of Science and TechnologyWuhan430074China PhenoTrait Technology Co. Ltd.Beijing100096China MetaPheno Laboratory Shanghai201114China SpeCloud Technology Co. Ltd.Sanya572025China State Key Laboratory of Plant Cell and Chromosome Engineering Institute of Genetics and Developmental BiologyChinese Academy of SciencesBeijing100101China

We present Depth-Informed Crop Segmentation(DepthCropSeg),an almost unsupervised crop segmentation approach without manual pixel-level *** segmentation is a fundamental vision task in agriculture,which benefits a number of downstream applications such as crop growth monitoring and yield *** the past decade,image-based crop segmentation approaches have shifted from classic color-based paradigms to recent deep learning-based *** latter,however,rely heavily on large amounts of data with high-quality manual annotation such that considerable human labor and time are *** this work,we leverage Depth Anything V2,a vision foundation model,to produce high-quality pseudo crop masks for training segmentation *** compile a dataset of 17,199 images from six public plant segmentation sources,generating pseudo masks from depth maps after normalization and *** a coarse-to-fine manual screening,1378 images with reliable masks are *** compare four semantic segmentation models and enhance the top-performing one with depth-informed two-stage self-training and depth-informed *** evaluate the feasibility and robustness of DepthCropSeg,we benchmark the segmentation performance on 10 public crop segmentation testing sets and a self-collect dataset covering in-field,laboratory,and unmanned aerial vehicle(UAV)*** results show that our DepthCropSeg approach can achieve crop segmentation performance comparable to the fully supervised model trained with manually annotated data(86.91 vs.87.10).For the first time,we demonstrate almost unsupervised,close-to-full-supervision crop segmentation successfully.

关键词： Crop segmentation Plant phenotyping Depth anything Segment anything Efficient labeling

来源：评论

学校读者我要写书评

暂无评论

Multi-timescale feature extraction method of wastewater treatment process based on adaptive entropy

引用

Chinese Journal of Chemical engineering 2024年第12期76卷 264-271页

作者： Honggui Han Yaqian Zhao Xiaolong Wu Hongyan Yang School of Information Science and Technology Beijing University of TechnologyBeijing 100124China College of Environmental Sciences and Engineering Beijing University of TechnologyBeijing 100124China Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing 100124China Engineering Research Center of Digital Community Ministry of EducationBeijing 100124China

In wastewater treatment systems,extracting meaningful features from process data is essential for effective monitoring and ***,the multi-time scale data generated by different sampling frequencies pose a challenge to accurately extract *** solve this issue,a multi-timescale feature extraction method based on adaptive entropy is ***,the expert knowledge graph is constructed by analyzing the characteristics of wastewater components and water quality data,which can illustrate various water quality parameters and the network of relationships among ***,multiscale entropy analysis is used to investigate the inherent multi-timescale patterns of water quality data in depth,which enables us to minimize information loss while uniformly optimizing the ***,we harness partial least squares for feature extraction,resulting in an enhanced representation of sample data and the iterative enhancement of our expert knowledge *** experimental results show that the multi-timescale feature extraction algorithm can enhance the representation of water quality data and improve monitoring capabilities.

关键词： Feature extraction Knowledge graph Wastewater treatment process Adaptive entropy

来源：评论

学校读者我要写书评

暂无评论

Silicon dioxide-protection boosting the peroxidase-like activity of Fe single-atom catalyst for combining chemo-photothermal therapy

引用

Nano Research 2024年第6期17卷 4924-4933页

作者： Yu Fan Yu Yi Hongpan Rong Jiatao Zhang Beijing Key Laboratory of Construction-Tailorable Advanced Functional Materials and Green Applications School of Materials Science&EngineeringBeijing Institute of TechnologyBeijing 100081China CAS Center for Excellence in Nanoscience CAS KeyLaboratory for Biomedical Effects of Nanomaterials and NanosafetyNational Center for Nanoscience and Technology(NCNST)Beijing 100190China Key Laboratory of Medical Molecule Science and Pharmaceutics Engineering Ministry of Industry and Information TechnologySchool of Chemistry&Chemical EngineeringBeijing Key Laboratory of Construction-Tailorable Advanced Functional Materials and Green ApplicationsSchool of Materials Science and EngineeringBeijing Institute of TechnologyBeijing 100081China

