检索结果-内蒙古大学图书馆

14th International Conference on Bio-inspired computing: Theories and Applications, BIC-TA 2019

作者： Li, Wei Fan, Yaochi Jiang, Qiaoyong School of Computer Science and Engineering Xi’an University of Technology Xi’an710048 China Shaanxi Key Laboratory for Network Computing and Security Technology Xi’an710048 China

ISBN: (纸本)9789811534249

Due to the fact that many realistic problems are multimodal optimization problems (MMOPs), multimodal optimization has attracted a growing interest. In this paper, a Species-based differential evolution with migration algorithm is proposed for MMOPs. First, a migration strategy is developed to improve the exploration ability of species with less individuals. Then, an improved operation of creating local individuals is introduced to help the algorithm to find high-quality solutions. Finally, an archive mechanism is applied to preserve the best solutions found during previous generations and avoid the loss of the peaks. Experimental results on CEC2013 test problems confirm the effectiveness of the proposed algorithm compared to several well-known multimodal optimization algorithms. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Feature Aggregation network for Memory-Based Industrial Anomaly Detection

Feature Aggregation Network for Memory-Based Industrial Anom...

引用

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Min Li Delong Han Rui Shao Jinghui He Faculty of Data Science City University of Macau China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China 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 Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350391367

ISBN: (纸本)9798350391374

In the process of large-scale industrial production, complex defects of different shapes and sizes can occur in industrial products and their components, and these defects seriously affect the performance of industrial products and their components, and being able to quickly and accurately identify defective industrial products and their components is an important task. Memory-based methods are usually used for anomaly detection, and these methods often rely on pre-trained models for feature extraction, but have high requirements on feature quality. In addition, patch-based methods mainly focus on local differences in feature embedding when detecting anomalies without explicitly exploiting broader contextual information, thus greatly affecting the robustness and accuracy of anomaly detection. Aiming at the above problems and requirements, this paper proposes a Feature Aggregation network for Memory-Based Industrial Anomaly Detection (FANet), which is based on the pre-extraction of anomalous features, attentional attention to key features, information aggregation of multi-level and multi-scale features, and the FANet provides advanced performance in industrial image anomaly detection and localisation by pre-extraction of anomalous features, attentional attention to key features, information aggregation of multi-layered and multi-scale features, and introduction of environmental information in the anomaly score computation to perform industrial anomaly detection tasks, and using core set subsampling to reduce storage requirements. On the MVTec AD, FANet has an image-level AUROC score of 99.1% and a pixel-level AUROC score of 98.2%. Similarly high detection results were achieved on the ViSA dataset, further demonstrating the robustness of FANet.

关键词： Training Runtime Shape Memory management Training data Production Feature extraction Robustness Anomaly detection Testing

来源：评论

学校读者我要写书评

暂无评论

FAST: a dual-tier few-shot learning paradigm for whole slide image classification 24

FAST: a dual-tier few-shot learning paradigm for whole slide...

引用

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

作者： Kexue Fu Xiaoyuan Luo Linhao Qu Shuo Wang Ying Xiong Ilias Maglogiannis Longxiang Gao Manning 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 and Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China Digital Medical Research Center School of Basic Medical Sciences Fudan University and Shanghai Key Lab of Medical Image Computing and Computer Assisted Intervention Fudan University University of Piraeus

ISBN: (纸本)9798331314385

The expensive fine-grained annotation and data scarcity have become the primary obstacles for the widespread adoption of deep learning-based Whole Slide Images (WSI) classification algorithms in clinical practice. Unlike few-shot learning methods in natural images that can leverage the labels of each image, existing few-shot WSI classification methods only utilize a small number of fine-grained labels or weakly supervised slide labels for training in order to avoid expensive fine-grained annotation. They lack sufficient mining of available WSIs, severely limiting WSI classification performance. To address the above issues, we propose a novel and efficient dual-tier few-shot learning paradigm for WSI classification, named FAST. FAST consists of a dual-level annotation strategy and a dual-branch classification framework. Firstly, to avoid expensive fine-grained annotation, we collect a very small number of WSIs at the slide level, and annotate an extremely small number of patches. Then, to fully mining the available WSIs, we use all the patches and available patch labels to build a cache branch, which utilizes the labeled patches to learn the labels of unlabeled patches and through knowledge retrieval for patch classification. In addition to the cache branch, we also construct a prior branch that includes learnable prompt vectors, using the text encoder of visual-language models for patch classification. Finally, we integrate the results from both branches to achieve WSI classification. Extensive experiments on binary and multi-class datasets demonstrate that our proposed method significantly surpasses existing few-shot classification methods and approaches the accuracy of fully supervised methods with only 0.22% annotation costs. All codes and models will be publicly available on https://***/fukexue/FAST.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Routing Mutation Mechanism based on Mutation Cost and Resource Trustworthiness in network Moving Target Defense 7

