检索结果-内蒙古大学图书馆

Information and Communication Technology (ICTech), International Conference of

作者： HongLiang Wang GuoYang Xing JunLi Wang Xing Gao XueRao Li XingYu Liu Shenyang Institute of Computing Technology Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China Liaoning Province Human-Computer Interaction System Engineering Research Center Based on Digital Twin Shenyang China Affiliated Hospital of Guangdong Medical University Guangzhou China Shengjing Hospital of China Medical University Shenyang China

ISBN: (数字)9798350376258

ISBN: (纸本)9798350376265

The development of server arithmetic benchmarking is of great significance to the development of the whole chip and the whole server arithmetic. Currently, the existing arithmetic tests are categorized into traditional server arithmetic tests, e.g., Linpack, and AI server arithmetic tests, e.g., MlPerl. Traditional server arithmetic tests are insufficient to reflect the arithmetic power of AI servers, and existing AI servers ignore the limitations of the parallelism method, which leads to the instability of the final test results. In this paper, we propose a parallel computing method, DPipe-C, for benchmarking to balance the contradiction between long testing time and unstable test results during training tests. The method uses a dual-pipe approach in order to reduce the size of bubbles in the parallel process and improve the overall throughput of the system. It also uses synchronization to ensure the stability of its results. In the different stages of data transmission, the data is compressed to improve the overall training efficiency, and the delayed delivery error method is used to reduce the impact of the compression process on the training results to ensure the stability of the results. Using this method, the overall throughput of the system is increased by nearly 20%. At the same time, the training accuracy can reach the original accuracy of the model.

关键词： Training Industries Computational modeling Parallel processing Throughput Stability analysis Servers Synchronization Artificial intelligence Arithmetic

来源：评论

学校读者我要写书评

暂无评论

research on Load Forecasting based on IPSO-BILSTM-GRU Model

Research on Load Forecasting Based on IPSO-BILSTM-GRU Model

引用

International Conference on Computer and Communications (ICCC)

作者： Xueting Li Hongliang Wang Pengfei Xiu Yongfeng Li Shenyang Institute of Computing Technology Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China Liaoning Province Human-Computer Interaction System Engineering Research Center Based on Digital Twin Shenyang China

High accuracy of resource load prediction can provide basis for real-time task scheduling, thus reducing energy consumption. Aiming at the problems that the CPU and memory load changes in cloud computing platform cannot be accurately predicted and it is difficult to adjust the parameters of common timing prediction algorithms, a combined prediction model of bidirectional long short-term memory network (BILSTM) and gated recurrent unit (GRU) based on improved particle swarm optimization (IPSO), IPSO-BILSTM-GRU, was proposed. Our model combines the characteristics of high prediction accuracy of BILSTM network and short prediction time of GRU network. The IPSO algorithm is used to optimize the model parameters. In the experiment, the combined values of CPU and memory indexes of Google data center are selected as input data and compared with many typical time series prediction algorithms. Experimental results show that the MAPE (mean absolute percentage error) of IPSO-BILSTM-GRU model is reduced by 1.0% to 4.4%, and the training time is shortened by more than 11%. The experimental results verify that the method has higher accuracy and strong applicability in time series prediction, which provides an important scientific basis for elastic capacity expansion using load prediction results.

关键词： Cloud computing Load forecasting Computational modeling Time series analysis Predictive models Prediction algorithms Timing

来源：评论

学校读者我要写书评

暂无评论

Load Balancing Strategy based on Stochastic Theory

Load Balancing Strategy Based on Stochastic Theory

引用

International Conference on Computer and Communications (ICCC)

作者： Ruifeng Guo Youkang Li Hongliang Wang Pengfei Xiu Yunjiang Liu Shenyang Institute of Computing Technology Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Shenyang China Liaoning Provience Human-Computer Interaction System Engineering Research Center Based on Digital Twin Shenyang China

In order to further improve the load balancing strategy, this paper summarizes and designs a load balancing method based on random selection. By introducing the Balls into Bins problem into the load balancing strategy, random selection is used to reduce the time spent in the allocation process. And batch selection is used to reduce the possibility of overloading nodes. The result shows that these methods algorithm can get a better task allocation method in as short a time as possible.

关键词： Scheduling algorithms Stochastic processes Big Data Load management Prediction algorithms Scheduling Resource management

来源：评论

学校读者我要写书评

暂无评论

research on Sensitive Text Classification based on Knowledge Base and Hybrid Network

Research on Sensitive Text Classification Based on Knowledge...

引用

International Conference on Computer and Communications (ICCC)

作者： Yongfeng Li Hongliang Wang Xueting Li Pengfei Xiu Shenyang Institute of Computing Technology Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China Liaoning Province Human-Computer Interaction System Engineering Research Center Based on Digital Twin Shenyang China

Aiming at the problems that convolution neural network is not sufficient to extract text features, it is difficult to capture long text structure information and sentence semantic relationship, and neural network can only extract the surface features of text, and it is difficult to obtain the implicit features of sentences when classifying text, this paper proposes a hybrid neural network text classification method based on a knowledge base. By extracting keywords from the category text, the keyword weight is calculated according to the co-occurrence relationship, and the category keyword knowledge base is constructed. It integrates CNN and bilstm, introduces attention mechanism, enhances the ability to extract local and temporal features of text, and improves the accuracy of text classification in combination with knowledge base information. The experimental results on the CNews dataset show that compared with TextCNN, TextRCNN, BILSTM and Bert models, this model can effectively improve the accuracy of text classification.

