检索结果-南通市图书馆

维普期刊数据库

DepthGAN: GAN-based depth generation from semantic layouts

在线全文

学校读者我要写书评

暂无评论

Computational Visual Media 2024年第3期10卷 505-522页

作者： Yidi Li jun xiao Yiqun Wang Zhengda lu school of Artificial Intelligence University of Chinese Academy of SciencesBeijingChina College of Computer Science Chongqing UniversityChongqingChina

Existing GAN-based generative methodsare typically used for semantic image synthesis. Wepose the question of whether GAN-based architecturescan generate plausible depth maps and find thatexisting methods have difficulty in generating depthmaps which reasonably represent 3D scene structuredue to the lack of global geometric ***, we propose DepthGAN, a novel method ofgenerating a depth map using a semantic layout asinput to aid construction, and manipulation of wellstructured 3D scene point clouds. Specifically, wefirst build a feature generation model with a cascadeof semantically-aware transformer blocks to obtaindepth features with global structural *** our semantically aware transformer block, wepropose a mixed attention module and a semanticallyaware layer normalization module to better exploitsemantic consistency for depth features ***, we present a novel semantically weighteddepth synthesis module, which generates adaptivedepth intervals for the current scene. We generate thefinal depth map by using a weighted combination ofsemantically aware depth weights for different depthranges. In this manner, we obtain a more accuratedepth map. Extensive experiments on indoor andoutdoor datasets demonstrate that DepthGAN achievessuperior results both quantitatively and visually for thedepth generation task.

关键词： depth map generation generative model transformer scene generation

Feature Matching via Topology-Aware Graph Interaction Model

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第1期11卷 113-130页

作者： Yifan lu Jiayi Ma xiaoguang Mei jun Huang xiao-Ping Zhang the Electronic Information school Wuhan UniversityWuhan 430072China IEEE Tsinghua Berkeley Shenzhen Institute Shenzhen 518071China the Department of Electrical Computer and Biomedical EngineeringToronto Metropolitan UniversityToronto ON M5B 2K3Canada

Feature matching plays a key role in computer vision. However, due to the limitations of the descriptors, the putative matches are inevitably contaminated by massive *** paper attempts to tackle the outlier filtering problem from two aspects. First, a robust and efficient graph interaction model,is proposed, with the assumption that matches are correlated with each other rather than independently distributed. To this end, we construct a graph based on the local relationships of matches and formulate the outlier filtering task as a binary labeling energy minimization problem, where the pairwise term encodes the interaction between matches. We further show that this formulation can be solved globally by graph cut algorithm. Our new formulation always improves the performance of previous localitybased method without noticeable deterioration in processing time,adding a few milliseconds. Second, to construct a better graph structure, a robust and geometrically meaningful topology-aware relationship is developed to capture the topology relationship between matches. The two components in sum lead to topology interaction matching(TIM), an effective and efficient method for outlier filtering. Extensive experiments on several large and diverse datasets for multiple vision tasks including general feature matching, as well as relative pose estimation, homography and fundamental matrix estimation, loop-closure detection, and multi-modal image matching, demonstrate that our TIM is more competitive than current state-of-the-art methods, in terms of generality, efficiency, and effectiveness. The source code is publicly available at http://***/Yifanlu2000/TIM.

关键词： Feature matching graph cut outlier filtering topology preserving

维普期刊数据库

CNN-LSTM based incremental attention mechanism enabled phase-space reconstruction for chaotic time series prediction

在线全文

学校读者我要写书评

暂无评论

Journal of Electronic Science and Technology 2024年第2期22卷 77-90页

作者： xiao-Qian lu jun Tian Qiang Liao Zheng-Wu Xu lu Gan Bidding and Purchasing Center University of Electronic Science and Technology of ChinaChengdu611731China Yibin Research Institute University of Electronic Science and Technology of ChinaYibin644000China school of Information and Communication Engineering University of Electronic Science and Technology of ChinaChengdu611731China

To improve the prediction accuracy of chaotic time series and reconstruct a more reasonable phase space structure of the prediction network,we propose a convolutional neural network-long short-term memory(CNN-LSTM)prediction model based on the incremental attention ***,a traversal search is conducted through the traversal layer for finite parameters in the phase ***,an incremental attention layer is utilized for parameter judgment based on the dimension weight criteria(DWC).The phase space parameters that best meet DWC are selected and fed into the input ***,the constructed CNN-LSTM network extracts spatio-temporal features and provides the final prediction *** model is verified using Logistic,Lorenz,and sunspot chaotic time series,and the performance is compared from the two dimensions of prediction accuracy and network phase space ***,the CNN-LSTM network based on incremental attention is compared with long short-term memory(LSTM),convolutional neural network(CNN),recurrent neural network(RNN),and support vector regression(SVR)for prediction *** experiment results indicate that the proposed composite network model possesses enhanced capability in extracting temporal features and achieves higher prediction ***,the algorithm to estimate the phase space parameter is compared with the traditional CAO,false nearest neighbor,and C-C,three typical methods for determining the chaotic phase space *** experiments reveal that the phase space parameter estimation algorithm based on the incremental attention mechanism is superior in prediction accuracy compared with the traditional phase space reconstruction method in five networks,including CNN-LSTM,LSTM,CNN,RNN,and SVR.