A Hybrid Routing Mutation Mechanism based on Mutation Cost a...

引用

7th IEEE International Conference on Data Science in Cyberspace, DSC 2022

作者： Guo, Kun Gao, Yibo Wang, Dongbin Zhi, Hui Zhang, Tao Lu, Yueming Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education Beijing University of Posts and Telecommunications Beijing China Beijing University of Posts and Telecommunications Cyberspace Security Research Center Peng Cheng Laboratory Beijing China Beijing University of Posts and Telecommunications National Engineering Laboratory for Mobile Network Beijing China TravelSky Technology Limited Beijing China China Academy of Launch Vehicle Technology Beijing China

ISBN: (数字)9781665474801

ISBN: (纸本)9781665474801

network moving target defense technology can effectively defend against attacker monitoring of the service. The technology makes it more difficult for attackers to attack and can ensure secure communication for services. However, there may be multiple network attacks in the network. As a result, there may be security problems with the trustworthiness of the network resource mutation space required for network moving target defense technology. The focus of current researches is mostly on the mutation timing and cost optimization of the resource mutation space. It may lead to the possibility that the resources in the resource mutation space have been already under network attacks. In this paper, we propose a hybrid routing mutation mechanism based on mutation cost and resource trustworthiness in SDN networks. The mechanism is able to evaluate the routing mutation space selected by the routing-based network moving target defense technology. In terms of both mutation cost and resource trustworthiness, the optimal weighting ratio of the two factors will be to discovered. Simulation results show that the proposed mechanism can effectively enhance the ability of the routing mutation space to avoid attacked nodes and links and improve the transmission success rate of services. © 2022 IEEE.

关键词： network routing

来源：评论

学校读者我要写书评

暂无评论

A Threshold-Free Random Access Preamble Detection Method Based on Joint Clustering for 6G NTN

A Threshold-Free Random Access Preamble Detection Method Bas...

引用

2021 IEEE Globecom Workshops, GC Wkshps 2021

作者： Zhen, Li Wang, Yue Sun, Teng Wang, Wenjing Yu, Keping Kharel, Rupak Xi'An University of Posts and Telecommunications Shaanxi Key Laboratory of Information Communication Network and Security Xi'an China Global Information and Telecommunication Institute Waseda University Tokyo Japan Manchester Metropolitan University Department of Computing and Mathematics United Kingdom

ISBN: (纸本)9781665423908

Thanks to its irreplaceable superiority in providing seamless coverage, satellite communication is expected to play an important role in supporting ubiquitous and continuous connectivity services for 6G wireless networks. With the pre-compensation of timing and frequency offset, we propose a novel random access (RA) preamble detection method for the high-dynamic non-terrestrial networks (NTN). Unlike the conventional threshold-based methods, the proposed method leverages a joint clustering algorithm to accurately capture the timing position corresponding to the first arrival path without noise variance estimation. Simulation results validate the effectiveness of the proposed method in a typical satellite non line-of-sight (NLOS) scenario, and indicate that our method can achieve a notable performance enhancement in terms of the error detection probability (EDP) and the timing mean square error (MSE), in comparison to the exiting methods. © 2021 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Improved YOLOv5 Object Detection Method for Cervical Fluid Cell Pathological Image Detection

Improved YOLOv5 Object Detection Method for Cervical Fluid C...

