检索结果-内蒙古大学图书馆

International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)

作者： He Tong Qing-Zhe Cui Wei Xu Ding-Ge Jin Meng-Ying Li Ting-Ting Xu Li-Xiang Xu Yuan-Yan Tang Department of Basic Chinese people's Liberation Army Aviation School Beijing China School of Artificial Intelligence and Big Data Hefei University Hefei China School of Public Afairs University of Science and Technology of China Hefei China Economics Teaching and Research Office Party School of Lu'an Municipal Committee of the Communist Party of China Zhuhai UM Science and Technology Research Institute FST University of Macau Macau

In recent years, social enterprises have gradually emerged as a major force in community governance. In order for social enterprises to better participate in community governance, this paper examines the trust mechanism between social enterprises and community governance, and offers suggestions for social enterprises in community governance. Firstly, this paper takes social trust as the object of study, divides it into ordinary trust and spe-cial trust, community governance effect as the dependent variable, selects intermediate variables to construct a non-linear regression model, and combines the correlation coefficient analysis to derive the mechanism of building trust relationship between social enterprises and community governance. Finally, there are sound suggestions for community governance aspects.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Semi-supervised Bilingual Lexicon Induction Method for Distant Language Pairs Based on Bidirectional Adversarial Model

A Semi-supervised Bilingual Lexicon Induction Method for Dis...

引用

IEEE International Conference on big Knowledge (ICBK)

作者： Wenwu Zhi Yuhong Zhang Key Laboratory of Knowledge Engineering with Big Data (Hefei University of Technology) Ministry of Education School of Computer Science and Information Engineering Hefei University of Technology Hefei China

ISBN: (纸本)9781665438599

Bilingual lexicon induction (BLI) can transfer knowledgefrom well- to under- resourced language, and has been widelyapplied to various NLP tasks. Recent work on BLI is projection-based that learns a mapping to connect source and target embedding spaces, with the isomorphism assumption. Unfortunately, the isomorphism assumption doesn't hold gener-ally, especially in typologically distant language pairs. Moreover, without supervised signals guiding, the training will further com-plicates BLI, making the performance of unsupervised methods unsatisfactory. To broke the restrict of isomorphism, we propose a semi-supervised method for distant BLI tasks, named A Semi-supervised Bilingual Lexicon Induction method in Latent Space based on Bidirectional Adversarial Model. First, two latent spaces are learned by two autoencoders for source and target domain independently to weaken the constraint of isomorphism in the embedding spaces. Then we add a few pairs of dictionary to learn the initial mapping to connect the Latent Space. Last, based on initial mapping, Cycle-Consistency is combined with Distance constraint constraint to maintain the geometry structure of both embedding spaces stable in the learning of bi-direction mapping based on adversarial model. By conducting extensive experiments, our method gets state-of-the-art results on most language pairs, especially with significant improvements on distant language pairs.

关键词： Training Geometry Dictionaries Conferences Bidirectional control Task analysis

来源：评论

学校读者我要写书评

暂无评论

A reservation system with an efficient matching-and-scheduling mechanism for private parking-sharing programs 25

A reservation system with an efficient matching-and-scheduli...

引用

25th World Multi-Conference on Systemics, Cybernetics and Informatics, WMSCI 2021

作者： Yan, Pengyu Cai, Xiaoqiang Chu, Feng Ni, Debing School of Management and Economics University of Electronic Science and Technology of China Chengdu China Shenzhen Key Laboratory of IoT Intelligent Systems and Wireless Network Technology The Chinese University of Hong Kong Shenzhen Guangdong China Shenzhen Research Institute of Big Data Guangdong China Laboratoire IBISC Univ Evry Universitie Paris-Saclay Evry91025 France

ISBN: (纸本)9781713835196

We design a smart parking-sharing reservation system composed of three modules: Pre-processing, matching, and pricing. With the announced supply and demand information, the pre-processing module identifies a set of feasible parking slots for each driver concerning the compatibility of slot supply for the driver's demand. The matching module generates a system-wide optimal matching solution and further schedules the driver's parking time by using the flexibility of driver travel plans. The pricing module adopts a novel VCG-based pricing to determine the parking fees of drivers under an incomplete information setting in which each driver (player) cannot obtain the knowledge of the other competitors (players) who will compete against her. We find that the designed reservation system can not only elicit drivers' truthful demand reports but also achieve the optimal performance of the system. In this short paper we briefly describe our system and the main solution approaches we use. © WMSCI *** right reserved.

