检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Ding, Lichao Zhao, Jing Lu, Kai Hao, Zenghao Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (纸本)9781665410205

Knowledge graphs (KGs) provide a structured representation of the real world through entity-relation triples. However, current KGs are often incomplete, typically containing only a small fraction of all possible facts. This involves inferring missing content from existing information, a task known as link prediction. Existing methods in the field of link prediction struggle with controlling the dimensionality of embedding vectors or suffer from overly complex models. In order to tackle these challenges, we introduce a method in this paper, named Low-Dimensional Embedding Method for Link Prediction Combining Self-Attention and Enhanced-TuckER (LESaET). LESaET leverages both self-attention mechanisms and tensor factorization to learn expressive contextual-enhanced representations of KGs. Specifically, LESaET employs the multi-head self-attention mechanism of Transformer as an encoder to capture the mutual information between entities and relationships, and utilizes Enhanced-TuckER as a decoder, ultimately achieving expressive low-dimensional embeddings for link prediction tasks. LESaET demonstrates competitive performance compared to advanced methods on standard datasets. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Shrinkage Estimation for Location and Scale Parameters of Logistic Distribution Under Record Values

引用

Annals of data Science 2024年第4期11卷 1209-1224页

作者： Gupta, Shubham Vishwakarma, Gajendra K. Elsawah, A.M. Department of Mathematics & amp Computing Indian Institute of Technology Dhanbad826004 India Department of Statistics and Data Science Faculty of Science and Technology Beijing Normal University-Hong Kong Baptist University United International College Zhuhai519087 China Guangdong Provincial Key Laboratory of Interdisciplinary Research and Application for Data Science BNU-HKBU United International College Zhuhai519087 China Department of Mathematics Faculty of Science Zagazig University Zagazig44519 Egypt

Logistic distribution (LogDis) is frequently used in many different applications, such as logistic regression, logit models, classification, neural networks, physical sciences, sports modeling, finance and health and disease studies. For instance, the distribution function of the LogDis has the same functional form as the derivative of the Fermi function that can be used to set the relative weight of various electron energies in their contributions to electron transport. The LogDis has wider tails than a normal distribution (NorDis), so it is more consistent with the underlying data and provides better insight into the likelihood of extreme events. For this reason the United States Chess Federation has switched its formula for calculating chess ratings from the NorDis to the LogDis. The outcomes of many real-life experiments are sequences of record-breaking data sets, where only observations that exceed (or only those that fall below) the current extreme value are recorded. The practice demonstrated that the widely used estimators of the scale and location parameters of logistic record values, such as the best linear unbiased estimators (BLUEs), have some defects. This paper investigates the shrinkage estimators of the location and scale parameters for logistic record values using prior information about their BLUEs. Theoretical and computational justifications for the accuracy and precision of the proposed shrinkage estimators are investigated via their bias and mean square error (MSE), which provide sufficient conditions for improving the proposed shrinkage estimators to get unbiased estimators with minimum MSE. The performance of the proposed shrinkage estimators is compared with the performances of the BLUEs. The results demonstrate that the resulting shrinkage estimators are shown to be remarkably efficient. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Multilingual Knowledge Graph Completion via Multimodal Decouple and Relation-based Ensemble Inference 29

Multilingual Knowledge Graph Completion via Multimodal Decou...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Liu, Xiaojing Jiang, Xuesong Yi, Fengge Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China

ISBN: (纸本)9798350330717

The objective of Multimodal Knowledge Graph Completion (MKGC) is to forecast absent entities within a knowledge graph by leveraging additional textual and visual modalities. Existing studies commonly utilize a singular relationship embedding to depict all modalities within an entity pair, thus connecting several relationships derived from diverse modalities. However, this coupling may introduce interference from conflicting information between modalities, as the relationships between modalities for a given entity pair can be contradictory. Moreover, existing Ensemble Inference methods fail to dynamically adjust modal weights based on their differences and importance, despite the varying contributions of different modalities. In this paper, we propose the Multimodal Decouple and Relation-based Ensemble inference (MDRE) model. For each modality, we construct corresponding relationship embeddings and build separate triple representations to avoid interferences among modalities. During the training phase, we employ confidence-constrained training with temperature scaling to alleviate conflicting information in textual and visual modalities. For inference, we utilize the Relation-based Ensemble Inference method to adjust modal weights at the relationship level, thus achieving improved prediction results. Experimental results on two datasets demonstrate that MDRE outperforms existing single-modal and multimodal knowledge graph completion methods in terms of performance. © 2023 IEEE.

