检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Guohua Lv Mao Yuan Zengbin Zhang Zhengyang Zhang Zhenhui Ding Guangxiao Ma Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China Shandong Key Laboratory of Ubiquitous Intelligent Computing Jinan China College of Computer Science and Engineering Shandong University of Science and Technology Qingdao China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Co-salient object detection (CoSOD) aims to detect common salient objects across multiple related images. However, existing methods often struggle with limited attention coverage, missing some co-salient objects. To address this, we propose a two-stage feature processing module (FPM) comprising comprehensive feature extraction module (CFE) and feature enhancement module (FEM). CFE extracts comprehensive cosalient features while reducing background noise, and FEM enhances feature representation and adjusts attention weights for full object coverage. Additionally, we introduce an adversarial learning module (ALM) to improve prediction quality by reducing noise in the co-salient regions. Extensive experiments on three benchmark datasets—CoCA, CoSOD3k, and CoSal2015—demonstrate that our model significantly outperforms state-of-the-art methods. The source code is available at https://***/yaobaimiao/CFPAM.

关键词： Attention mechanisms Source coding Noise Object detection Benchmark testing Feature extraction Adversarial machine learning Finite element analysis Background noise Speech processing

来源：评论

学校读者我要写书评

暂无评论

DAC-UNet: Dual Attention CNN-Enhanced CswinUnet for Gastric Cancer Pathological Image Segmentation

DAC-UNet: Dual Attention CNN-Enhanced CswinUnet for Gastric ...

引用

Medical Artificial Intelligence (MedAI), IEEE International Conference on

作者： Tao Hu Jingshan Pan Na Li Tangbin Tian Shengyu Liu Lu Zhang Yujiao Han Jiwei Xu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center(National Supercomputer Center in Jinan) Qilu University of Technology(Shandong Academy of Sciences) Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Jinan China

ISBN: (数字)9798350377613

ISBN: (纸本)9798350377620

Gastric cancer is one of the most lethal cancers. Currently, clinical diagnosis primarily relies on gastroscopic biopsies and the manual experience of doctors to assess the development of lesions in tissue sections. However, pathological screening requires a significant amount of time from specialized pathologists. Due to variations in clinical experience and limitations in medical resources, the detection of gastric cancer still faces challenges. Traditional methods for segmenting gastric cancer images often overlook the hierarchical structure of features and the spatial details, both local and global, in the lesion images. To address the above issues, this paper proposes a hybrid and efficient pathological image segmentation network named DAC-UNet, designed for precise pathological image segmentation tasks. DAC-UNet uses Cswin Transformer blocks to build a hierarchical structure, allowing it to capture global information with less computational complexity. The network also includes multi-scale dual attention skip connections between the encoder and decoder to preserve local spatial details and improve global interactions across different scales. We conducted a thorough theoretical analysis of this method and validated it on a gastric slice dataset. The experimental results demonstrate that our proposed method achieves outstanding performance on both our gastric slice dataset and the MoNuSeg dataset. Specifically, on our gastric slice dataset, we obtained a Dice similarity coefficient (DSC) of 89.42% and an HD95 of 47.24, while on the MoNuSeg dataset, we achieved a DSC of 79.28% and a 95th percentile Hausdorff distance (HD95) of 19.38.

关键词： Image segmentation Pathology Semantics Manuals Transformers Decoding Lesions Medical diagnostic imaging Faces Cancer

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Prediction of MPI Communication Time in High-Performance computing Applications

Machine Learning-Based Prediction of MPI Communication Time ...