关键词： Costs

来源：评论

学校读者我要写书评

暂无评论

Learning Unified Embeddings for Recommendation via Meta-path Semantics 21

Learning Unified Embeddings for Recommendation via Meta-path...

引用

29th ACM International Conference on Multimedia, MM 2021

作者： Hao, Qianxiu Xu, Qianqian Yang, Zhiyong Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China Artificial Intelligence Research Center Peng Cheng Laboratory Shenzhen China

ISBN: (纸本)9781450386517

Heterogeneous information networks (HINs) have become a popular tool to capture complicated user-item relationships in recommendation problems in recent years. As a typical instantiation of HINs, meta-path is introduced in search of higher-level representations of user-item interactions. Though remarkable success has been achieved along this direction, existing meta-path-based recommendation methods face at least one of the following issues: 1) existing methods merely adopt simple meta-path fusion rules, which might be insufficient to exclude inconsistent information of different meta-paths that may hurt model performance;2) the representative power is limited by shallow/stage-wise formulations. To solve these issues, we propose an end-to-end and unified embedding-based recommendation framework with graph-based learning. To address 1), we propose a flexible fusion module to integrate meta-path-based similarities into relative similarities between users and items. To address 2), we take advantage of the powerful representative ability of deep neural networks to learn more complicated and flexible latent embeddings. Finally, empirical studies on real-world datasets demonstrate the effectiveness of our proposed method. © 2021 ACM.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

High-spatial-resolution light field 3D perception based on unidirectional object motion

引用

Optics Letters 2025年第11期50卷 3672-3675页

作者： Wang, Dongyang Zhang, Zhijun Zhai, Jianpang Kang, Yan Wu, Qingyang College of Applied Sciences Shenzhen University Shenzhen518060 China Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging National-Regional Key Technology Engineering Laboratory for Medical Ultrasound School of Biomedical Engineering Shenzhen University Medical School Shenzhen518060 China College of Big Data and Internet Shenzhen Technology University Shenzhen518060 China Technology Co. Ltd. Anbo Technology Park 2 2 Baolong 4th Road Shenzhen518060 China College of New Materials and New Energies Shenzhen Technology University Shenzhen518060 China College of Health Science and Environmental Engineering Shenzhen Technology University Shenzhen518060 China

Light field cameras can capture comprehensive light information within a scene. Their core architecture incorporates a micro-lens array (MLA) positioned in front of the imaging sensor, mimicking the compound eye structure of insects. By processing the acquired data, these cameras enable the reconstruction of 3D spatial information. Despite their numerous advantages, light field cameras suffer from a critical drawback: low spatial resolution. To address this limitation, this study proposes a high-spatial-resolution light field imaging approach based on unidirectional object motion (UOMLF). A non-focused light field camera equipped with a hexagonally arranged MLA was developed as the foundation for a unidirectional object motion platform. Additionally, a 3D reconstruction algorithm tailored to high-resolution light field imaging was designed to complement this system. Experimental evaluations were conducted using the USAF resolution test chart and detector chip leads. Results demonstrate that the proposed method significantly enhances xy-plane resolution (approximately four times improvement) while maintaining z-axis resolution. This high-spatial-resolution light field technique based on unidirectional object motion offers broad potential for applications in both industrial and scientific fields. © 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： Digital cameras

来源：评论

学校读者我要写书评

暂无评论

Training time minimization for federated edge learning with optimized gradient quantization and bandwidth allocation

引用

Frontiers of Information technology & Electronic Engineering 2022年第8期23卷 1247-1263页

