检索结果-内蒙古大学图书馆

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

Experimental Study on Flow Characteristics in a Compound Open Channel with Flexible Vegetation

Experimental Study on Flow Characteristics in a Compound Ope...

引用

2021 International Conference on Agriculture Science and Water Resource, ASWR 2021

作者： Guo, Xiaoxiao Jing, Hefang Wang, Weihong Wu, Juntao Zhang, Qiaoling Research Institute of Numerical Computation and Engineering Applications North Minzu University Yinchuan China The Key Laboratory of Intelligent Information and Big Data Processing of Ningxia Province North Minzu University Yinchuan China School of Mathematics and Information Science North Minzu University Yinchuan China

In order to study the effect of flexible vegetation for the flow in open channels with flood plains, a series of experiments were carried out in a laboratory flume with a two-stage floodplain. Four cases, i.e., dense parallel arrangement, normal parallel arrangement, sparse parallel arrangement and no vegetation condition, were designed with fixed water depth and discharge. By using three dimensional (3D) laser Doppler velocimeter (LDV) and other instruments, under the condition of the four cases,3D flow velocities, water level and turbulence intensity were measured, The experimental results show that, compared with the non-vegetation situation, the arrangement of grasses on the floodplain will increase the water surface gradient, hydraulic gradient and turbulence intensity to a certain extent. © Published under licence by IOP Publishing Ltd.

关键词： Vegetation

来源：评论

学校读者我要写书评

暂无评论

A method for detecting floating objects on water based on edge computing

A method for detecting floating objects on water based on ed...

引用

2023 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting, BMSB 2023

作者： Li, He Yang, Shuaipeng Liu, Jinjiang Fang, Honglin Fu, Zhumu Zhang, Rui Jia, Huimei Lv, Lianmeng Henan Costar Group Co. Ltd Henan Nanyang473003 China Henan University of Science and Technology College of Information Engineering Henan Luoyang471000 China Nanyang Normal University Henan Engineering Research Center of Intelligent Processing for Big Data of Digital Image School of Computer Science and Technology Nanyang473061 China Beijing University of Posts and Telecommunication State Key Laboratory of Networking and Switching Technology Beijing100876 China Xi'an Hengpin Electronic Technology Co. Ltd Xi'an710100 China

ISBN: (纸本)9798350321524

With the development and application of computer vision, many target detection networks are applied to the detection of floating objects in rivers. For the detection problems such as small targets easily missed and misdetected in water surface floating object detection tasks and difficult to deploy models. An edge computing-oriented approach to river floater detection is proposed. First, a four-fold down-sampling feature layer is added to the YOLOv5 network which enhances more target detail features and improves the detection capability of small objects. Second, CA (Coordinate Attention) is added to the Backbone to suppress background noise interference, and different pooling is used to accommodate different hierarchical features. Then, a bilinear interpolation method is adopted for up-sampling to avoid the loss of small object features. Design a data enhancement algorithm for small targets based on Mosaic to increase the number of small objects and enrich the training background. Finally, for the edge computing architecture platform, the channel pruning algorithm is used to prune and compress the model structure to adapt to the computing capability of edge devices. The experimental results show that the method can effectively improve the detection capability of the network for floating objects on the water surface. The detection accuracy can reach 93.6%, and the detection speed can be maintained at 36 frames per second, which can achieve high-precision real-time detection of floating objects on the water surface. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Medical image super-resolution algorithm based on multi-scale feature aggregation

Medical image super-resolution algorithm based on multi-scal...

引用

Medical Artificial Intelligence (MedAI), IEEE International Conference on

作者： Xinyu Han Xun Gong School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education Chengdu China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu China Manufacturing Industry Chains Collaboration and InformationSupport Technology Key Laboratory of Sichuan Province Southwest Jiaotong University Chengdu China

ISBN: (数字)9798350377613

ISBN: (纸本)9798350377620

Ultrasound images are vital for medical diagnostics but often suffer from information loss and blurred details due to limitations in imaging systems and sensor technologies. Many researchers have proposed super-resolution algorithms to enhance medical images. But existing super-resolution methods struggle with the uneven distribution of noise and clarity. To address this, we propose a super-resolution algorithm for medical images based on multi-scale feature aggregation Leveraging the architecture of Unet as our primary framework, our method enhances output details through multi-scale hole convolutions. Taking into consideration the characteristics of ultrasonic images, we propose a frequency domain-based module to enhances edge information while effectively denoising the image. Furthermore, to improve the quality of the output images, we introduce an image processing module grounded in global information. The module ensures clarity while considering the overarching context, thereby preserving global consistency and enhancing output quality. We experiment on three datasets to demonstrate the effectiveness of our model. Additionally, significant improvements in medical image segmentation are observed, proving the practicability of our proposed approach.

