检索结果-内蒙古大学图书馆

International Conference on Computer Supported Cooperative Work in Design

作者： Wenqiang Li Aimin Li Xiaotong Kong Yuechen Zhang Zhiyao Li 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 Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Remote sensing object detection has flourished at a rapid rate of development. In remote sensing images (RSI), most algorithms perform well in detecting medium and large objects but perform poorly on small objects. This is because small objects occupy fewer pixels in the entire image, and the detector is more likely to be biased towards detecting large objects. In addition, the huge background in the image also introduces noise, causing many detection failures. Most approaches solve the problem of small object detection by increasing the depth of the neural network, but the results are not satisfactory. To solve the above problems, we propose a new method, MF-YOLO, that utilizes fused infrared (IR) and red-green-blue (RGB) images for remote sensing object detection. Through multimodal fusion (MF), we can obtain more positive information, thereby improving detection accuracy. In addition, we introduced the Bi-Level Routing Attention (BRA) module to improve the YOLOv5s model structure, and proposed a new loss function to enhance the model’s learning discrimination ability. Experimental results show that the accuracy of MF-YOLO on the VEDAI and NWPU VHR-10 datasets is 76.62% and 91.63% respectively (in terms of mAP @0.5 ). Compared with the existing state-of-the-art, the detection accuracy is significantly improved. In addition, our model has fewer weight parameters than YOLOv5s, allowing it to achieve relatively high near-real-time detection speed.

关键词： YOLO Accuracy Federated learning Noise Neural networks Prediction algorithms Routing

来源：评论

学校读者我要写书评

暂无评论

HSD-YOLO: A Lightweight and Accurate Method for PCB Defect Detection

HSD-YOLO: A Lightweight and Accurate Method for PCB Defect D...

引用

International Joint Conference on Neural networks (IJCNN)

作者： Zhiyao Li Aimin Li Wenqiang Li Xiaotong Kong Yuechen Zhang 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 Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

PCB defect detection is a typical small objects detection task, as with other objects, there is a small object size, the detection process is susceptible to the problem of background interference. In practical industrial production, it is difficult for existing object detection models to realize the balance between accuracy and real-time performance. Therefore, we propose a new and lightweight object detection model. And we named it Hsd-YOLO. Firstly, HGNetv2, the backbone of the new paradigm RT-DETR for object detection, is chosen as the backbone of our model, which makes the model more lightweight and reduces the number of parameters and computation while guaranteeing the accuracy of the model’s detection. Secondly, we use the more lightweight convolutional GSConv, which is introduced into the neck to make the model balance between accuracy and speed. Finally, a unified dynamic head framework, DyHead (Dynamic Head), is introduced to make the model improve the representation of the object detection head without increasing the computational overhead. We perform comparison experiments as well as ablation experiments on a publicly available PCB defect datasets to fully illustrate the effectiveness of ours model. We conduct ablation experiments on the current state-of-the-art single-stage model YOLOv8, and our model improves AP, AR, mAP@0.5 and mAP@0.5-0.9 by 3.8%, 0.2%, 0.6% and 2.2%, respectively, and reduces the number of parameters in 385312 while ensuring accuracy. Comparing with major object detection models, our model performs the best in accuracy.

关键词： Accuracy Computational modeling Neural networks Object detection Quality control Production Real-time systems

来源：评论

学校读者我要写书评

暂无评论

A Grouping Strategy-Based Progressive Fusion network for Hyperspectral Image Super-Resolution

A Grouping Strategy-Based Progressive Fusion Network for Hyp...

引用

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

作者： Guohua Lv Baodong Zhang Yongbiao Gao Guixin Zhao Guotao Wang Juncan Wang 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 Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Application (Southeast University) Ministry of Education China Beihang University Beijing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Hyperspectral super-resolution involves combining low-resolution hyperspectral images with high-resolution multispectral images to produce a high-resolution hyperspectral image. Recently, although many methods for hyperspectral image super-resolution have been proposed, they often fail to fully utilize the high similarity among adjacent bands to enhance fusion performance. Therefore, we propose a grouping strategy-based progressive fusion network (GPFNet) for hyperspectral super-resolution. The core of GPFNet is the grouping strategy fusion block (GPF block), in which grouping-based spatial-spectral information fusion and spatial information refinement are performed. We design the spatial-spectral information fusion module (SSIFM) based on grouped convolutions to capture the feature differences from adjacent bands. To refine spatial details, we develop the spatial information enhancement module (SpaEM), which leverages the hierarchical features extracted by the multi-scale feature extraction module (MIEM). Additionally, a progressive fusion strategy, which involves using multiple upsampled hyperspectral images and downsampled multispectral images, further preserves spectral integrity and spatial details. Extensive experiments show that GPFNet outperforms state-of-the-art methods both qualitatively and quantitatively.