作者： Peixi LIU Jiamo JIANG Guangxu ZHU Lei CHENG Wei JIANG Wu LUO Ying DU Zhiqin WANG State Key Laboratory of Advanced Optical Communication Systems and Networks Department of ElectronicsPeking UniversityBeijing 100871China China Academy of Information and Communications Technology Beijing 100191China Shenzhen Research Institute of Big Data Shenzhen 518172China College of Information Science and Electronic Engineering Zhejiang UniversityHangzhou 310027China Zhejiang Provincial Key Laboratory of Information Processing Communication and NetworkingHangzhou 310027China

Training a machine learning model with federated edge learning(FEEL)is typically time consuming due to the constrained computation power of edge devices and the limited wireless resources in edge *** this study,the training time minimization problem is investigated in a quantized FEEL system,where heterogeneous edge devices send quantized gradients to the edge server via orthogonal *** particular,a stochastic quantization scheme is adopted for compression of uploaded gradients,which can reduce the burden of per-round communication but may come at the cost of increasing the number of communication *** training time is modeled by taking into account the communication time,computation time,and the number of communication *** on the proposed training time model,the intrinsic trade-off between the number of communication rounds and per-round latency is ***,we analyze the convergence behavior of the quantized FEEL in terms of the optimality ***,a joint data-and-model-driven fitting method is proposed to obtain the exact optimality gap,based on which the closed-form expressions for the number of communication rounds and the total training time are *** by the total bandwidth,the training time minimization problem is formulated as a joint quantization level and bandwidth allocation optimization *** this end,an algorithm based on alternating optimization is proposed,which alternatively solves the subproblem of quantization optimization through successive convex approximation and the subproblem of bandwidth allocation by bisection *** different learning tasks and models,the validation of our analysis and the near-optimal performance of the proposed optimization algorithm are demonstrated by the simulation results.

关键词： Federated edge learning Quantization optimization Bandwith allocation Training time minimization

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning-Based Paradigm for Retrieving Ocean Wave Spectra from Spaceborne SAR

A Deep Learning-Based Paradigm for Retrieving Ocean Wave Spe...

引用

SAR in big data Era: Models, Methods and Applications (bigSARdata)

作者： Ke Wu Xiao-Ming Li Chinese Acadamy of Sciences Key Laboratory of Digital Earth Science Aerospace Information Research Institute International Research Center of Big Data for Sustainable Development Goals University of Chinese Academy of Sciences Key Laboratory of Digital Earth of Hainan Province Hainan Aerospace Information Research Institute Hainan Aerospace Technology Innovation Center

The ocean wave spectrum is an essential parameter to fully describe the dynamic ocean waves. Although the spaceborne Synthetic Aperture Radar (SAR) is a potential instrument to measure the ocean wave spectrum, its retrieval is intricated by the complicated non-linear SAR-wave imaging mechanisms. This study introduced a deep learning (DL) method to address the ocean wave spectrum retrieval tasks from SAR images. The DL-based framework modifies the classical CNN architecture according to the multiple outputs of the target parameters and imposes a soft constraint based on the characteristics of the ocean wave spectrum. Trained and evaluated by the measurements of in-situ buoys deployed in the global ocean, the proposed model achieved root-mean-square errors of 0.53 m for significant wave heights and 1.24 s mean wave periods, demonstrating a generalized and robust performance. Our study represents a significant breakthrough in the longstanding challenge of SAR retrievals in ocean remote sensing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learnable Convolutional Attention Network for Knowledge Graph Completion

SSRN

引用

SSRN 2023年

作者： Shang, Bin Zhao, Yinliang Liu, Jun School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Xi’an710049 China Shaanxi Province Key Laboratory of Satellite and Terrestrial Network Tech. R&D Xi’an Jiaotong University Shaanxi Xi’an710049 China National Engineering Lab for Big Data Analytics Shaanxi Xi’an710049 China