引用

Frontiers technology of Information and Computer (ICFTIC), IEEE International Conference on

作者： Zhuang Wang Yuan Zhuang Yunhui Zeng Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798331541750

ISBN: (纸本)9798331541767

The rapid advancements in high-performance computing (HPC) have made large-scale parallel computing feasible. As a commonly used parallel programming model, Message Passing Interface (MPI) plays a crucial role in HPC systems and directly affects the performance and efficiency of these applications. Therefore, modeling and predicting the performance of MPI communication is critically important. This paper utilizes a machine learning-based approach to predict MPI communication time. It uses performance analysis tools to collect real-time communication data and select critical features related to execution time. The data is categorized, then, for each type of MPI communication, a dedicated regression model is trained. Firstly, XGBoost and Artificial Neural networks (ANN) are employed for function level modeling. Then, fusion techniques are used to combine XGBoost and ANN models to improve prediction accuracy. Finally, these function level models are integrated into an application level model to predict the overall communication time. This model is evaluated using CG, FT, and CPMD. Experimental results show that the average prediction errors of the model are 12.6%, 13.2%, and 13.5%, with a minimum error of 7%.

关键词： Accuracy Computational modeling High performance computing Message passing Artificial neural networks Machine learning Predictive models Data models Supercomputers Tuning

来源：评论

学校读者我要写书评

暂无评论

TDMF: Text-Guided Denoising and Interactive Medical Image Fusion

TDMF: Text-Guided Denoising and Interactive Medical Image Fu...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Aimei Dong Jingyuan Xu Long Wang Guohua Lv Guixin Zhao Jinyong Cheng Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Faculty of Computer Science and Technology Qilu University of Technology(Shandong Academy of Sciences) Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Multimodal image fusion aims to merge features from different modalities to create a comprehensively representative image. However, existing medical image fusion methods often struggle to handle noise generated during image acquisition, significantly diminishing their impact on visual quality. To address these challenges, we propose a semantically text-guided medical image fusion model, named TDMF. Specifically, TDMF guides classical image fusion through textual semantics and effectively coordinates the resolution of degradation and interaction issues during the fusion process. By integrating text encoders and interactive fusion modules, TDMF establishes a unified framework for denoising and interactive fusion of medical images. Extensive experiments have demonstrated that our proposed text-guided image fusion strategy offers significant advantages over state-of-the-art methods in medical image fusion performance.

关键词： Visualization Image resolution Semantics Noise reduction Noise Pipelines Noise measurement Speech processing Image fusion Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

HiRes: Hierarchical Feature Optimization and Rescorer for Automatic ICD Coding

HiRes: Hierarchical Feature Optimization and Rescorer for Au...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Zhenpeng Liang Hongjiao Guan Wenpeng Lu Xueping Peng Bing Xu Muyun Yang Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China Australian Artificial Intelligence Institute University of Technology Sydney Sydney Australia Faculty of Computing Harbin Institute of Technology Harbin China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The International Classification of Diseases (ICD) coding assigns standardized codes to diseases. Automating this process enhances the efficiency and accuracy of clinical records processing. However, current methods struggle with noisy and lengthy clinical texts, making it difficult to ensure the reliability of feature extraction. Furthermore, they typically make separate binary predictions for each code, overlooking the dependencies between them. To address these issues, we propose a novel model called Hierarchical Feature Optimization and Rescorer (HiRes). We employ a cascaded convolution architecture to mitigate noise and enhance feature representation. Additionally, a masked autoencoder-based rescorer is introduced to capture ICD code interdependencies, refining initial predictions for improved accuracy. The model also considers the inconsistencies in code representations. Experiments on the MIMIC datasets demonstrate the effectiveness of our model.

关键词： Codes Accuracy Computational modeling Noise Refining Encoding Reliability Speech processing Optimization Diseases

来源：评论

学校读者我要写书评

暂无评论

Offloading Mode Hidden for Delay Sensitive Tasks in Edge computing networks

Offloading Mode Hidden for Delay Sensitive Tasks in Edge Com...