关键词： Convolution Superresolution Feature extraction Acoustics Data mining Speech processing Hyperspectral 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

Symbiosis Rather Than Aggregation: Towards Generalized Federated Learning via Model Symbiosis

引用

IEEE Internet of Things Journal 2025年

作者： Liu, Yuange Liu, Yuru Zhang, Weishan Zheng, Chaoqun Jiang, Wei Luo, Daobin Qiao, Qiao Meng, Lingzhao Zhao, Hongwei Yang, Su College of Computer Science and Technology Qingdao266580 China Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan Jinan250014 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Jinan250014 China Information Science Academy of China Electronics Technology Group Corporation Beijing100036 China Fudan University School of Computer Science Shanghai200433 China

Federated Learning (FL) faces significant challenges in scenarios with non-IID (non-independent and identically distributed) data distributions across participating clients. Traditional aggregation-based approaches often struggle with the inherent misalignment between local and global optimization objectives, leadingwhich leads to gradient divergence and suboptimal generalization performance. This paper proposes a novel FL framework that replaces conventional aggregation with a biologically inspired model symbiosis approach called FedSym, which employs a dual-level symbiotic mechanism. Ectosymbiosis performs coarse-grained hierarchical parameter recombinations through random layer-wise model combination, while endosymbiosis enables fine-grained intra-layer parameter fusion through weighted averaging, collectively steering model updates towards flatter loss landscapes. Our theoretical analysis demonstrates that FedSym's convergence rate is O(1T) under non-IID conditions, which matches the convergence properties of FedAvg. Extensive experimentsevaluations across multiple datasets and model architectures show that FedSym achieves substantial improvements over state-of-the-art FL methods, particularly in challenging scenarios with high data heterogeneity, and demonstrates robust performance across varying numbers of participating clients and federation scales. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A New Method to Enhance Container with vTPM 8

A New Method to Enhance Container with vTPM

引用

8th IEEE International Conference on Computer and Communications, ICCC 2022

作者： Jian, Zhang Xiao Peng, Zhou Qi, Wang Peng, Gao Liang, Wang Yi State Grid Smart Grid Research Institute Co. Ltd. State Grid Key Laboratory of Information & Network Security Nanjing China State Grid Zhejiang Electric Power Corporation Information & Telecommunication Branch Hangzhou China

ISBN: (纸本)9781665450515

This paper proposes a new container security enhancement system and method for containers running on 5G edge computing nodes. The system consists of vTPM module, physical TPM, container manager, vTPM manager, MEC controller and physical host. vTPM module is responsible for not only container image integrity measurement and starting up the container with trust, but also the trustworthiness measurement of container runtime file system and process. Physical TPM undertakes data encryption and password protection. Container manager performs trustworthiness measurement and verification of container. The MEC controller stores the measurement reference value for the physical TPM and issues keys and certificates for the physical TPM. The container enhancing method based on this system establishes a complete trust chain from the host to the container manager, and finally to containers. This ensures the trusted startup of the container, preventing the container itself and its runtime environment from being maliciously tampered with. It also dynamically measures the file system of the container in runtime to ensure the trustworthiness of the container. The experimental results indicate that this method is able to meet the requirements of container security enhancement for power 5G edge computing nodes. © 2022 IEEE.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

T-M Net: A Fusion Convolutional Neural network Method for Lung Aging Assessment

T-M Net: A Fusion Convolutional Neural Network Method for Lu...

引用

Medical Artificial Intelligence (MedAI), IEEE International Conference on

作者： Tangbin Tian Jingshan Pan Jing Ge Na Li Dexin Yu Liping Zuo 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 Department of Radiology Qilu Hospital of Shandong University Jinan China

ISBN: (数字)9798350377613

ISBN: (纸本)9798350377620

As the population ages, the precise assessment of pulmonary senescence becomes essential for the diagnosis and management of chronic respiratory diseases. However, existing medical imaging analysis techniques encounter significant chal-lenges due to data scarcity, especially in the domain of lung CT imaging. This research proposes an innovative method for assessing lung aging in CT images-T-M Net. This method combines transfer learning and MS-CNN to improve the accuracy and efficiency of lung aging assessment in CT images. We employed a pretrained ResNet18 model, capitalizing on transfer learning to harness the insights from extensive datasets, thereby minimizing the computational demands of model training. Furthermore, a channel attention mechanism is integrated within the transfer learning framework to heighten the model's focus on critical pulmonary regions, thus augmenting its predictive accuracy and interpretability. To accommodate the distinctive characteristics of lung CTs, a MS CNN architecture was developed, capturing multi-dimensional information ranging from microscopic details to macroscopic structures through variously sized convolutional kernels. Testing on a lung CT dataset revealed that our approach surpasses traditional methods in accuracy and generalizability, underscoring its potential utility in the early diagnosis and effective treatment of pulmonary ailments.