Recently, graph convolutional networks (GCNs) and graph attention networks (GATs) have been widely used in knowledge graph completion (KGC), which aims to solve the incompleteness of knowledge graphs (KGs). However, GCNs based KGC models tend to stack redundant information when one entity have several noisy neighbors. GATs based KGC models may focus on certain neighbors and lead to weakening of structural information. Furthermore, relations in KGs have their specific semantics and should be considered when aggregating neighbor information (message passing). To address the above limitations, we propose a learnable convolutional attention network for knowledge graph completion named LCA-KGC. LCA-KGC introduces a knowledge graph convolutional attention network by using the convolution operation before the attention mechanism to ensure the structural information acquisition and avoid the redundant information stacking. Furthermore, to complete the autonomous switching of GNNs types and eliminate the necessity of pre-validating the local structure of KGs, LCA-KGC designs a learnable knowledge graph convolutional attention network by comprising three types of GNNs in one learnable formulation. Moreover, a learnable message function is proposed to emphasize relational semantics when aggregating neighbor information. Extensive experiments on standard KG datasets validate the effectiveness of the proposed innovations, and LCA-KGC achieves state-of-the-art (SOTA) performance compared to existing approaches (e.g., compared to SOTA approaches, LCA-KGC improves MRR from 0.360 to 0.372 on FB15k-237 dataset, and Hits@3 from 0.561 to 0.581 on YAGO3-10 dataset). © 2023, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Camera Calibration Method Based on Sine Cosine Algorithm

Camera Calibration Method Based on Sine Cosine Algorithm

引用

Symposium of Image, Signal Processing, and Artificial Vision (STSIVA)

作者： Zhihui Feng Quan Liang Zicheng Zhang Wei Ji School of Computer Science and Mathematics Fujian University of Technology Fuzhou China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fuzhou China

ISBN: (纸本)9781665426565

Aiming at the problems of traditional camera calibration method, such as sensitivity to the initial values of camera model parameters and unstable calibration results. This paper proposes a camera calibration method based on sine cosine algorithm. After obtaining a certain initial value by Zhang's camera calibration method, use the sine cosine algorithm (SCA) to form the initial population in the field near the initial value, and perform iterative optimization. The average error between the actual projection point and the calculated projection point is the accuracy criterion. Using the volatility and periodicity of the sine function and cosine function to search and iterate, so that the solution can be oscillating towards the global optimum and achieve the purpose of optimization. Experiments have proved that the adaptive parameters and randomness parameters in the algorithm better balance the exploration and development capabilities of the algorithm. The improved algorithm has fewer parameters, simple structure, easy implementation, and fast convergence speed. The experiment proves that the camera calibration accuracy is effectively improved.

关键词： Sensitivity Sociology Parallel processing Cameras Iterative algorithms Calibration Statistics

来源：评论

学校读者我要写书评

暂无评论

Large Language Model Supply Chain: A Research Agenda

引用

ACM Transactions on Software Engineering and Methodology 2025年第5期34卷

作者： Wang, Shenao Zhao, Yanjie Hou, Xinyi Wang, Haoyu Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology China

The rapid advancement of large language models (LLMs) has revolutionized artificial intelligence, introducing unprecedented capabilities in natural language processing and multimodal content generation. However, the increasing complexity and scale of these models have given rise to a multifaceted supply chain that presents unique challenges across infrastructure, foundation models, and downstream applications. This article provides the first comprehensive research agenda of the LLM supply chain, offering a structured approach to identify critical challenges and opportunities through the dual lenses of software engineering (SE) and security and privacy (S&P). We begin by establishing a clear definition of the LLM supply chain, encompassing its components and dependencies. We then analyze each layer of the supply chain, presenting a vision for robust and secure LLM development, reviewing the current state of practices and technologies, and identifying key challenges and research opportunities. This work aims to bridge the existing research gap in systematically understanding the multifaceted issues within the LLM supply chain, offering valuable insights to guide future efforts in this rapidly evolving domain. © 2025 Association for Computing Machinery. All rights reserved.

关键词： Large Language Models LLM Supply Chain

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：