关键词： Image segmentation Ultrasonic imaging Image edge detection Frequency-domain analysis Superresolution Noise reduction Noise Medical diagnosis Artificial intelligence Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Impact of DG on short circuit current detected by protection 5

Impact of DG on short circuit current detected by protection

引用

5th International Conference on Energy Engineering and Environmental Protection, EEEP 2020

作者： Gong, Jing School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture Beijing100044 China Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing100044 China National Virtual Simulation Experimental Center for Smart City Education Beijing100044 China

DG (distributed generation) access causes the change of current detected by the protection, and then affects the sensitivity of the original protection. In order to solve the problem, the influences of DG capacity, DG access location and short-circuit location on short circuit current are analysed in this paper. When the DG capacity and grid-connected position remain unchanged, the unit current method is used to solve the short-circuit current by solving the transfer impedance. The relationship between the change of short circuit position and the impact degree of DG is discussed in detail, and the calculation formula of extreme point is derived. When the DG capacity and short circuit location remain unchanged, the impact of DG grid-connected position on the upstream and downstream current is analysed. The characteristic curve of the impact of DG position change on protection current detection is given, and the impact of DG grid-connected position on protection sensitivity is explained clearly. The conclusion provides an important reference for the selection of DG grid-connected position and the calculation of relay protection in distribution network with DG. © Published under licence by IOP Publishing Ltd.

关键词： Timing circuits

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserved Neural Graph Similarity Learning

Privacy-Preserved Neural Graph Similarity Learning

引用

IEEE International Conference on data Mining (ICDM)

作者： Yupeng Hou Wayne Xin Zhao Yaliang Li Ji-Rong Wen Gaoling School of Artificial Intelligence Renmin University of China Beijing Key Laboratory of Big Data Management and Analysis Methods Engineering Research Center of Next-Generation Intelligent Search and Recommendation Ministry of Education Alibaba Group

To develop effective and efficient graph similarity learning (GSL) models, a series of data-driven neural algorithms have been proposed in recent years. Although GSL models are frequently deployed in privacy-sensitive scenarios, the user privacy protection of neural GSL models has not drawn much attention. To comprehensively understand the privacy protection issues, we first introduce the concept of attackable representation to systematically characterize the privacy attacks that each model can face. Inspired by the qualitative results, we propose a novel P rivacy-P reserving neural G raph M atching network model, named PPGM, for graph similarity learning. To prevent reconstruction attacks, the proposed model does not communicate node-level representations between devices. Instead, we learn multi-perspective graph representations based on learnable context vectors. To alleviate the attacks to graph properties, the obfuscated features that contain information from both graphs are communicated. In this way, the private properties of each graph can be difficult to infer. Based on the node-graph matching techniques while calculating the obfuscated features, PPGM can also be effective in similarity measuring. To quantitatively evaluate the privacy-preserving ability of neural GSL models, we further propose an evaluation protocol via training supervised black-box attack models. Extensive experiments on widely-used benchmarks show the effectiveness and strong privacy-protection ability of the proposed model PPGM. The code is available at: https://***/RUCAIBox/PPGM.

关键词： Training Performance evaluation Knowledge engineering Privacy Protocols Neural networks Closed box

来源：评论

学校读者我要写书评

暂无评论

ReconBoost: boosting can achieve modality reconcilement 24

ReconBoost: boosting can achieve modality reconcilement

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Cong Hua Qianqian Xu Shilong Bao Zhiyong Yang Qingming Huang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China and School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China and School of Cyber Security University of Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China and Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China and Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores a novel multi-modal alternating learning paradigm pursuing a reconciliation between the exploitation of uni-modal features and the exploration of cross-modal interactions. This is motivated by the fact that current paradigms of multi-modal learning tend to explore multi-modal features simultaneously. The resulting gradient prohibits further exploitation of the features in the weak modality, leading to modality competition, where the dominant modality overpowers the learning process. To address this issue, we study the modality-alternating learning paradigm to achieve reconcilement. Specifically, we propose a new method called ReconBoost to update a fixed modality each time. Herein, the learning objective is dynamically adjusted with a reconcilement regularization against competition with the historical models. By choosing a KL-based reconcilement, we show that the proposed method resembles Friedman's Gradient-Boosting (GB) algorithm, where the updated learner can correct errors made by others and help enhance the overall performance. The major difference with the classic GB is that we only preserve the newest model for each modality to avoid overfitting caused by ensembling strong learners. Furthermore, we propose a memory consolidation scheme and a global rectification scheme to make this strategy more effective. Experiments over six multi-modal benchmarks speak to the efficacy of the method. We release the code at https://***/huacong/ReconBoost.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic Alarm Causality Analysis Method Integrating Monitoring Contribution and Transfer Entropy

Dynamic Alarm Causality Analysis Method Integrating Monitori...

