检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第1期5卷 70-79页

作者： Wang, Chunjie Dai, Dawei Xia, Shuyin Liu, Yingge Wang, Guoyin Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and Telecommunications College of Computer Science and Technology Chongqing400065 China

Edge detection, a basic task in the field of computer vision, is an important preprocessing operation for the recognition and understanding of a visual scene. In conventional models, the edge image generated is ambiguous, and the edge lines are also very thick, which typically necessitates the use of nonmaximum suppression (NMS) and morphological thinning operations to generate clear and thin edge images. In this article, we aim to propose a one-stage neural network model that can generate high-quality edge images without postprocessing. The proposed model adopts a classic encoder-decoder framework in which a pretrained neural model is used as the encoder and a multifeature-fusion mechanism that merges the features of each level with each other functions as a learnable decoder. Further, we propose a new loss function that addresses the pixel-level imbalance in the edge image by suppressing the false positive edge information near the true positive edge and the false negative nonedge. The results of experiments conducted on several benchmark datasets indicate that the proposed method achieves state-of-the-art (SOTA) results without using NMS and morphological thinning operations. © 2020 IEEE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

SDGNN: Symmetry-Preserving Dual-Stream Graph Neural Networks

引用

IEEE/CAA Journal of Automatica Sinica 2024年第7期11卷 1717-1719页

作者： Jiufang Chen Ye Yuan Xin Luo the College of Computer Science and Technology Chongqing University of Posts and TelecommunicationsChongqing 400065 the Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent TechnologyChinese Academy of SciencesChongqing 400714China the College of Computer and Information Science Southwest UniversityChongqing 400715China IEEE

Dear Editor,This letter proposes a symmetry-preserving dual-stream graph neural network(SDGNN) for precise representation learning to an undirected weighted graph(UWG). Although existing graph neural networks(GNNs) are influential instruments for representation learning to a UWG, they invariably adopt a unique node feature matrix for illustrating the sole node set of a UWG.

关键词： representation preserving undirected

来源：评论

学校读者我要写书评

暂无评论

Single-cell transcriptomic atlas of goat ovarian aging

引用

Journal of Animal science and Biotechnology 2024年第1期15卷 146-161页

作者： Dejun Xu Shuaifei Song Fuguo Wang Yawen Li Ziyuan Li Hui Yao Yongju Zhao Zhongquan Zhao Chongqing Key Laboratory of Herbivore Science College of Animal Science and TechnologySouthwest UniversityChongqing 400715China

Background The ovaries are one of the first organs that undergo degenerative changes earlier in the aging process,and ovarian aging is shown by a decrease in the number and quality of ***,little is known about the molecular mechanisms of female age-related fertility decline in different types of ovarian cells during aging,especially in ***,the aim of this study was to reveal the mechanisms driving ovarian aging in goats at single-cell *** For the first time,we surveyed the single-cell transcriptomic landscape of over 27,000 ovarian cells from newborn,young and aging goats,and identified nine ovarian cell types with distinct gene-expression *** enrichment analysis showed that ovarian cell types were involved in their own unique biological processes,such as Wnt beta-catenin signalling was enriched in germ cells,whereas ovarian steroidogenesis was enriched in granulosa cells(GCs).Further analysis showed that ovarian aging was linked to GCs-specific changes in the antioxidant system,oxidative phosphorylation,and ***,we identified a series of dynamic genes,such as AMH,CRABP2,THBS1 and TIMP1,which determined the fate of ***,FOXO1,SOX4,and HIF1A were identified as significant regulons that instructed the differentiation of GCs in a distinct manner during ovarian *** This study revealed a comprehensive aging-associated transcriptomic atlas characterizing the cell typespecific mechanisms during ovarian aging at the single-cell level and offers new diagnostic biomarkers and potential therapeutic targets for age-related goat ovarian diseases.