引用

International Joint Conference on Neural networks (IJCNN)

作者： Qingyan Ding Xuecheng Dong Na Li Yu Pan Wan Zheng Dept. 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 Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Cervical liquid-based cell pathology image detection and recognition is a key task in gynecological pathology aimed at early detection of cervical precancerous lesions. In this study, a deep learning based method is proposed for the detection and recognition of cervical liquid-based cell images. This paper is based on the YOLOv5 network model for improvement. Firstly, in the data preprocessing stage: for the characteristics of the dataset, this paper proposes two data enhancement methods to augment the training dataset; secondly, the Transformer module for local information enhancement is improved by introducing a local attention mechanism, which restricts each position to only pay attention to positions within a certain range around it; then, the spatial pyramid pooling module (DSPPCSPC) is improved, and the spatial Pyramid Pooling Module (DSPPC-SPC), introducing deformable mask of deformable convolution (ODConv); then, this paper proposes a new Attention Module (XCAttention), improving S2Attention to focus on the local information of the image, and introducing its Channel Attention Module into the third branch, which performs the Dot with the first and the second branches that have gone through Spatial-shift to obtain the final output. Product operation to get the final output. Through experiments, this paper’s algorithm improves in Precision, Recall, mAP50, and mAP50-95 metrics by 1.9%, 1.9%, 2%, and 1.2%, respectively. The experimental results show that this paper’s algorithm can effectively improve the detection performance of the model.

关键词： YOLO Training Deep learning Pathology Technological innovation Image recognition Convolution

来源：评论

学校读者我要写书评

暂无评论

Trust Evaluation Model of Social Internet of Things Based on Multi-relationships

Trust Evaluation Model of Social Internet of Things Based on...

引用

2022 International Conference on networking and network Applications, NaNA 2022

作者： Fan, Fan Zhang, Hongbin Zhao, Dongmei Wang, Yanxia Liu, Bin Liu, Jian Hebei University of Science and Technology School of Information Science and Engineering Shijiazhuang China Hebei Normal University Hebei Key Laboratory of Network and Information Security Shijiazhuang China Hebei Geological Workers' University Shijiazhuang China Hebei University of Science and Technology School of Economics and Management Research Center of Big Data and Social Computing Shijiazhuang China

ISBN: (数字)9781665461313

ISBN: (纸本)9781665461313

Trust plays a vital role in ensuring the security of the Social Internet of Things. Due to the increased mobility of intelligent devices, there are frequent interactions between machines and changes in social relationships. It leads to a possible data sparsity problem in the Social Internet of Things. Therefore, it is presented that the trust evaluation model is based on various social relationships. The model considers the impact of multiple dynamically changing social relationships between nodes on trust. The implicit social relationship is mined based on the stated social relationship and potential attributes connecting nodes. It addresses the scarcity issue and the slow start of the Social Internet of Things. Simulations on the Santander Smart Cities dataset demonstrate that the approach improves the accuracy and convergence of trust evaluation in both sparse and regular networks. © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Task Offloading and Primary Node Selection in Blockchain, Digital Twin, and MEC Enabled Internet of Vehicles 100

Task Offloading and Primary Node Selection in Blockchain, Di...

引用

100th IEEE Vehicular technology Conference, VTC 2024-Fall

作者： Du, Jianbo Fang, Huifang Li, Shulei Du, Pengfei Kong, Ziwen Kang, Jiawen Niyato, Dusit Xi'an University of Posts and Telecommunications Shaanxi Key Laboratory of Information Communication Network and Security School of Communications and Information Engineering Xi'an China Xidian University School of Communications Engineering Xi'an710071 China Tianyuan Ruixin Communication Technology Co. LTD. Xi'an710071 China Xihua University Engineering Research Center of Intelligent Airground Integrated Vehicle and Traffic Control Ministry of Education Chengdu610039 China Guangdong University of Technology School of Automation China Nanyang Technological University School of Computer Science and Engineering Singapore

