检索结果-内蒙古大学图书馆

7th International Conference on information Science and Control Engineering, ICISCE 2020

作者： Lu, Yan Cao, Xinrong Li, Zuoyong Wang, Tao Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Fuzhou350121 China Fuzhou Digital Healthcare Industry Technology Innovation Center Fuzhou350121 China

ISBN: (纸本)9781728164069

White blood cell (WBC, leukocyte) in blood smear image plays a crucial role in the diagnosis of many blood diseases. WBC segmentation is an important preprocessing step in blood disease diagnosis. However, due to some factors such as different dying technologies and different WBC appearances, WBC segmentation is still challenging. To improve accuracy of WBC segmentation, we propose an end-to-end WBC segmentation network. Specifically, we first introduce Dual Path Network (DPN) as a context-aware feature encoder to extract multi-scale image features. Then, we use a channel attention module to capture the interdependencies between channel maps, and further enhance feature representation capability of the proposed network. Finally, we reconstruct WBC feature maps by a feature decoder, and use skip connections to reduce image information loss. Experimental results on three datasets show that the proposed method obtains higher segmentation accuracy than the other methods. © 2020 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Cross-receptive Focused Inference Network for Lightweight Image Super-Resolution

arXiv

引用

arXiv 2022年

作者： Li, Wenjie Li, Juncheng Gao, Guangwei Deng, Weihong Zhou, Jiantao Yang, Jian Qi, Guo-Jun The Intelligent Visual Information Perception Laboratory Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing210046 China The Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou215006 China The School of Communication and Information Engineering Shanghai University Shanghai200444 China Jiangsu Key Laboratory of Image and Video Understanding for Social Safety Nanjing University of Science and Technology Nanjing210094 China The Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China The State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science Faculty of Science and Technology University of Macau 999078 China The School of Computer Science and Technology Nanjing University of Science and Technology Nanjing210094 China The Research Center for Industries of the Future The School of Engineering Westlake University Hangzhou310024 China OPPO Research SeattleWA98101 United States

Recently, Transformer-based methods have shown impressive performance in single image super-resolution (SISR) tasks due to the ability of global feature extraction. However, the capabilities of Transformers that need to incorporate contextual information to extract features dynamically are neglected. To address this issue, we propose a lightweight Cross-receptive Focused Inference Network (CFIN) that consists of a cascade of CT Blocks mixed with CNN and Transformer. Specifically, in the CT block, we first propose a CNN-based Cross-Scale information Aggregation Module (CIAM) to enable the model to better focus on potentially helpful information to improve the efficiency of the Transformer phase. Then, we design a novel Cross-receptive Field Guided Transformer (CFGT) to enable the selection of contextual information required for reconstruction by using a modulated convolutional kernel that understands the current semantic information and exploits the information interaction within different self-attention. Extensive experiments have shown that our proposed CFIN can effectively reconstruct images using contextual information, and it can strike a good balance between computational cost and model performance as an efficient model. Source codes will be available at https://***/IVIPLab/CFIN. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Magnetic plasmon resonances in nanostructured topological insulators for strongly enhanced light-MoS_(2) interactions

引用

Light(Science & Applications) 2020年第1期9卷 155-164页

作者： Hua Lu Zengji Yue Yangwu Li Yinan Zhang Mingwen Zhang Wei Zeng Xuetao Gan Dong Mao Fajun Xiao Ting Mei Weiyao Zhao Xiaolin Wang Min Gu Jianlin Zhao MOE Key Laboratory of Material Physics and Chemistry under Extraordinary Conditions and Shaanxi Key Laboratory of Optical Information TechnologySchool of Physical Science and TechnologyNorthwestern Polytechnical University710129 Xi’anChina Institute for Superconducting&Electronic Materials and ARC Centre of Excellence in Future Low-Energy Electronics University of WollongongNorth WollongongNSW 2500Australia Center for Artificial-Intelligence Nanophotonics School of Optical-Electrical and Computer EngineeringUniversity of Shanghai for Science and Technology200093 ShanghaiChina Guangdong Provincial Key Laboratory of Optical Fiber Sensing and Communications Institute of Photonics TechnologyJinan University510632 GuangzhouChina State Key Laboratory of Solidification Processing School of Materials Science and EngineeringNorthwestern Polytechnical University710072 Xi’anChina