关键词： Convolution Computational modeling Text categorization Knowledge based systems Neural networks Semantics Feature extraction

来源：评论

学校读者我要写书评

暂无评论

CL-MIL: Multi-Instance Learning on Whole-Slide Images with Self-Supervised Contrastive Learning

CL-MIL: Multi-Instance Learning on Whole-Slide Images with S...

引用

International Conference on Computer and Communications (ICCC)

作者： Pengfei Xiu Dongying Liu Sheng Wang Hongliang Wang Wei Wang Shun Li Shenyang Institute of Computing Technology Chinese Academy of Science Shenyang China University of Chinese Academy of Sciences Beijing China Liaoning Province Human-Computer Interaction System Engineering Research Center Based on Digital Twin Shenyang China Department of Gastroenterology Shengjing Hospital of China Medical University Shenyang China School of Computer Science and Engineering Northeastern University Shenyang China

ISBN: (数字)9798331507077

ISBN: (纸本)9798331507084

Histopathological examination of tissue slides is considered the gold standard for clinical cancer diagnosis. However, it heavily relies on pathologists' subjective judgment and involves substantial workload. Existing convolutional neural network (CNN)-based whole slide image (WSI) diagnostic methods suffer from high annotation costs and complex data acquisition processes. Therefore, this study proposes a weakly supervised multiple instance learning method based on self-supervised contrastive learning (CL-MIL) for WSI classification. By integrating self-supervised contrastive learning strategies, leveraging data augmentation through H&E stain separation, and introducing causal intervention via backdoor adjustment to mitigate dataset bias, our approach significantly enhances feature representation and classification performance in pathological images. Experimental results on the Camelyon16 and TCGA lung cancer datasets demonstrate that our method outperforms other comparable WSI classification models across various evaluation metrics, achieving higher diagnostic efficiency and accuracy. Additionally, our method exhibits good interpretability, enabling precise localization of pathological regions and providing robust technical support for clinical applications.

关键词： Measurement Location awareness Pathology Accuracy Weak supervision Lung cancer Contrastive learning Feature extraction Standards Image classification

来源：评论

学校读者我要写书评

暂无评论

Towards Emotion Analysis in Short-form Videos: A Large-Scale Dataset and Baseline

arXiv

引用

arXiv 2023年

作者： Wu, Xuecheng Sun, Heli Xue, Junxiao Nie, Jiayu Kong, Xiangyan Zhai, Ruofan He, Liang School of Computer Science and Technology Xi’an Jiaotong University Xi’an China Research Center for Space Computing System Zhejiang Lab Hangzhou China School of Electronics and Information Engineering Harbin Institute of Technology Harbin China School of Cyber Science and Engineering Zhengzhou University Zhengzhou China

Nowadays, short-form videos (SVs) are essential to web information acquisition and sharing in our daily life. The prevailing use of SVs to spread emotions leads to the necessity of conducting video emotion analysis (VEA) towards SVs. Considering the lack of SVs emotion data, we introduce a large-scale dataset named eMotions, comprising 27,996 videos. Meanwhile, we alleviate the impact of subjectivities on labeling quality by emphasizing better personnel allocations and multi-stage annotations. In addition, we provide the category-balanced and test-oriented variants through targeted data sampling. Some commonly used videos, such as facial expressions, have been well studied. However, it is still challenging to analysis the emotions in SVs. Since the broader content diversity brings more distinct semantic gaps and difficulties in learning emotion-related features, and there exists local biases and collective information gaps caused by the emotion inconsistence under the prevalently audio-visual co-expressions. To tackle these challenges, we present an end-to-end audio-visual baseline AV-CANet which Copyright © 2023, The Authors. All rights reserved.

关键词： Video analysis

来源：评论

学校读者我要写书评

暂无评论

CL-MIL: Multi-Instance Learning on Whole-Slide Images with Self-Supervised Contrastive Learning 10

CL-MIL: Multi-Instance Learning on Whole-Slide Images with S...

引用

10th International Conference on Computer and Communications, ICCC 2024

作者： Xiu, Pengfei Liu, Dongying Wang, Sheng Wang, Hongliang Wang, Wei Li, Shun Shenyang Institute of Computing Technology Chinese Academy of Science Shenyang China University of Chinese Academy of Sciences Beijing China Liaoning Province Human-Computer Interaction System Engineering Research Center Based on Digital Twin Shenyang China Shengjing Hospital of China Medical University Department of Gastroenterology Shenyang China School of Computer Science and Engineering Northeastern University Shenyang China

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

A large model method for fine-tuning segmentation of all abdominal tumors based on the AdaLoRA approach

A large model method for fine-tuning segmentation of all abd...