关键词： knowledge graph knowledge graph completion multimodal fusion

来源：评论

学校读者我要写书评

暂无评论

Cascade Detector Based on Multi-scale Features for Small Objects in Various Backgrounds of Remote Sensing 2nd

Cascade Detector Based on Multi-scale Features for Small Obj...

引用

2nd International Conference on Image, Vision and Intelligent Systems, ICIVIS 2022

作者： Li, Yan Han, Shi-Yuan Xu, Tao Yang, Xiao-hui Lu, Qiu Shen, Yuan University of Jinan Jinan250022 China China High-Resolution Earth Observation System Shandong Center of Data and Application University of Jinan Jinan250022 China Shandong Provincial Key Laboratory of Network-Based Intelligent Computing University of Jinan Jinan250022 China

ISBN: (纸本)9789819909223

Different from natural images, remote sensing images in complex backgrounds have the challenges of small object feature extraction with small size, few available features, and high localization accuracy requirements. Consequently, it is difficult to detect these small objects with mainstream object detection methods. To enhance the retention of small object feature details during feature extraction and characteristics enhancement, this paper improves the Cascade R-CNN algorithm to solve the above problems of small object detection. Res2Net was used to enhance feature representation and feature fusion to extract features with fine-grained and rich semantic information. PAFPN was used for learning high-resolution features with large perceptual fields to perceive contextual information from the area around the object for inference. Cascade R-CNN was used as a high-quality detector by continuously increasing the threshold of IOU. Experiments show that the detection performance of the method proposed in this paper is 4.3% higher than that of the current mainstream deep learning methods, which is significantly better than other mainstream detection methods. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Probing Globular Cluster with MeerKAT and FAST: A Pulsar Polarization Census

arXiv

引用

arXiv 2025年

作者： Zhang, Lei Abbate, Federico Li, Di Possenti, Andrea Bailes, Matthew Ridolfi, Alessandro Freire, Paulo C.C. Ransom, Scott M. Zhang, Yong-Kun Guo, Meng Ni, Meng-Meng Hu, Jia-Le Feng, Yi Wang, Pei Zhang, Jie Zhi, Qi-Jun National Astronomical Observatories Chinese Academy of Sciences Beijing100101 China Centre for Astrophysics and Supercomputing Swinburne University of Technology VIC3122 Australia INAF Osservatorio Astronomico di Cagliari Via della Scienza 5 SelargiusI-09047 Italy Max-Planck-Institut für Radioastronomie Auf dem Hügel 69 BonnD-53121 Germany Department of Astronomy Tsinghua University Beijing100190 China Swinburne University of Technology VIC3122 Australia Faculty of Physics University of Bielefeld Bielefeld33501 Germany National Radio Astronomy Observatory 520 Edgemont Road Charlottesville22903 United States National Supercomputing Center in Jinan Qilu University of Technology Jinan250103 China Jinan Institute of Supercomputing Technology 28666 East Jingshi Road Jinan250103 China Research Center for Intelligent Computing Platforms Zhejiang Laboratory Hangzhou311100 China Institute for Astronomy School of Physics Zhejiang University Hangzhou310027 China College of Physics and Electronic Engineering Qilu Normal University Jinan250200 China Guizhou Provincial Key Laboratory of Radio Astronomy and Data Processing Guizhou Normal University Guiyang550001 China

Only one globular cluster (GC), 47 Tuc, has been found to containintracluster medium, with an electron density 100 times higher than that of theISM in its vicinity. The characteristics of this intracluster medium areclosely related to GC evolution and the compact objects within. However,significant knowledge gaps remain regarding the ionized gas content of GCs,particularly in Galactic halo clusters. We carried out a polarization census ofGC pulsars using MeerKAT and FAST. This first combined effort of observationsfrom these two major radio telescopes resulted in high signal-to-noise ratio,full polarization pulse profiles for 43 pulsars in 8 GCs, doubling the numberof rotation measures (RMs) known in these clusters. The accuracy of dispersionmeasures (DMs) was improved by a factor of 8 compared to previous *** intracluster medium was found, and at least two halo GCs showed morestringent upper limits on electron density than that detected in 47 Tuc. Thesurprising barrenness of GCs suggests effective gas removal mechanisms, such asstrong winds from millisecond pulsars and/or ionizing radiation from post-AGBstars and young white dwarfs. Copyright © 2025, The Authors. All rights reserved.

