检索结果-内蒙古大学图书馆

9th IEEE International Conference on Data Science in Cyberspace, DSC 2024

作者： Wang, Lianhai Wang, Xinlei Liu, Tianrui Wang, Yingxiaochun Li, Qi 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 Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Industrial Network and Information System Security Jinan China

ISBN: (纸本)9798350391367

The rapid growth of healthcare data transactions has fostered win-win developments in healthcare technology innovation and economic benefits. However, the issue of secondary transactions makes data ownership vulnerable to infringement due to the easily replicable nature of the data. As the importance of ownership and privacy increases, more and more users protect the privacy of data through encryption methods, making it impossible for existing methods to make infringement judgments on ciphertext data. To solve this problem, we propose an infringement detection and traceability scheme based on feature extraction of ciphertext data. Firstly, the characteristics of fully homomorphic encryption are utilized to obtain data features in the ciphertext state, and the plaintext state of these features is used as the basis for infringement judgment. Additionally, during the data transaction process, the ownership registration of the sales data is verified through smart contracts to ensure the effective association between the transaction data and the seller's address. The experimental results show that the scheme can accurately determine infringement while protecting data security and privacy. © 2024 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Multi-Label Text Classification for Judicial Texts via Dual Graph and Label Feature Fusion 10

Multi-Label Text Classification for Judicial Texts via Dual ...

引用

10th IEEE Smart World Congress, SWC 2024

作者： Gu, Qiliang Lu, Qin Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Industrial Network and Information System Security Jinan China

ISBN: (纸本)9798331520861

The legal judgement prediction (LJP) of judicial texts represents a multi-label text classification (MLTC) problem, which in turn involves three distinct tasks: the prediction of charges, legal articles, and terms of penalty. Nevertheless, extant multi-label text classification models tend to eschew the consideration of multiple correlations and semantic information between labels when predicting judicial texts, which may result in the loss of pertinent information. Furthermore, these models do not take full advantage of the local and overall information of the labels in the process of selecting appropriate labels for the text using the multi-head attention mechanism. To address these issues, we propose a new model, BGFLFF, which explores label correlation and semantics among the three tasks by employing Graph Convolutional network (GCN) and multi-head attention mechanisms. In particular, we propose a Bi-Graph Fusion GCN (BGF-GCN), which fuses the co-occurrence matrix of labels with the cosine similarity matrix, thereby fully exploiting the multiple correlations between labels. Furthermore, prior to embedding the tags, the interpretations of the labels are obtained via Google in order to enhance the semantic information between the labels. To further reinforce the interconnections between labels and text and more effectively comprehend the interrelationships between the three tasks, we propose a Multi-Head Label Feature Fusion Attentional Mechanism (MH-LFFAtt), which assigns distinct weights to the pertinent label information in the text by fusing the local and overall features of the labels. The experimental results demonstrate that the F1 score exhibits an improvement of up to 2. 2 8 % and a minimum of 1. 2 9 % across the various tasks of the two datasets. This evidence substantiates the assertion that BGFLFF outperforms the existing baseline model. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Lightweight Image Captioning Model Based on Knowledge Distillation 30th

Lightweight Image Captioning Model Based on Knowledge Disti...

引用

30th International Conference on MultiMedia Modeling, MMM 2024

作者： Cui, Zhenlei Tang, Zhenhua Li, Jianze Chen, Kai School of Computer and Electronics Information Guangxi University Nanning530004 China Guangxi Key Laboratory of Multimedia Communication and Network Technology Nanning530004 China

ISBN: (纸本)9783031533075

The performance of image captioning models based on deep learning has been significantly improved compared with traditional algorithms. However, due to the complex network structure and huge parameters, these image captioning models are hard to apply to resource-constrained appliances such as mobile embedded systems. To address this issue, we propose two lightweight image captioning models based on two pre-training models, i.e. M2 Transformer and CaMEL. To improve the performances of the proposed lightweight models, we also develop an optimization training strategy based on knowledge distillation. Specifically, we design knowledge distillation loss functions in the encoder, decoder, and response modules, which can use the multi-modal feature mapping of the original models to transfer prior knowledge, improving the feature learning ability and generalization ability of the lightweight models. Experimental results show that the proposed lightweight models are superior to the original pre-trained models in performance when reducing the parameters greatly. Besides, the proposed lightweight models also have a good knowledge transfer ability. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

ID-YOLOv7: A Method for Steel Surface Defect Detection Combining Residual Attention and Dynamic Upsampling 10

ID-YOLOv7: A Method for Steel Surface Defect Detection Combi...