关键词： Goat Granulosa cells Ovarian aging Single-cell transcriptomic

来源：评论

学校读者我要写书评

暂无评论

A Novel Quantization and Model Compression Approach for Hardware Accelerators in Edge Computing

引用

computers, Materials & Continua 2024年第8期80卷 3021-3045页

作者： Fangzhou He Ke Ding DingjiangYan Jie Li Jiajun Wang Mingzhe Chen State Key Laboratory of Intelligent Vehicle Safety Technology Chongqing401133China Foresight Technology Institute Chongqing Changan Automobile Co.Ltd.Chongqing400023China School of Computer Science and Engineering Chongqing University of Science and TechnologyChongqing401331China

Massive computational complexity and memory requirement of artificial intelligence models impede their deploy-ability on edge computing devices of the Internet of Things(IoT).While Power-of-Two(PoT)quantization is pro-posed to improve the efficiency for edge inference of Deep Neural Networks(DNNs),existing PoT schemes require a huge amount of bit-wise manipulation and have large memory overhead,and their efficiency is bounded by the bottleneck of computation latency and memory *** tackle this challenge,we present an efficient inference approach on the basis of PoT quantization and model *** integer-only scalar PoT quantization(IOS-PoT)is designed jointly with a distribution loss regularizer,wherein the regularizer minimizes quantization errors and training ***,two-stage model compression is developed to effectively reduce memory requirement,and alleviate bandwidth usage in communications of networked heterogenous learning *** product look-up table(P-LUT)inference scheme is leveraged to replace bit-shifting with only indexing and addition operations for achieving low-latency computation and implementing efficient edge ***,comprehensive experiments on Residual Networks(ResNets)and efficient architectures with Canadian Institute for Advanced Research(CIFAR),ImageNet,and Real-world Affective Faces Database(RAF-DB)datasets,indicate that our approach achieves 2×∼10×improvement in the reduction of both weight size and computation cost in comparison to state-of-the-art methods.A P-LUT accelerator prototype is implemented on the Xilinx KV260 Field Programmable Gate Array(FPGA)platform for accelerating convolution operations,with performance results showing that P-LUT reduces memory footprint by 1.45×,achieves more than 3×power efficiency and 2×resource efficiency,compared to the conventional bit-shifting scheme.

关键词： Edge computing model compression hardware accelerator power-of-two quantization

来源：评论

学校读者我要写书评

暂无评论

Rough set model of incomplete interval rough number decision systems

引用

Journal of Intelligent and Fuzzy Systems 2024年第4期46卷 8829-8843页

作者： Zhou, Yinwei Hu, Jun Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and Telecommunications Chongqing China School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing China

The rough set model has been extended to interval rough number decision systems, but the existing studies do not consider interval rough number decision systems with missing values. To this end, a rough set model of incomplete interval rough number decision systems (IIRNDSs) is proposed, and its uncertainty measures are investigated. Firstly, the similarity of two incomplete interval rough numbers (IIRNs) are defined by calculating their optimistic and pessimistic distances of the lower and upper approximation intervals of IIRNs. Then, the rough sets in IIRNDSs are constructed by the induced similarity relation. Next, four uncertainty measures, including approximation accuracy, approximation roughness, conditional entropy, and decision rough entropy are given, which exhibit a monotonic variation with changes in the size of attribute sets, α, and θ. Finally, the experimental results demonstrate the proposed rough set model of IIRNDSs is feasible and effective. © 2024 - IOS Press. All rights reserved.

关键词： Rough set theory

来源：评论

学校读者我要写书评

暂无评论

Energy dissipation mechanism and ballistic characteristic optimization in foam sandwich panels against spherical projectile impact

引用

Defence technology（防务技术） 2024年第5期35卷 108-122页

作者： Jianqiang Deng Tao Liu Liming Chen Xin Pan Jingzhe Wang Shaowei Zhu Weiguo Li College of Aerospace Engineering Chongqing UniversityChongqing 400030China State Key Laboratory of Coal Mine Disaster Dynamics and Control Chongqing UniversityChongqing 400030China Chongqing Key Laboratory of Heterogeneous Material Mechanics Chongqing UniversityChongqing 400030China State Key Laboratory of Explosion Science and Technology Beijing Institute of TechnologyBeijing 100081China