关键词： Chaotic time series Incremental attention mechanism Phase-space reconstruction

Experimental study of the damage characteristics of rocks containing non-penetrating cracks under cyclic loading

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of Mining Science and Technology 2024年第2期34卷 197-210页

作者： jun Xu xiaochun xiao lu Ma Sen luo Jiaxu Jin Baijian Wu school of Mechanics and Engineering Liaoning Technical UniversityFuxin 123000China school of Civil Engineering Liaoning Technical UniversityFuxin 123000China Department of Engineering Mechanics Southeast UniversityNanjing 211189China

The damage evolution process of non-penetrating cracks often causes some unexpected engineering *** specimens containing non-penetrating crack(s)are used to study the damage evolution and characteristics under cyclic *** results show that under cyclic loading,the relationship between the number of non-penetrating crack(s)and the characteristic parameters(cyclic number,peak stress,peak strain,failure stress,and failure strain)of the pre-cracked specimens can be represented by a decreasing linear *** damage evolution equation is fitted by calibrating the accumulative plastic strain for each cycle,and the damage constitutive equation is proposed by the concept of effective ***,non-penetrating cracks are more likely to cause uneven stress distribution,damage accumulation,and local failure of *** local failure can change the stress distribution and relieve the inhibition of non-penetrating crack extension and eventually cause a dramatic destruction of the ***,the evolution process caused by non-penetrating cracks can be regarded as one of the important reasons for inducing *** results are expected to improve the understanding of the process of spalling formation and rockburst and can be used to analyze the stability of rocks or rock structures.

关键词： Damage characteristics Constitutive model Fissured rocks Non-penetrating crack Cyclic loading

维普期刊数据库

Review on regulation of MnS in non-qquenched and tempered steel

在线全文

学校读者我要写书评

暂无评论

Journal of Iron and Steel Research International 2024年第4期31卷 779-789页

作者： Guo-xing Qiu Qing Du Feng lu De-jun Miao Yong-kun Yang xiao-ming Li school of Metallurgical Engineering Xi'an University of Architecture and TechnologyXi'an 710055ShaanxiChina Laigang Technique Center Shandong Iron and Steel Group Co.Ltd.Jinan 271104ShandongChina

An overview of the current research status and control methods of MnS in non-quenched and tempered steel was *** a low-melting plastic inclusion,the morphology and distribution of MnS were influenced by various production ***,control of MnS is a systematic problem that must be integrated into the entire production *** on the production process,the factors affecting the morphology and distribution of MnS in steel were *** effects of oxygen activity,manganese,sulfur,and some alloys on MnS inclusion precipitation were summarized,mainly including MnS modification treatment and oxygen-sulfide composite precipitation *** is believed that MnS precipitates during the solidification process of steel,and controlling the solidification cooling rate could effectively regulate the size and morphology of MnS,avoiding the precipitation of ***,by changing the deformation rate,deformation amount,deformation temperature during the hot deformation process,and heating time and temperature during heat treatment,the distribution and morphology of MnS could be *** the fine control of the above process parameters,the number of II-MnS in steel could be effectively reduced,and their morphology could be improved,thereby enhancing the performance of non-quenched and tempered steel and promoting its wider ***,applying laboratory research results to industrial production is an important direction for future research efforts in this field.

关键词： MnS Non-quenched and tempered steel Control technology Process parameter Morphology Distribution

Energy-efficient buffer and service rate allocation in manufacturing systems using hybrid machine learning and evolutionary algorithms

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Advances in Manufacturing 2024年第2期12卷 227-251页

作者： Si-xiao Gao Hui Liu jun Ota Key Laboratory of Traffic Safety on Track of Ministry of Education Institute of Artificial Intelligence and Robotics(IAIR)School of Traffic and Transportation EngineeringCentral South UniversityChangsha410075People’s Republic of China Research into Artifacts Center for Engineering School of EngineeringThe University of TokyoTokyoJapan

Currently,simultaneous buffer and service rate allocation is a topic of interest in the optimization of manufacturing *** allocation problems have been solved previously to satisfy economic requirements;however,owing to the progress of green manufacturing,energy conservation and environmental protection have become increasingly ***,an energy-efficient approach is developed to maximize the throughput and minimize the energy consumption of manufacturing systems,subject to the total buffer capacity,total service rate,and predefined energy *** energy-efficient approach integrates the simulated annealing-non-dominated sorting genetic algorithm-II with the honey badger algorithm-histogram-based gradient boosting regression *** former algorithm searches for Pareto-optimal solutions of sufficient *** latter algorithm builds prediction models to rapidly calculate the throughput,energy consumption,and energy *** examples show that the proposed hybrid approach can achieve a better solution quality compared with previously reported ***,the prediction models can rapidly evaluate manufacturing systems with sufficient *** study benefits the multi-objective optimization of green manufacturing systems.