引用

10th IEEE Smart World Congress, SWC 2024

作者： Liu, Shanshan Liu, Xiangzhi Man, Jiazheng Cao, Bingyang Dong, Yunfeng Wu, Xiaoming Jinan China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (纸本)9798331520861

Industrial defect detection is a crucial challenge in computer vision. The accuracy of detecting defects on steel surfaces is hindered by spatially varying noise. To address this challenge, we propose an efficient method for steel surface defect detection. Firstly, considering the impact of the shape and proportions of bounding boxes on localization accuracy, we developed an Adaptive Shape-Inner Intersection over Union (ASIIoU) loss function. This function dynamically adjusts auxiliary bounding boxes and takes into account their shape and scale to optimize the loss, thereby improving the accuracy of bounding box regression loss. Secondly, to enhance the ability of the model to learn local features, we designed a Content-Guided Residual Attention Block (CGRAB). It captures rich local features across different convolutional layers via skip connections while discarding irrelevant information. Lastly, to avoid the potential issue of detail blurring caused by traditional upsampling methods, we optimized the upsampling process to preserve key details and structural information in the image, reducing unnecessary noise amplification. Experimental validation demonstrates the effectiveness of our method, which achieved a 76.7 % mAP on the NEU-DET dataset. © 2024 IEEE.

关键词： Surface defects

来源：评论

学校读者我要写书评

暂无评论

SGNet: A Multi-Scale Method for Steel Surface Defect Detection 10

SGNet: A Multi-Scale Method for Steel Surface Defect Detecti...

引用

10th IEEE Smart World Congress, SWC 2024

作者： Liu, Shanshan Liu, Xiangzhi Man, Jiazheng Cao, Bingyang Dong, Yunfeng Wu, Xiaoming Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Industrial Network and Information System Security Jinan China

ISBN: (纸本)9798331520861

The large variation in target scales within steel surface defect images often results in low detection accuracy. To address this issue, we have developed a multi-scale defect detection method named SGNet. Initially, we introduced a Self-Guided Bi-Level Routing Transformer (SG-BiFormer) as the backbone network of our model. SG-BiFormer utilizes a self-guided strategy to model global information and dynamically reallocates tokens based on the importance of image regions, increasing token quantity in significant areas to preserve fine-grained details and reducing it in less critical areas. This strategy significantly enhances the accuracy and efficiency of the model in handling multi-scale targets. Subsequently, we incorporated Grouped Separable Convolutions (GSConv) to manage local information of multi-scale features. GSConv automatically adjusts the size and shape of the convolution kernels according to different input features. This design not only improves global information processing capabilities but also ensures sensitive and precise detail capture. Lastly, we employed MPDIoU as the loss function for our model, which optimizes corner positioning to tackle the challenges of regression tasks, substantially improving the accuracy of the model in handling complex defects. Experimental evidence confirms the effectiveness of this method. Our SGNet achieved a 77.1% mAP on the NEU-DET dataset, demonstrating outstanding performance. © 2024 IEEE.

关键词： Surface defects

来源：评论

学校读者我要写书评

暂无评论

network link weight optimization based on antisymmetric deep graph networks and reinforcement learning 6

Network link weight optimization based on antisymmetric deep...

引用

6th International Conference on Next Generation Data-Driven networks, NGDN 2024

作者： Chen, Yuhan Guo, Yingya Department of Computer and Data Science Fuzhou University Fuzhou China Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou China

ISBN: (纸本)9798350388374

Route optimization is a key core technology to optimize network traffic distribution, achieve network load balancing, and improve network performance. Traditional distributed networks widely run shortest-path based routing protocols, and the path of traffic is determined by the link weights of the distributed network, so routing optimization methods are usually optimized around the link weights of the network. Heuristics-based link weight optimization methods are widely used. However, heuristic methods rely on manually set rules, which are poorly generalized and cannot adapt well to dynamically changing traffic demands. Compared to heuristics, deep reinforcement learning (DRL) has the advantage of extracting more accurate feature representations in addition to its ability to handle high-dimensional state and action spaces. We propose a network link weight optimization method based on anti-symmetric deep graph networks (A-DGN) and reinforcement learning using a novel GNN framework anti-symmetric deep graph networks, where link weights are adjusted to reduce the network link utilization with the optimization objective of minimizing the maximum link utilization in the network. Experimental results show that the proposed method achieves significant performance improvements in the link weight optimization problem in four real-world network topology scenarios. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Generalization analysis for multi-label learning 24

Generalization analysis for multi-label learning

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Yi-Fan Zhang Min-Ling Zhang School of Cyber Science and Engineering Southeast University Nanjing China and Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education China Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education China and School of Computer Science and Engineering Southeast University Nanjing China