This study systematically examines the energy dissipation mechanisms and ballistic characteristics of foam sandwich panels(FSP)under high-velocity impact using the explicit non-linear finite element *** on the geometric topology of the FSP system,three FSP configurations with the same areal density are derived,namely multi-layer,gradient core and asymmetric face sheet,and three key structural parameters are identified:core thickness(t_(c)),face sheet thickness(t_(f))and overlap face/core number(n_(o)).The ballistic performance of the FSP system is comprehensively evaluated in terms of the ballistic limit velocity(BLV),deformation modes,energy dissipation mechanism,and specific penetration energy(SPE).The results show that the FSP system exhibits a significant configuration dependence,whose ballistic performance ranking is:asymmetric face sheet>gradient core>*** mass distribution of the top and bottom face sheets plays a critical role in the ballistic resistance of the FSP *** BLV and SPE increase with tf,while the raising tcor noleads to an increase in BLV but a decrease in ***,a face-core synchronous enhancement mechanism is discovered by the energy dissipation analysis,based on which the ballistic optimization procedure is also conducted and a design chart is *** study shed light on the anti-penetration mechanism of the FSP system and might provide a theoretical basis for its engineering application.

关键词： Sandwich panel Numerical simulation Ballistic resistance Specific penetration energy Energy analysis

来源：评论

学校读者我要写书评

暂无评论

OsNAC120 balances plant growth and drought tolerance by integrating GA and ABA signaling in rice

引用

Plant Communications 2024年第3期5卷 197-215页

作者： Zizhao Xie Liang Jin Ying Sun Chenghang Zhan Siqi Tang Tian Qin Nian Liu Junli Huang Key Laboratory of Biorheological Science and Technology of Ministry of Education Bioengineering College of Chongqing UniversityChongqingChina

The crosstalk between gibberellin(GA)and abscisic acid(ABA)signaling is crucial for balancing plant growth and adaption to environmental ***,the molecular mechanism of their mutual antagonism still remains to be fully *** this study,we found that knockout of the rice NAC(NAM,ATAF1/2,CUC2)tran-scription factor gene OsNAC120 inhibits plant growth but enhances drought tolerance,whereas OsNAC120 overexpression produces the opposite *** GA can rescue the semi-dwarf phenotype of osnac120 mutants,and further study showed that OsNAC120 promotes GA biosynthesis by transcriptionally activating the GA biosynthetic genes OsGA20ox1 and *** DELLA protein SLENDER RICE1(SLR1)interacts with OsNAC120 and impedes its transactivation ability,and GA treatment can remove the inhi-bition of transactivation activity caused by *** the other hand,OsNAC120 negatively regulates rice drought tolerance by repressing ABA-induced stomatal *** investigation revealed that OsNAC120 inhibits ABA biosynthesis via transcriptional repression of the ABA biosynthetic genes OsNCED3 and *** OSMOTIC STRESS/ABA-ACTIVATED PROTEIN KINASE 9(OsSAPK9)physically interacts with OsNAC120 and mediates its phosphorylation,which results in OsNAC120 *** treatment ac-celerates OsNAC120 degradation and reduces its transactivation ***,our findings provide evidence that OsNAC120 plays critical roles in balancing GA-mediated growth and ABA-induced drought tolerance in *** research will help us to understand the mechanisms underlying the trade-off between plant growth and stress tolerance and to engineer stress-resistant,high-yielding crops.