关键词： Energy-efficient allocation Multi-objective optimization Energy efficiency Energy consumption Machine learning

Triboelectric nanogenerators for self-powered neurostimulation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Nano Research 2024年第10期17卷 8926-8941页

作者： Shumao Xu Farid Manshaii xiao xiao junyi Yin jun Chen Department of Bioengineering University of CaliforniaLos AngelesLos AngelesCA 90095USA

The burgeoning field of soft bioelectronics heralds a new dawn in medical treatment for neurological and psychiatric conditions,presenting innovative methods for the stimulation,inhibition,and precise sensing of neuronal *** to these advancements is the challenge of power supply;devices dependent on traditional batteries face limitations regarding miniaturization and require invasive surgeries for battery *** nanogenerators(TENGs),which generate power from biomechanical movements,offer a promising solution for developing self-powered neurostimulation devices without the need for an external power *** review delves into recent progress in TENGs,with a focus on their application in selfpowered neurostimulation *** utility of TENGs across various nervous systems—including the center,autonomic,and somatic nervous systems—is explored and presented,highlighting the potential for these devices to facilitate neurological *** summarizing TENGs’operational details and the potential for clinical translation,this review also identifies challenges associated with the implantation and integration of neural electrodes and presents recent advances in solutions,aiming to reshape electric treatments for neurological diseases.

关键词： triboelectric nanogenerators neurostimulation self-powered soft bioelectronics biomechanical energy harvesting

Mechanism of Ta on the microstructure and properties of Fe-Mn damping alloys

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Tungsten 2024年第4期6卷 767-777页

作者： Gui-Xiang Liu Kun Zhang Chao Han xiao-Lin Shao jun lu Lin Zhang xiao-Song Jiang Zi-Xuan Wu Liu Yang The Second Sub-Institute Nuclear Power Institute of China Key Laboratory of Advanced Technologies of Materials Ministry of Education school of Materials Science and Engineering Southwest Jiao tong University school of Engineering and Materials Science Queen Mary University of London Institute for Applied Materials (IAM-WK) Karlsruhe Institute of Technology (KIT)

Fe-Mn-Co-xTa alloys（x=0,1,2,3 wt.%） were fabricated using spark plasma sintering to explore the influence of Ta content on the microstructure,mechanical properties,and damping characteristics of Fe-17Mn-3Co damping *** micro structural analysis reveals the dominant presence of γ-austenite,ε-martensite,α'-martensite,and Co3Ta precipitates within the *** increments in Ta content exhibit proportional enhancements in hardness,tensile strength,and fracture elongation of the ***,these improvements in mechanical attributes are closely correlated with the generated second-phase *** the Ta content increases,there is a gradual augmentation in the formation of Co3Ta within the ***,the damping property initially experiences an ascent followed by a subsequent decline with rising Ta *** damping behavior finds its origins in multiple mechanisms,including grain boundary damping stemming from reduced grain size,interfacial damping induced by the generated Co3Ta,and dislocation *** is noteworthy that the emergence of the secondary phase wields a dual impact on damping *** the one hand,the proliferation of the second phase fosters increased interfaces for energy *** the other hand,these interfaces give rise to compressive stresses,constraining interface movement and thus impeding damping property enhancement.

关键词： Damping Fe–Mn–Co Mechanical properties Spark plasma sintering Ta

Joint Sample Position Based Noise Filtering and Mean Shift Clustering for Imbalanced Classification Learning

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Tsinghua Science and Technology 2024年第1期29卷 216-231页

作者： Lilong Duan Wei Xue jun Huang xiao Zheng school of Computer Science and Technology Anhui University of TechnologyMaanshan 243032China Institute of Artificial Intelligence Hefei Comprehensive National Science CenterHefei 230088China

The problem of imbalanced data classification learning has received much *** classification algorithms are susceptible to data skew to favor majority samples and ignore minority *** weighted minority oversampling technique(MWMOTE)is an effective approach to solve this problem,however,it may suffer from the shortcomings of inadequate noise filtering and synthesizing the same samples as the original minority *** this end,we propose an improved MWMOTE method named joint sample position based noise filtering and mean shift clustering(SPMSC)to solve these ***,in order to effectively eliminate the effect of noisy samples,SPMsC uses a new noise filtering mechanism to determine whether a minority sample is noisy or not based on its position and distribution relative to the majority *** that MWMOTE may generate duplicate samples,we then employ the mean shift algorithm to cluster minority samples to reduce synthetic replicate ***,data cleaning is performed on the processed data to further eliminate class *** on extensive benchmark datasets demonstrate the effectiveness of SPMsC compared with other sampling methods.

关键词： imbalanced data classification oversampling noise filtering clustering