引用

Chinese Automation Congress (CAC)

作者： Yi Luo Lingkai Yang Linhao Nie Yuan Xu Qunxiong Zhu Jian Cheng State Key Laboratory for Intelligent Coal Mining and Strata Control Research Institute of Mine Big Data Chinese Institute of Coal Science Tiandi Science and Technology Co. Ltd. Beijing China College of Information Science and Technology Beijing University of Chemical Technology Beijing China

Alarm flooding poses a significant safety hazard in industry. It is of paramount importance to uncover the causality behind alarm flooding at its early stages. On one hand, limited data samples make it challenging to accurately determine the causal relationships among alarms. On the other hand, a massive volume of data samples may lead to delays in causal inference. This paper proposes a Contribution and Transfer-entropy based Dynamic Alarm Causality analysis method (CT-DAC) to address this. CT-DAC reconstructs the contribution of each monitored variable to the dynamic anomalies in the system, enabling dynamic causal relationship mining based on limited data. This approach offers a faster and more accurate solution for identifying the initial alarm causality triggering alarm flooding problems. Experimental work conducted on the Tennessee Eastman Process demonstrates the superior performance of the CT-DAC method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Optimization of Production Planning Scheme of China's New Energy Vehicles

SSRN

引用

SSRN 2022年

作者： Luo, Lina Li, Chengjiang Wang, Honglei Hu, Yujie Wang, Xiaolin School of Management Guizhou University Guiyang China Key Laboratory of "Internet +" Collaborative Intelligent Manufacturing in Guizhou Province China State Key Laboratory of Public Big Data Guizhou University Guizhou Guiyang550025 China School of Engineering University of Tasmania HobartTAS7005 Australia

To help enterprises control the carbon emissions of vehicles in the production process and obtain better profits, we proposes a fuzzy multi-objective optimization model, which considers the maximization of enterprise profits and the minimization of carbon emissions in the production process to plan the optimal production of new energy vehicles. The research results show that the market share of electric vehicles below 100,000 yuan is the highest, accounting for 39% of the market;The proportion of PHEVs and BEVs with more than 300,000 yuan is increasing year by year, indicating that the middle and high-end series of vehicles are becoming the main sales force in the new energy vehicle market;In addition, the output of FCVs and MVs will increase significantly in 2024 and 2025 under the guidance of policies and the active research and promotion of enterprises. © 2022, The Authors. All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Marine Fish Object Detection Based on YOLOv5 and Attention Mechanism

Marine Fish Object Detection Based on YOLOv5 and Attention M...

引用

Symposia and Workshops on Ubiquitous, Autonomic and Trusted Computing, UIC-ATC

作者： Lulu Chen Zhaoxiang Zang Tianxing Huang Zhao Li Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering China Three Gorges University Yichang Hubei China Nanhai Resources Big Data Center Southern Marine Science and Engineering Guangdong Laboratory (Zhanjiang) Zhanjiang Guangdong China

Automatic fish object detection methods based on computer vision have been widely used in recent years. In this paper, a YOLOv5s marine fish detection method that integrates attention mechanisms is proposed, which has alleviated the issue of misdetections and omissions caused by the shape, color, and size of the marine fish object. First, the multi-scale clustering method is used to recalculate the anchor box for matching the dataset. Then, the channel attention module is added to the feature extraction network of YOLOv5s by using the lightweight attention ECA-Net to obtain important feature information. Meanwhile, the spatial attention module SSA is used to enhance the edge feature information and improve detection accuracy. To further increase the generalization of the detection model, the DropBlock regularization method is added to sparse the features extracted from the backbone network to lessen the overfitting problem. The network is trained and tested using a combination of two publicly available datasets and a self-built dataset with rich samples covering complex living environments of marine fishes. Experiments demonstrate that our method can effectively increase the accuracy of fish object detection while also maintaining the speed of object detection.

关键词：

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：