引用

Artificial Intelligence, networking and Information technology (AINIT), International Seminar on

作者： Guowei Zhang Jiayuan Du School of Cyber Science and Engineering Qufu Normal University Qufu China Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology (Shandong Academy of Sciences) Jinan China

ISBN: (数字)9798350385557

ISBN: (纸本)9798350385564

Edge computing has been developed to support local services with lower burden to the core network. However, privacy issues deteriorate when terminal users enjoy the high-quality services with the price of sending their data to multiple service nodes (SNs) scattered throughout the network. Existing researches concerning this problem are almost all based on the traditional security technologies including encryption and authentication, which are too complicated to be well supported by the terminal nodes (TNs) in edge networks due to the poor local processing capabilities. In view of the above, this article proposes an offloading mode hidden (OMH) algorithm, which reduces the risk level by equalizing the task offloading modes of different TNs. Gaming process is adopted to achieve the risk-minimized offloading solutions for TNs. Numerical results demonstrate that comparing with the Greedy algorithm, the proposed OMH algorithm can achieve lower task offloading risk with higher efficiency and provide more TNs with satisfied services.

关键词： Greedy algorithms Seminars Privacy Risk minimization Processor scheduling Scheduling Delays

来源：评论

学校读者我要写书评

暂无评论

$k$k-TEVS: A $ k$k-Times E-Voting Scheme on Blockchain With Supervision

引用

IEEE Transactions on Dependable and Secure computing 2024年第3期22卷 2326-2337页

作者： Yang Liu Debiao He Min Luo Lianhai Wang Cong Peng School of Cyber Science and Engineering Wuhan University Wuhan China Institute of Information Technology Shenzhen Institute of Information Technology Shenzhen China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shanghai Technology Innovation Centre of Distributed Privacy-Preserving Artificial Intelligence Matrix Elements Technologies Shanghai China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China

The e-vote is regarded as a way to express the opinion that the voters ask for. Actually, the e-vote could be applied wildly like questionnaire, survey and feedback. Moreover, the coexistences of efficiency and security as well as transparency and privacy could be considered as building blocks in the e-vote system. The blockchain could provide a public access board to reduce the storage costs for the field consisted of the vote group manager (GM) with its vote assistants (VA). Particularly the $k$ -times anonymous authentication ( $k$ -TAA) could also be a practical approach to preserve voters’ privacy and reduce the computation costs during the vote process. However, the e-vote scheme with pure $k$ -TAA strategy could damage either the supervision of voting or the efficiency and consistency of authentication process. What’s more, the impacts of dishonest voters couldn’t be stopped until the vote end. To tackle these problems, we apply the accumulator technology to add or revoke the voters at any time and extend the framework of $k$ -TAA with the update process for the e-vote on blockchain for supervision ( $ k$ -TEVS). In our scheme, the voter updates his membership witness and proves the fact that he is still a valid member with respective VA under the latest accumulator value. What’s more, this witness update operation is not contained in the authentication process, which means that the authentication process is still constant and efficient. Moreover, our add or delete update process with signature of knowledge needs only one pairing operation. For the security, we prove that the relaxed anonymity still holds in the $ k$ -TEVS framework. Finally, We implement $ k$ -TEVS scheme, the Emura’s work [1] and the Huang’s work [2] for comparison. Then we make time cost and communication cost experiments, which present the feasibility and practicality of this scheme.

关键词： Blockchains Authentication Costs Protocols security Privacy Surveys Electronic voting Computer science Information security

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Node Verification and Protection Strategy for Edge computing

A Lightweight Node Verification and Protection Strategy for ...

引用

Artificial Intelligence, networking and Information technology (AINIT), International Seminar on

作者： Jiayuan Du Guowei Zhang School of Cyber Science and Engineering Qufu Normal University Qufu China Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology (Shandong Academy of Sciences) Jinan China

ISBN: (数字)9798350385557

ISBN: (纸本)9798350385564

To alleviate the burden on the core network, edge computing has rapidly advanced to support distributed computing. However, as sensitive information is delegated to the edge layer closer to endpoints, the privacy protection challenges faced by edge nodes intensify while striving to deliver high-quality services. Existing studies predominantly rely on various encryption algorithms to safeguard privacy information, such as identity, location, and offloading routes privacy. Unfortunately, these approaches exhibit high overhead and often neglect the potential maliciousness of the nodes themselves. To address these issues, this paper introduces a lightweight edge node verification and protection strategy. This strategy not only verifies the reliability of edge nodes but also enables anonymized uploading of private information. Numerical simulation results demonstrate the superiority of this strategy over existing schemes, showcasing reduced computational overhead while achieving enhanced protection.