关键词： White dwarfs

来源：评论

学校读者我要写书评

暂无评论

Joint Sparsification and Quantization for Wireless Federated Learning under Communication Constraints 24

Joint Sparsification and Quantization for Wireless Federated...

引用

24th IEEE International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2023

作者： Su, Junshen Wang, Xijun Chen, Xiang Cheng, Ray-Guang Sun Yat-Sen University School of Electronics and Information Technology Guangzhou China The Chinese University of HongKong Guangdong Provincial Key Laboratory of Big Data Computing Shenzhen China National Taiwan University of Science and Technology Department of Electronic and Computer Engineering Taipei Taiwan

ISBN: (纸本)9781665496261

Communication efficiency is one of the key bottlenecks in Federated Learning (FL). Compression techniques, such as sparsification and quantization, are used to reduce communication overhead. However, joint designs of these techniques under communication constraints are not well-explored. This paper investigates the joint uplink compression problem in communication-constrained FL systems. We propose a Block-TopK sparsification scheme to reduce the proportion of bits used for locating entries of a sparsified vector. Considering the communication constraints, an optimization formulation is proposed to minimize the compression error. By solving the optimization problem, our joint compression method provides a better trade-off between sparsity budget and bit width. Numerical results demonstrate that our approach achieves 99.96% of baseline accuracy with only 1.56% of the baseline communication overhead when training ResNet-18 on CIFAR-10. © 2023 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

IDENTIFYMIX: AN EFFICIENT TWO-STAGE LEARNING APPROACH TO COMBATING LABEL NOISE

Journal of Applied and Numerical Optimization

引用

Journal of Applied and Numerical Optimization 2023年第2期5卷 237-253页

作者： Tong, Kai Ke, Xiao Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou University Fuzhou350116 China Key Laboratory of Spatial Data Mining & Information Sharing Ministry of Education Fuzhou350003 China

Deep neural networks require correct label annotation during supervised learning. It is inevitable, however, that some labels are noisy during the labeling process. A deep neural network retains incorrect labels during training, resulting in a degradation of performance. Therefore, it is essential to identify samples with potentially correct labels. In state-of-the-art methods, small-loss samples are chosen for subsequent training through a sample selection strategy. Howerver, it typically ignores the imbalance in noise ratios between mini-batches when performing sample selection within each minibatch. Further, numerous valuable samples with high losses are discarded, which adversely affects the generalization performance of the model, particularly under conditions of high noise ratios. To this end, this paper proposes IdentifyMix, an effective two-stage learning approach for noisy robust learning that combines an unique sample selection strategy and the semi-supervised learning technique. By observing how the dynamics of network training are changing, AUM (Area Under the Margin) provides a criterion that is applied in this research to identify mislabeled data. Moreover, by combining semi-supervised learning with contrastive learning and data augmentation, it is possible to extract more useful information from mislabeled samples. Experiments on several synthetic and real-world noise benchmarks demonstrate the effectiveness of IdentifyMix compared with state-of-the-art methods. © 2023 Journal of Applied and Numerical Optimization.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Multi-task Network for Intelligent Management of Garbage Deposit Points

Deep Learning-based Multi-task Network for Intelligent Manag...