Despite great advances in algorithms for multilabel learning, research on the theoretical analysis of generalization is still in the early stage. Some recent theoretical results has investigated the generalization performance of multi-label learning under several evaluation metrics, however, how to reduce the dependency on the number of labels, explicitly introduce label correlations, and quantitatively analyze the impact of various inductive biases in the generalization analysis of multi-label learning is still a crucial and open problem. In an attempt to make up for the gap in the generalization theory of multi-label learning, we develop several novel vector-contraction inequalities, which exploit the Lipschitz continuity of loss functions, and derive generalization bounds with a weaker dependency on the number of labels than the state of the art in the case of decoupling the relationship among different components, which serves as theoretical guarantees for the generalization of multilabel learning. In addition, we derive the generalization bound for Macro-Averaged AUC and analyze its relationship with class-imbalance. The mild bounds without strong assumptions explain the good generalization ability of multi-label learning with first-order label correlations and high-order label correlations induced by norm regularizers.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dual Radial-Resonant Wide Beamwidth Circular Sector Microstrip Patch Antennas

引用

Chinese Journal of Electronics 2023年第4期32卷 710-719页

作者： MAO Xiaohui LU Wenjun JI Feiyan XING Xiuqiong ZHU Lei Jiangsu Key Laboratory of Wireless Communications Nanjing University of Posts and Telecommunications Key Laboratory of Wireless Sensor Network & Communication Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences Department of Electrical and Computer Engineering Faculty of Science and Technology University of Macau

In this article, a design approach to a radial-resonant wide beamwidth circular sector patch antenna is advanced. As properly evolved from a U-shaped d ipole, a prototype magnetic dipole can be fit in the radial direction of a circular sector patch radiator, with its length set as the positive odd-integer multiples of onequarter wavelength. In this way, multiple TM0m（m = 1,2,...） modes resonant circular sector patch antenna with short-circuited circumference and widened E-plane beamwidth can be realized by proper excitation and perturbations. Prototype antennas are then designed and fabricated to validate the design approach. Experimental results reveal that the E-plane beamwidth of a dual-resonant antenna fabricated on air/Teflon substrate can be effectively broadened to 128°/120°, with an impedance bandwidth of 17.4%/7.1%, respectively. In both cases, the antenna heights are strictly limited to no more than 0.03-guided wavelength. It is evidently validated that the proposed approach can effectively enhance the operational bandwidth and beamwidth of a microstrip patch antenna while maintaining its inherent low profile merit.

关键词： Geometry Patch antennas Perturbation methods Prototypes Magnetic resonance Microstrip antennas Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Multi-label open set recognition 24

Multi-label open set recognition

引用

Proceedings of the 38th International Conference on Neural information Processing Systems

作者： Yi-Bo Wang Jun-Yi Hang Min-Ling Zhang School of Computer Science and Engineering Southeast University Nanjing China and Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education China

ISBN: (纸本)9798331314385

In multi-label learning, each training instance is associated with multiple labels simultaneously. Traditional multi-label learning studies primarily focus on closed set scenario, i.e. the class label set of test data is identical to those used in training phase. Nevertheless, in numerous real-world scenarios, the environment is open and dynamic where unknown labels may emerge gradually during testing. In this paper, the problem of multi-label open set recognition (MLOSR) is investigated, which poses significant challenges in classifying and recognizing instances with unknown labels in multi-label setting. To enable open set multi-label prediction, a novel approach named SLAN is proposed by leveraging sub-labeling information enriched by structural information in the feature space. Accordingly, unknown labels are recognized by differentiating the sub-labeling information from holistic supervision. Experimental results on various datasets validate the effectiveness of the proposed approach in dealing with the MLOSR problem.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Blockchain-Based Hierarchical Dynamic Collaborative Storage Model 10

A Blockchain-Based Hierarchical Dynamic Collaborative Storag...

引用

10th IEEE Smart World Congress, SWC 2024

作者： Yuan, Qile Liu, Xiangzhi Wang, Yu Dong, Yunfeng Jia, Haoyu Wu, Xiaoming Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Industrial Network and Information System Security Jinan China

ISBN: (纸本)9798331520861

The pervasive application of blockchain technology has led to a significant increase in data volume, presenting significant challenges to existing storage architectures in environments characterized by large volumes of data and highfrequency transactions. To enhance the scalability of blockchain, this study introduces an innovative framework, Hierarchical Dynamic Storage Management Chain Model, named HDSMC. The model consists of two stages. In the first phase of the model, when multimodal data files are uploaded, LBA techniques are employed to securely eliminate unnecessary redundancy, effectively preventing the storage of duplicate data. In the second phase, further processing is conducted on the generated blocks. This involves analyzing the frequency of block access to compute the variation in block 'heat'. Based on the Block Heat (BH), the number of replicas for each block across participating nodes is then determined. Furthermore, the framework implements an adaptive tiering strategy based on data access frequency and its importance, which facilitates the timely migration of data to an appropriate storage level. A simulated Hyperledger Fabric environment was employed to deploy the HDSMC framework and to assess its performance against current storage methodologies. The empirical outcomes indicated that this approach could achieve lower storage expenditures while ensuring high reliability. This research not only presents a novel strategy for blockchain storage management but also suggests potential applications for storage optimization in other big data scenarios. © 2024 IEEE.

关键词： Blockchain Data Sharding Hierarchical Storage Performance Optimization Scalability

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：