关键词： Seminars Privacy Numerical simulation Mathematical models Performance analysis security Reliability

来源：评论

学校读者我要写书评

暂无评论

Ensemble Learning-based Traffic Classification with Small-Scale Datasets for Wireless networks

Ensemble Learning-based Traffic Classification with Small-Sc...

引用

IEEE Conference on Computer Communications Workshops, INFOCOM Wksps

作者： Xiaorong Wang Wenting Wei Xiaoshan Yu Danyang Zheng Neeraj Kuma Lei Liu State Key Laboratory of Integrated Service Networks Xidian University Xi'an China School of Computing and Artificial Intelligence Southwest Jiaotong University China Department of Computer Science and Engineering Thapar Institute of Engineering and Technology India Guangzhou Institute of Technology Xidian University Xi'an China Shaanxi Key Laboratory of Information Communication Network and Security Xi'an University of Posts & Telecommunications Xi'an China

ISBN: (数字)9798350384475

ISBN: (纸本)9798350384482

Traffic classification is an essential part of intelligent network management in Fifth generation (5G) networks, from quality of service guarantees to security monitoring. With the evolution of diverse services and applications over 5G networks, traffic patterns and their implications also becoming more complicated, especially in wireless networks. How to dynamically manage the growing traffic demand and satisfy the quality of service (QoS) needs of new applications is particularly critical. The biggest challenge is how to identify traffic types accurately without application information and manual features. However, the existing deep learning (DL)-based classifiers heavily rely on extensive and high-quality samples, which proves impractical to obtain in wireless networks. To overcome this limitation, we propose an ensemble Learning based traffic classification model to provide accurate identification with small-scale datasets, where Attention-based Long Short-Term Memory networks are bagged to train this classifier. The ensemble learning approach employs a combinatorial design involving five base models to construct more accurate and robust learning models. This enables effective feature absorption, making it feasible to train classifiers on limited sample sets. Comprehensive experiments are conducted using a real-world dataset covering 16 applications. Results demonstrate that, even with a mere 10% of training samples, our proposed model achieves a classification accuracy of 95.57% and a precision of 95.83%, surpassing multiple cutting-edge methods.

关键词： Training Accuracy 5G mobile communication Wireless networks Computational modeling Quality of service Telecommunication traffic

来源：评论

学校读者我要写书评

暂无评论

Prediction Model for Continuous Observation of Aerosol Extinction Coefficient Based on Random Forest from Mie Lidar Signal

SSRN

引用

SSRN 2023年

作者： Chen, Hao Gao, Fei Rao, Zhimin Hua, Dengxin Xi’an University of Technology Xi’an710048 China Shaanxi Key Laboratory for Network Computing and Security Technology Xi’an710048 China North Minzu University Xi’an710048 China School of Mechanical and Precision Instrument Engineering Xi’an University of Technology No. 5 South Jinhua Road Shaanxi Xi’an710048 China

A new prediction model was developed for continuous observation of the aerosol extinction coefficient from Mie lidar signals. Based on the random forest method, the model was trained using a dataset built from the Mie lidar signal, detection time, height, pressure, and humidity data. The model parameters were optimised using a Bayesian optimisation method to improve the accuracy of the model prediction results. Three types of datasets representing the characteristics of atmospheric detection data were selected for model performance testing. The experimental results show that, compared with LR, KNN and BP model, the inversion result of the aerosol extinction coefficient predicted by this model has the minimum error and the highest accuracy and is closest to the Klett. The research presented in this paper provides a technical means for an accurate study of the optical characteristics of atmospheric environmental parameters. © 2023, The Authors. All rights reserved.

关键词： Aerosols

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：