关键词： Training Accuracy Attention mechanisms Lungs Computational modeling Computed tomography Transfer learning Aging Convolutional neural networks Load modeling

来源：评论

学校读者我要写书评

暂无评论

Generating Personalized Imputations for Patient Health Status Prediction in Electronic Health Records

Generating Personalized Imputations for Patient Health Statu...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Yang Liu Weiyu Zhang Jiasheng Si Zhao Li Xueping Peng Wenpeng Lu 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 Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China Evay Info Jinan China Australian Artificial Intelligence Institute University of Technology Sydney Sydney Australia

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Electronic health records (EHRs) play a crucial role in the development of personalized treatment plans for patients. However, EHRs are often highly incomplete, posing significant challenges for predictive modeling. While existing deep learning models employ various imputation techniques to reconstruct missing values, they often fail to represent missing data in a personalized manner and do not learn from the missingness patterns in EHRs data. This limitation reduces their effectiveness in practical personalized healthcare applications. To address this issue, we propose SPIME, a self-supervised model that generates personalized imputations in EHRs data for patient health status prediction. We introduce a personalized missing mask (PMM) based on the frequency of feature measurements. Additionally, we incorporate a masked imputation task (MIT) loss that minimizes the loss of artificially introduced missing values, thereby enhancing the model’s capability to handle missing data. SPIME adopts self-supervised pretraining to learn representations from personalized missing patterns and reconstructs missing data in the latent space. To further enhance representation learning, two independent attention mechanisms are applied separately across the feature and temporal dimensions. Experimental results on two real-world EHRs datasets show that SPIME outperforms existing state-of-the-art methods in predicting in-hospital mortality and decompensation, demonstrating its effectiveness in reconstructing missing data and predicting patient health status. The code will be published at https://***/cling6666/SPIME.

关键词： Training Representation learning Biological system modeling Mortality Predictive models Biomedical measurement Imputation Data models Frequency measurement Electronic medical records

来源：评论

学校读者我要写书评

暂无评论

On the -differential spectra of two classes of power functions over finite fields

引用

Applicable Algebra in Engineering, Communication and computing 2025年 1-30页

作者： Liu, Qian Huang, Zhiwei Chen, Zhixiong Jiang, Rong Zhang, Liupiao Key Laboratory of Information Security of Network Systems College of Computer and Data Science Fuzhou University Fuzhou China Hubei Key Laboratory of Applied Mathematics Faculty of Mathematics and Statistics Hubei University Wuhan China Yunnan Key Laboratory of Service Computing Yunnan University of Finance and Economics Kunming China Fujian Key Laboratory of Financial Information Processing Putian University Putian China School of Computer Science and Technology Dongguan University of Technology Dongguan China

Recently, a new concept called multiplicative differential was introduced by Ellingsen et al. [7]. As an extension of the differential uniformity, it is theoretically appealing to determine the properties of c-differential uniformity and the corresponding c-differential spectrum. In this paper, based on certain quadratic character sums and two special elliptic curves over $$\mathbb {F}_p$$ , the $$(-1)$$ -differential spectra of the following two classes of power functions over $$\mathbb {F}_{p^n}$$ is completely determined: (1) $$f_1(x)=x^{\frac{p^n+3}{2}}$$ , where $$p>3$$ and $$p\equiv 3\pmod 4$$ ; (2) $$f_2(x)=x^{p^n-3}$$ , where $$p>3$$ . The obtained result shows that the $$(-1)$$ -differential spectra of $$f_1(x)$$ and $$f_2(x)$$ can be expressed explicitly in terms of n. Moreover, an upper bound of the c-differential uniformity of $$f_2(x)$$ is given.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EeCA: A Novel Approach for Energy Conservation in MEC via NDN-Based Content Caching

EeCA: A Novel Approach for Energy Conservation in MEC via ND...

引用

Asia-Pacific network Operations and Management Symposium (APNOMS)

作者： Jiaxin Xu Huiling Shi Haoxiang Chu Wei Zhang 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

In the context of escalating demands on wireless networks owing to the widespread application of 5G and the Internet of Things (IoT), enhancing network performance and user experience through the convergence of Multi-access Edge computing (MEC) and information-Centric networking (ICN) has become a critical research focus. This paper proposes a novel Energy-efficient Caching Algorithm (EeCA) based on Named Data networking (NDN), a specific implementation of ICN. This NDN-based caching strategy extends local caching in MEC networks and enhances the overall network performance by considering the multitude of repeated computational tasks and the residual energy of low-energy devices. The EeCA aims to reduce redundant offloading of tasks across the entire network, contributing to energy savings, and reducing overall system costs. Simulations reveal superior performance of EeCA compared to four other caching methods, specifically in terms of cache hit ratio and energy consumption, making it a promising solution for network performance enhancement and energy conservation in MEC networks.

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：