Carbon-based single-atom catalysts(SACs)have been widely studied in the field of biomedicine due to their excellent catalytic ***,carbon-based SACs usually aggregate during pyrolysis,which leads to the reduction of catalytic ***,we describe a method to improve the monodispersion of SACs using silicon dioxide as a protective *** decoration of silicon dioxide serves as a buffer layer for individual nanoparticles,which is not destroyed during the pyrolysis process,ensuring the single-particle dispersion of the nanoparticles after *** approach increased the hydroxyl groups on the surface of Fe-SAC(Fe-SAC-SE)and improved its water solubility,resulting in a four times enhancement of the peroxidase(POD)-like activity of Fe-SAC-SE(58.4 U/mg)than that of non-protected SACs(13.9 U/mg).The SiO_(2)-protection approach could also improve the catalytic activities of SACs with other metals such as Mn,Co,Ni,and Cu,indicating its generality for SACs *** advantage of the high POD-like activity,photothermal properties,and large specific surface area of Fe-SAC-SE,we constructed a synergistic therapeutic system(Fe-SAC-SE@DOX@PEG)for combining the photothermal therapy,catalytic therapy,and *** was verified that the photothermal properties of Fe-SAC-SE@DOX@PEG could effectively improve its POD-like activity,exhibiting excellent tumor-killing performance at the cellular *** work may provide a general approach to improve the performances of SACs for disease therapy and diagnosis.

关键词： single-atom catalysts peroxidase-like activity SiO2-protection photothermal therapy catalytic therapy chemotherapy

来源：评论

学校读者我要写书评

暂无评论

Novel Sparse Codebook Design for MIMO-SCMA

引用

IEEE Transactions on Vehicular technology 2025年第5期74卷 8407-8412页

作者： Lei, Tuofeng Luo, Qu Ni, Shuyan Chen, Shimiao Yu, Lisu Xiao, Pei Space Engineering University Key Laboratory of Intelligent Space TTC&O Ministry of Education Beijing101416 China University of Electronic Science and Technology of China National Key Laboratory of Science and Technology on Communications Chengdu610054 China Nanchang University School of Information Engineering Nanchang330031 China Xidian University State Key Laboratory of ISN Xi'an710071 China

The combination of multiple-input multiple-output (MIMO) and sparse code multiple access (SCMA), referred to as MIMO-SCMA, can be leveraged to achieve high spectrum efficiency and provide massive connectivity for future machine-type communication networks. This paper aims to design enhanced sparse codebooks for MIMO-SCMA by jointly combining frequency and spatial diversity over Rayleigh fading channels. First, based on the pairwise error probability (PEP), novel codebook design criteria have been presented, namely the hybrid minimum product distance of the Euclidean distance (MPD-ED) and the minimum Euclidean distance of the superimposed constellation at each frequency element (MED-FE). Then, enhanced mother constellations (MC) are proposed by maximizing the MPD-ED of the MC based on the alternating optimization. Subsequently, the multi-dimensional codebooks are obtained by applying user-specific rotation of the proposed MC to maximize the MED-FE, where the unitary rotations are considered to fully leverage the Euclidean space of the transmit antennas while maintaining the MPD-ED value of the codebook. Finally, numerical results demonstrate that the proposed approach significantly outperforms the state-of-the-art codebooks. © 1967-2012 IEEE.

关键词： Fading channels

来源：评论

学校读者我要写书评

暂无评论

High-performance self-powered ultraviolet to near-infrared photodetector based on WS_(2)/InSe van der Waals heterostructure

引用

Nano Research 2023年第5期16卷 7851-7857页

作者： Jinping Chen Zhen Zhang Yi Ma Jiying Feng Xiaoyu Xie Xiaoxuan Wang Aoqun Jian Yuanzheng Li Zhuxin Li Heng Guo Yizhi Zhu Qiannan Cui Zengliang Shi Chunxiang Xu State Key Laboratory of Bioelectronics School of Biological Science and Medical EngineeringSoutheast UniversityNanjing 210096China Micro Nano System Research Center Key Laboratory of Advanced Transducers and Intelligent Control System of the Ministry of Education&College of Information Engineering and ComputerTaiyuan University of TechnologyTaiyuan 030024China Key Laboratory of UV-Emitting Materials and Technology of Ministry of Education Northeast Normal UniversityChangchun 130024China

van der Waals heterostructures(vdWHs)based on two-dimensional(2D)materials without the crystal lattice matching constraint have great potential for high-performance optoelectronic ***,a WS_(2)/InSe vdWH photodiode is proposed and fabricated by precisely stacking InSe and WS_(2)flakes through an all-dry transfer *** WS_(2)/InSe vdWH forms an n–n heterojunction with strong built-in electric field due to their intrinsic n-type semiconductor characteristics and energy-band alignments with a large Fermi level offset between WS_(2)and *** a result,the device displays excellent photovoltaic behavior with a large open voltage of 0.47 V and a short-circuit current of 11.7 nA under 520 nm light ***,a fast rising/decay time of 63/76μs,a large light on/off ratio of 105,a responsivity of 61 mA/W,a high detectivity of 2.5×10^(11) Jones,and a broadband photoresponse ranging from ultraviolet to near-infrared(325–980 nm)are achieved at zero *** study provides a strategy for developing high-performance self-powered broadband photodetectors based on 2D materials.