引用

IEEE International Conference on Signal and Image Processing (ICSIP)

作者： Hongliang Wang Hu Li Lijun Fu Xiaozhou Liu Jing Xu Shenyang Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Liaoning Province Human-Computer Interaction System Engineering Research Center Based on Digital Twin Shenyang China Shandong University Big Data Technology and Cognitive Intelligence Laboratory University of Chinese Academy of Sciences Shenyang China Stomatological Hospital Affiliated to China Medical University Shenyang China

ISBN: (数字)9798350350920

ISBN: (纸本)9798350350937

Medical image segmentation is an important task in the field of medical image processing, and deep learning-based methods have made significant progress in this area. However, traditional segmentation models have limitations when dealing with complex and diverse medical images, and they lack interactivity. To overcome these limitations, the SAM adapter is introduced into the SAM algorithm to provide greater flexibility and scalability. We also introduce an object detection interactive algorithm to enhance the interactivity of the model. The SAM adapter allows for customized model adjustments to adapt to different medical image segmentation tasks and datasets. By finetuning the SAM adapter using the AdaLORA method, we propose the AdaSAMed algorithm, which enables researchers to conveniently develop adaptive and accurate segmentation models, thus promoting further advancement in medical image segmentation of gastrointestinal tumors.

关键词： Learning systems Image segmentation Adaptation models Scalability Object detection Robustness Gastrointestinal tract

来源：评论

学校读者我要写书评

暂无评论

A Vein Segmentation Method based on Improved U-Net

A Vein Segmentation Method Based on Improved U-Net

引用

Information and Communication Technology (ICTech), International Conference of

作者： Hongliang Wang Liang Zhu Changyi Deng Pengfei Xiu Chinese Academy of Sciences Shenyang Institute of Computing Technology Shenyang China University of Chinese Academy of Sciences Beijing China Liaoning Province Human-Computer Interaction System Engineering Research Center Based on Digital Twin Shenyang China China Industrial Control Systems Cyber Emergency Response Team Institute of Software Beijing China

Recently, medical research has revealed that diffusion weighted imaging (DWI) is less sensitive than susceptibility-weighted imaging (SWI) for acute ischemic stroke. Brain vein analysis in SWI is very important for personalised therapy, quantitative diagnosis, and prognosis of acute ischemic stroke. Therefore, the accurate segmentation of veins in SWI images has important significance in supplementary diagnosis and medical research. However, vein segmentation in SWI is a challenging task because different veins show distinct variability and uneven intensity and are difficult to manually split. This paper proposes an improvement method based on U-net, by using dense connection and mixing loss function, the best Dice coefficient and the ASSD were obtained by other comparison methods. The method presented in this article can be used as a potential tool to accurately measure SWI cerebral veins and help physicians in decision making.

关键词：

来源：评论

学校读者我要写书评

暂无评论

STAR-RIS Enabled ISAC systems With RSMA: Joint Rate Splitting and Beamforming Optimization

引用

IEEE Transactions on Cognitive Communications and Networking 2025年

作者： Liu, Yuan Zhang, Ruichen Jiang, Ruihong Zhu, Yongdong Hu, Huimin Ni, Qiang Fei, Zesong Niyato, Dusit Zhejiang Laboratory Research Center for Space Computing System Hangzhou311100 China Nanyang Technological University College of Computing and Data Science Singapore 639798 Singapore Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing100876 China Cambridge Mechatronics Ltd CambridgeCB1 2PH United Kingdom Xi’an University of Posts and Telecommunications School of Communications and Information Engineering School of Artificial Intelligence Xi’an710121 China Lancaster University School of Computing and Communications LancasterLA1 4WA United Kingdom Beijing Institute of Technology School of Information and Electronics Beijing100081 China

This paper delves into an integrated sensing and communication (ISAC) system bolstered by a simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS). Within this system, a base station (BS) is equipped with communication and radar capabilities, enabling it to communicate with ground terminals (GTs) and concurrently probe for echo signals from a target of interest. Moreover, to manage interference and improve communication quality, the rate splitting multiple access (RSMA) scheme is incorporated into the system. The signal-to-interference-plus-noise ratio (SINR) of the received sensing echo signals is a measure of sensing performance. We formulate a joint optimization problem of common rates, transmit beamforming at the BS, and passive beamforming vectors of the STAR-RIS. The objective is to maximize sensing SINR while guaranteeing the communication rate requirements for each GT. We present an iterative algorithm to address the non-convex problem by invoking Dinkelbach’s transform, semidefinite relaxation (SDR), majorization-minimization, and sequential rank-one constraint relaxation (SROCR) theories. Simulation results manifest that the performance of the studied ISAC network enhanced by the STAR-RIS and RSMA surpasses other benchmarks considerably. The results evidently indicate the superior performance improvement of the ISAC system with the proposed RSMA-based transmission strategy design and the dynamic optimization of both transmission and reflection beamforming at STAR-RIS. © 2015 IEEE.

关键词： Signal to noise ratio

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：