关键词： abscisic acid ABA drought stress gibberellin GA OsNAC120 OsSAPK9 rice Oryza sativa L. SLR1

来源：评论

学校读者我要写书评

暂无评论

Mode coupling with Fabry-Perot modes in photonic crystal slabs

引用

Chinese Physics B 2024年第8期33卷 90-94页

作者：秦恳胡鹏刘杰向红韩德专 Department of Physics and Chongqing Key Laboratory for Strongly Coupled Physics Chongqing UniversityChongqing 401331China School of Science Chongqing Key Laboratory of New Energy Storage Materials and DevicesChongqing University of TechnologyChongqing 400054China

Fabry–Perot(FP)modes are a class of fundamental resonances in photonic crystal(PhC)*** to their low quality factors,FP modes are frequently considered as background fields with their resonance nature being ***,FP modes can play important roles in some phenomena,as exemplified by their coupling with guided resonance(GR)modes to achieve bound states in the continuum(BIC).Here,we further demonstrate the genuine resonance mode capability of FP modes PhC ***,we utilize temporal coupled-mode theory to obtain the transmittance of a PhC slab based on the FP ***,we construct exceptional points(EPs)in both momentum and parameter spaces through the coupling of FP and GR ***,we identify a Fermi arc connecting two EPs and discuss the far-field polarization *** work elucidates that the widespread FPs in PhC slabs can serve as genuine resonant modes,facilitating the realization of desired functionalities through mode coupling.

关键词： Fabry–Perot mode photonic crystal slab mode coupling exceptional point

来源：评论

学校读者我要写书评

暂无评论

AsyCo: an asymmetric dual-task co-training model for partial-label learning

引用

science China(Information sciences) 2025年第5期68卷 332-347页

作者： Beibei LI Yiyuan ZHENG Beihong JIN Tao XIANG Haobo WANG Lei FENG College of Computer Science Chongqing University State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences School of Software Technology Zhejiang University School of Computer Science and Engineering Nanyang Technological University

Partial-label learning(PLL) is a typical problem of weakly supervised learning, where each training instance is annotated with a set of candidate labels. Self-training PLL models achieve state-of-the-art performance but suffer from error accumulation problems caused by mistakenly disambiguated instances. Although co-training can alleviate this issue by training two networks simultaneously and allowing them to interact with each other, most existing co-training methods train two structurally identical networks with the same task, i.e., are symmetric, rendering it insufficient for them to correct each other due to their similar limitations. Therefore, in this paper, we propose an asymmetric dual-task co-training PLL model called AsyCo,which forces its two networks, i.e., a disambiguation network and an auxiliary network, to learn from different views explicitly by optimizing distinct tasks. Specifically, the disambiguation network is trained with a self-training PLL task to learn label confidence, while the auxiliary network is trained in a supervised learning paradigm to learn from the noisy pairwise similarity labels that are constructed according to the learned label confidence. Finally, the error accumulation problem is mitigated via information distillation and confidence refinement. Extensive experiments on both uniform and instance-dependent partially labeled datasets demonstrate the effectiveness of AsyCo.

关键词： machine learning weakly supervised learning partial-label learning co-training models candidate label sets

来源：评论

学校读者我要写书评

暂无评论

Re-quantization based binary graph neural networks

引用

science China(Information sciences) 2024年第7期67卷 160-171页

作者： Kai-Lang YAO Wu-Jun LI National Key Laboratory for Novel Software Technology Department of Computer Science and TechnologyNanjing University

Binary neural networks have become a promising research topic due to their advantages of fast inference speed and low energy consumption. However, most existing studies focus on binary convolutional neural networks, while less attention has been paid to binary graph neural networks. A common drawback of existing studies on binary graph neural networks is that they still include lots of inefficient full-precision operations in multiplying three matrices and are therefore not efficient enough. In this paper, we propose a novel method, called re-quantization-based binary graph neural networks(RQBGN), for binarizing graph neural networks. Specifically, re-quantization, a necessary procedure contributing to the further reduction of superfluous inefficient full-precision operations, quantizes the results of multiplication between any two matrices during the process of multiplying three matrices. To address the challenges introduced by requantization, in RQBGN we first study the impact of different computation orders to find an effective one and then introduce a mixture of experts to increase the model capacity. Experiments on five benchmark datasets show that performing re-quantization in different computation orders significantly impacts the performance of binary graph neural network models, and RQBGN can outperform other baselines to achieve state-of-the-art performance.

关键词： graph neural networks binary neural networks mixture of experts computation-efficient 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：