Magnetic resonances not only play crucial roles in artificial magnetic materials but also offer a promising way for light control and interaction with ***,magnetic resonance effects have attracted special attention in plasmonic systems for overcoming magnetic response saturation at high frequencies and realizing high-performance optical *** novel states of matter,topological insulators(TIs)present topologically protected conducting surfaces and insulating bulks in a broad optical range,providing new building blocks for ***,until now,high-frequency(*** range)magnetic resonances and related applications have not been demonstrated in TI ***,we report for the first time,to our knowledge,a kind of visible range magnetic plasmon resonances(MPRs)in TI structures composed of nanofabricated Sb_(2)Te_(3) *** experimental results show that the MPR response can be tailored by adjusting the nanogroove height,width,and pitch,which agrees well with the simulations and theoretical ***,we innovatively integrated monolayer MoS_(2) onto a TI nanostructure and observed strongly reinforced light-MoS_(2) interactions induced by a significant MPR-induced electric field enhancement,remarkable compared with TI-based electric plasmon resonances(EPRs).The MoS_(2) photoluminescence can be flexibly tuned by controlling the incident light *** results enrich TI optical physics and applications in highly efficient optical functionalities as well as artificial magnetic materials at high frequencies.

关键词： topological resonance visible

来源：评论

学校读者我要写书评

暂无评论

DRL-M4MR: An Intelligent Multicast Routing Approach Based on DQN Deep Reinforcement Learning in SDN

arXiv

引用

arXiv 2022年

作者： Zhao, Chenwei Ye, Miao Xue, Xingsi Lv, Jianhui Jiang, Qiuxiang Wang, Yong School of Information and Communication Guilin University of Electronic Technology Guilin541004 China Guangxi Key Laboratory of Wireless Wideband Communication and Signal Processing Guilin University of Electronic Technology Guilin541004 China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fujian Fuzhou350118 China Peng Cheng Lab. Guangdong Shenzhen518038 China School of Computer Science and Information Security Guilin University of Electronic Technology Guilin541004 China

Traditional multicast routing methods have some problems in constructing a multicast tree, such as limited access to network state information, poor adaptability to dynamic and complex changes in the network, and inflexible data forwarding. To address these defects, the optimal multicast routing problem in software-defined networking (SDN) is tailored as a multi-objective optimization problem, and an intelligent multicast routing algorithm DRL-M4MR based on the deep Q network (DQN) deep reinforcement learning (DRL) method is designed to construct a multicast tree in SDN. First, the multicast tree state matrix, link bandwidth matrix, link delay matrix, and link packet loss rate matrix are designed as the state space of the DRL agent by combining the global view and control of the SDN. Second, the action space of the agent is all the links in the network, and the action selection strategy is designed to add the links to the current multicast tree under four cases. Third, single-step and final reward function forms are designed to guide the intelligence to make decisions to construct the optimal multicast tree. The experimental results show that, compared with existing algorithms, the multicast tree construct by DRL-M4MR can obtain better bandwidth, delay, and packet loss rate performance after training, and it can make more intelligent multicast routing decisions in a dynamic network environment. Copyright © 2022, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Advancing Cross-Subject Domain Generalization in Brain–computer Interfaces With Multiadversarial Strategies

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Liu, Yici Qin, Lang Chen, Xin Le Bouquin Jeannes, Regine Louis Coatrieux, Jean Shu, Huazhong Southeast University LIST Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing Ministry of Education Nanjing210096 China INSERM RennesF-3502 France The First Affiliated Hospital With Nanjing Medical University Department of Radiology Nanjing210029 China Laboratoire Traitement du Signal et de l’Image Universit de Rennes 1 Rennes35000 France Centre de Recherche en Information Biomedicale Sino-Francais Rennes35042 France National Institute for Health and Medical Research Rennes35000 France

A cross-subject domain generalization (DG) approach with multiadversarial strategies (DGMA) is introduced to reduce brain-computer interfaces (BCIs) systems' dependency on high-quality, subject-specific electroencephalographic (EEG) data, making it adaptable to unseen domains. DGMA leverages annotated training data from other subjects and consists of three modules: 1) prefeature extraction (PFE), enhancing EEG signal separability through preprocessing, data augmentation, and tangent space mapping;2) distribution feature updater (DFU), aligning intersubject feature distributions with marginal maximum mean discrepancy (MMD);and 3) multiadversarial training (MAT), initially using gradient reversal layer (GRL) to amplify domain differences and classification loss, allowing the model to learn diverse domain-specific features before minimizing these differences to balance domain transferability and discriminability. DGMA is capable of better capturing domain-specific features while achieving stronger generalization compared with traditional methods focused solely on minimizing domain differences. Validated on four motor imagery datasets, DGMA achieved state-of-the-art accuracies of 76.1% on BCI Competition IV 2a and 72.4% on the 002-2014 dataset. Additional tests on a private fatigue dataset and the SEED dataset yielded accuracies of 99.5% and 86.6%, respectively. © 1963-2012 IEEE.