引用

IEEE International Symposium on Information (IT) in Medicine and Education, ITME

作者： Yezhen Wang Haobin Zheng Changjiang Mao Jing Zhang Xiao Ke College of Computer and Data Science Fuzhou University Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing Key Laboratory of Spatial Data Mining & Information Sharing Ministry of Education Fuzhou

ISBN: (纸本)9781728194202

With the economic and social development and the substantial improvement of material conditions, the generation of domestic waste has grown rapidly and has become a constraint factor for the development of new urbanization. In the past few years, research on the domestic waste industry has been limited to intelligent waste sorting, neglecting the role of intelligent management of waste storage sites. To relieve it, We propose a deep learning-based multi-task network for intelligent management of garbage deposit points, which combines algorithms such as YoloV5,Deepsort, Insightface, and Openpose to achieve waste bin detection, waste bin status recognition and analysis, face recognition, action recognition, and multiple object tracking based on real-time surveillance video. Besides, we propose a new dataset named Waste Bin Status, which provides a meaningful addition to the existing field of waste bin identification. Experiments on WBS dataset validate that our method is superior to other methods for garbage point status identification. Moreover, our network is trained to work with different scenarios of garbage deposits, demonstrating state-of-the-art performance in real-world tests.

关键词： Industries Face recognition Surveillance Education Streaming media Multitasking Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Scale-Adaptive Feature Aggregation for Efficient Space-Time Video Super-Resolution

arXiv

引用

arXiv 2023年

作者： Huang, Zhewei Huang, Ailin Hu, Xiaotao Hu, Chen Xu, Jun Zhou, Shuchang Megvii Technology China Nankai University China Guangdong Provincial Key Laboratory of Big Data Computing CUHK Hong Kong

The Space-Time Video Super-Resolution (STVSR) task aims to enhance the visual quality of videos, by simultaneously performing video frame interpolation (VFI) and video super-resolution (VSR). However, facing the challenge of the additional temporal dimension and scale inconsistency, most existing STVSR methods are complex and inflexible in dynamically modeling different motion amplitudes. In this work, we find that choosing an appropriate processing scale achieves remarkable benefits in flow-based feature propagation. We propose a novel Scale-Adaptive Feature Aggregation (SAFA) network that adaptively selects sub-networks with different processing scales for individual samples. Experiments on four public STVSR benchmarks demonstrate that SAFA achieves state-of-the-art performance. Our SAFA network outperforms recent state-of-the-art methods such as TMNet [83] and VideoINR [10] by an average improvement of over 0.5dB on PSNR, while requiring less than half the number of parameters and only 1/3 computational costs. Copyright © 2023, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

A Two-Stage Graph Computation Model with Communication Equilibrium 15th

A Two-Stage Graph Computation Model with Communication Equil...

引用

15th CCF Conference on Computer Supported Cooperative Work and Social computing, Chinese CSCW 2020

作者： Dong, Yanmei Chen, Rongwang Guo, Kun College of Mathematics and Computer Science Fuzhou University Fuzhou350108 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou China Key Laboratory of Spatial Data Mining and Information Sharing Ministry of Education Fuzhou350108 China College of Mathematics and Computer Science Wuyi University Wuyishan Fujian354300 China Digital Fujian Tourism Big Data Institute Wuyishan Fujian354300 China

ISBN: (纸本)9789811625398

Distributed graph computing aims at performing in-depth analysis on large networks in a parallel manner. Iterative communication computation is an important model to perform graph analysis. Moreover, high-efficiency iterative communication computation is necessary for assuring the quality of graph partitioning. Many strategies to improve graph computing are usually based on the hypothesis of single communication iteration which focuses on the optimization of load balance in a single graph partitioning and the improvement of parallel granularity or communication manners. However, a graph in the real-world usually requires complex communication iterations to achieve good analysis results, which often have the problems of data and communication tilting and low analysis efficiency. In this paper, we propose a two-stage graph computing model with communication equilibrium (TSMCE). The model employs a communication-equilibrated graph partitioning strategy (CEGP) for load balancing and a two-stage graph computing mode (TS) to reduce the crossing-partition communication. With the change of graph density, various factors such as load balancing, communication balancing, cross-partition transmission traffic, communication delay, and convergence speed can always maintain an efficient balance. The experiments conducted on the real-world datasets show that the communication-equilibrated graph partitioning strategy can divide a graph with high quality compared with Hash and Metis. Besides, the overall performance of our two-stage graph computing model with communication equilibrium is higher than that of the BSP model. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Efficiency

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：