关键词： two-dimensional materials van der Waals heterostructure self-powered photodetector photocurrent

来源：评论

学校读者我要写书评

暂无评论

Event-enhanced synthetic aperture imaging

引用

science China(information sciences) 2025年第3期68卷 388-390页

作者： Siqi LI Shaoyi DU Jun-Hai YONG Yue GAO Beijing National Research Center for Information Science and Technology School of SoftwareTsinghua University Institute for Brain and Cognitive Sciences Beijing Laboratory of Brain and Cognitive IntelligenceTsinghua University National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and ApplicationsInstitute of Artificial Intelligence and Robotics Xi'an Jiaotong University

Synthetic aperture imaging(SAI) methods aim to see through dense occlusions and reconstruct the target scene behind occlusions. Traditional frame-based SAI methods,e.g., DeOccNet [1], take the occluded light field ima...

关键词：

来源：评论

学校读者我要写书评

暂无评论

Using multi-scale interaction mechanisms in yolk-shell structured C/Co composite materials for electromagnetic wave absorption

引用

材料科学技术（英文版） 2025年第12期215卷 36-44页

作者： Jintang Zhou Kexin Zou Jiaqi Tao Jun Liu Yijie Liu Lvtong Duan Zhenyu Cheng Borui Zha Zhengjun Yao Guiyu Peng Xuewei Tao Hexia Huang Yao Ma Peijiang Liu Key Laboratory of Material Preparation and Protection for Harsh Environment Ministry of Industry and Information TechnologyCollege of Materials Science and TechnologyNanjing University of Aeronautics and AstronauticsNanjing211100China Yuxi Research Institute Yuxi Industries GroupChina North Industries CroupNanyang473000China School of Materials Science and Engineering Nanjing Institute of TechnologyNanjing211167China Key Laboratory of Material Preparation and Protection for Harsh Environment Ministry of Industry and Information TechnologyCollege of Materials Science and TechnologyNanjing University of Aeronautics and AstronauticsNanjing211100China College of Energy and Power Engineering Nanjing University of Aeronautics and AstronauticsNanjing210016China National Key Laboratory on Electromagnetic Environmental Effects and Electro-optical Engineering Army Engineering UniversityNanjing210007China Science and Technology on Reliability Physics and Application Technology of Electronic Component Laboratory the 5th Electronics Research Institute of the Ministry of Industry and Information TechnologyGuangzhou511370China

Advanced chemical engineering for simultaneous modulation of nanomaterial morphology,defects,inter-faces,and structure to enhance electromagnetic and microwave absorption(MA)***,accurately distinguishing the MA contributions of different scale factors and tuning the optimal com-bined effects remains a formidable *** study employs a synergistic approach combining tem-plate protection etching and vacuum annealing to construct a controlled system of micrometer-sized cav-ities and amorphous carbon matrices in metal-organic framework(MOF)*** results demon-strate that the spatial effects introduced by the hollow structure enhance dielectric loss but significantly weaken impedance *** increasing the proportion of amorphous carbon,the balance between electromagnetic loss and impedance matching can be effectively ***,in a suitable graphitization environment,the presence of oxygen vacancies in amorphous carbon can induce signif-icant polarization to compensate for the reduced conductivity loss due to the absence of sp2 *** the synergistic effects of morphology and composition,the samples exhibit a broader absorp-tion bandwidth(6.28 GHz)and stronger reflection loss(-61.64 dB)compared to the original *** conclusion,this study aims to elucidate the multiscale impacts of macroscopic micro-nano structure and microscopic defect engineering,providing valuable insights for future research in this field.

关键词： MOFs Multi-scale regulation Yolk-shell structure Amorphous carbon Oxygen vacancy Microwave absorption

来源：评论

学校读者我要写书评

暂无评论

Optimization of Anti-Air Defense Missile system Based on Kill Chain 3

Optimization of Anti-Air Defense Missile System Based on Kil...

引用

3rd International Symposium on Computer technology and information science, ISCTIS 2023

作者： Hu, Tao Luo, Xueshan Zhang, Xiaoxue Chen, Tao Cao, Tianruo Yuan, Hao National University of Defense Technology Science and Technology on Information System Engineering Laboratory Hunan Changsha China

ISBN: (纸本)9798350325386

The issue of resource allocation is the key to design the Anti-Air Defense Missile system As this is an NP-hard problem, allocating only end-point firepower cannot thoroughly address the issue. To better cater to real combat environments, this article uses a kill chain-based system resource allocation model that includes task completion rate, firepower cost, and completion time by utilizing discrete resources. To address the resource allocation problem, we optimized the non-dominated sorting genetic algorithm III (NSGA-III) by incorporating k-means clustering and the average clustering distance for congestion resolution. The results demonstrate that this method is effective in solving complex resource allocation problems, providing strong support for the command and decision-making of actual defense forces. © 2023 IEEE.

关键词： Resource allocation

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：