ISBN: (纸本)9798331517786

In this paper, we investigate the safe task offloading and primary node selection in blockchain, digital twin (DT) and Multi-access Edge computing (MEC) enabled Internet of Vehicles (IoV). Edge servers centers provide computing power for task processing for Mobile Vehicles (MVs), while blockchain can provide security guarantees for MVs during task offloading. Based on the above system, we propose a joint optimization scheme for vehicle task offloading decision and the Practical Byzantine Fault Tolerance (PBFT) consensus process. Due to the large number of optimization variables and constraints, the problem becomes more complex. Traditional convex optimization and dynamic programming methods are difficult to effectively solve this problem. To address this issue, we propose a deep reinforcement learning based algorithm that utilizes Proximal Policy Optimization (PPO). The experimental results show that the algorithm proposed in this paper outperforms the benchmark algorithm in terms of convergence and other aspects. © 2024 IEEE.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Few-shot Open Relation Extraction with Gaussian Prototype and Adaptive Margin

arXiv

引用

arXiv 2024年

作者： Guo, Tianlin Zhang, Lingling Wang, Jiaxin Lei, Yunkuo Li, Yifei Wang, Haofen Liu, Jun School of Computer Science and Technology Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi'an Jiaotong University Xi’an710049 China School of Computer Science and Technology Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Xi’an710049 China College of Design and Innovation Tongji University Shanghai200092 China

Few-shot relation extraction with none-of-the-above (FsRE with NOTA) aims at predicting labels in few-shot scenarios with unknown classes. FsRE with NOTA is more challenging than the conventional few-shot relation extraction task, since the boundaries of unknown classes are complex and difficult to learn. Meta-learning based methods, especially prototype-based methods, are the mainstream solutions to this task. They obtain the classification boundary by learning the sample distribution of each class. However, their performance is limited because few-shot overfitting and NOTA boundary confusion lead to misclassification between known and unknown classes. To this end, we propose a novel framework based on Gaussian prototype and adaptive margin named GPAM for FsRE with NOTA, which includes three modules, semi-factual representation, GMM-prototype metric learning and decision boundary learning. The first two modules obtain better representations to solve the few-shot problem through debiased information enhancement and Gaussian space distance measurement. The third module learns more accurate classification boundaries and prototypes through adaptive margin and negative sampling. In the training procedure of GPAM, we use contrastive learning loss to comprehensively consider the effects of range and margin on the classification of known and unknown classes to ensure the model's stability and robustness. Sufficient experiments and ablations on the FewRel dataset show that GPAM surpasses previous prototype methods and achieves state-of-the-art performance. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

An Auto-Parallel Method for Deep Learning Models Based on Genetic Algorithm 29

An Auto-Parallel Method for Deep Learning Models Based on Ge...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Zeng, Yan Huang, Chengchuang Ni, Yijie Zhou, Chunbao Zhang, Jilin Wang, Jue Zhou, Mingyao Xue, Meiting Zhang, Yunquan Hangzhou Dianzi University School of Computer Science and Technology Hangzhou310018 China Ministry of Education Key Laboratory for Modeling and Simulation of Complex Systems Hangzhou310018 China Data Security Governance Zhejiang Engineering Research Center Hangzhou310018 China Hangzhou Dianzi University School of ITMO Joint Institute Hangzhou310018 China Institute of Computer Network Information Center of the Chinese Academy of Sciences Beijing100086 China HuaWei China Institute of Computing Technology of the Chinese Academy of Sciences State Key Laboratory of Computer Architecture Beijing100086 China

ISBN: (纸本)9798350330717

As the size of datasets and neural network models increases, automatic parallelization methods for models have become a research hotspot in recent years. The existing auto-parallel methods based on machine learning or graph algorithms still have issues with search efficiency and applicability. This paper proposes an automatic parallel method based on a dual-population genetic algorithm, TGA, which transforms model partitioning and placement into an integer linear programming problem and constructs a cost model to evaluate the solution. The solution space is built using the neural network's dataflow graph and device cluster's topology, and the dual-population genetic algorithm is used to search for the optimal model parallel strategy. Experiments with various models show that the proposed method can improve single-step execution time by up to 42% compared to the Baechi method and up to 37.7% compared to the Hierarchical method. © 2023 IEEE.

关键词： Auto-Parallel Distributed machine learning Genetic algorithm Integer linear programming Model parallelism

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：