关键词： Signal reconstruction

来源：评论

学校读者我要写书评

暂无评论

Modeling and Analysis of Pumping Cell of Nox Sensor - Part Ii: Nox Pumping Cell

SSRN

引用

SSRN 2022年

作者： Wang, Zhen Deng, Zhong-Hua Wang, Jie Lin, Wei-Xun Fu, Xiao-Wei Li, Xi School of Artificial Intelligence and Automation Key Laboratory of Imaging Processing and Intelligent Control Education Ministry Huazhong University of Science and Technology Hubei Wuhan430074 China Shenzhen Huazhong University of Science and Technology Research Institute Guangdong Shenzhen518055 China Lambda Company Jiangsu Changzhou213100 China College of Computer Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Hubei Wuhan430081 China

To improve the performance of the NOx sensor, a combined model based on the electrochemical model and the diffusion model is developed for the NOx pumping cell of the NOx sensor. Considering that a small amount of oxygen enters the third chamber and part of NO is decomposed in the second chamber, the electrochemical model simultaneously considers the reactions of NO and oxygen at cathode, and the diffusion model additionally considers the diffusion of oxygen and the decomposition of NO. To validate the model at different gas concentrations, the sensor is mounted on the designed test rig. Then, the simulation results are compared with experimental data from the test rig and good agreement is obtained. In addition, three key parameters of the model of the NOx pumping cell are analyzed. The values and changing trends of these three parameters are given in the paper. © 2022, The Authors. All rights reserved.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Image Dust Storm Synthetic Method Based on Optical Model 3rd

Image Dust Storm Synthetic Method Based on Optical Model

引用

3rd International Conference on Machine Learning for Cyber Security, ML4CS 2020

作者： Huang, Jiayan Li, Zuoyong Wang, Chuansheng College of Mathematics and Computer Science Fuzhou University Fuzhou350108 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Minjiang University Fuzhou350121 China School of Computer Science and Technology Harbin University of Science and Technology Harbin150080 China

ISBN: (纸本)9783030624620

To address the problem that the dusty image dataset is small and difficult to collect, this paper presents a synthetic method for generating dusty image based on a classical optical model. The proposed method first learns the physical process of generating dusty image according to the classical optical model. Then, the transmission map is estimated and combined with the presupposed dust storm color map as inputs for obtaining a synthetic dusty image. Finally, considering the impact of image scene depth on the synthesis of dusty image, the proposed method selects an appropriate value of input parameter to obtain final synthetic dusty image. Experimental results on an image dataset captured in clear weather show that the synthetic dusty images obtained by the proposed method can be used as a good substitute for real dusty images. © 2020, Springer Nature Switzerland AG.

关键词： Storms

来源：评论

学校读者我要写书评

暂无评论

An Anomalous Traffic Detection Approach for the Private Network Based on Self-learning Model 1

引用

3rd International Conference on Machine Learning for Cyber Security, ML4CS 2020

作者： Han, Weijie Xue, Jingfeng Zhang, Fuquan Zhang, Yingfeng School of Computer Science and Technology Beijing Institute of Technology Beijing China School of Space Information Space Engineering University Beijing China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China Equipment Development Department Beijing100071 China

ISBN: (数字)9783030622237

ISBN: (纸本)9783030622220

Although being isolated from the external network, the private network is still faced with some security threats, such as violations communications, malware attacks, and illegal operations. It is an attractive approach to recognize these security threats by discovering the underlying anomalous traffic. By studying the anomalous traffic detection technologies, an anomalous traffic detection approach is developed by capturing and analyzing the network packets, detecting the anomaly traffic that occurs in the network, and then detects anomalous behaviors of the network timely. In order to enhance its effectiveness and efficiency, a self-learning model is proposed and deployed in the detection approach. Finally, we conduct necessary evaluations about the proposed approach. The test results show that the approach can reach a good effect for detecting the unknown anomalous traffic. © 2020, Springer Nature Switzerland AG.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Occlusion Scene Classification via Cascade Supervised Contrastive Learning

TechRxiv

引用

TechRxiv 2022年

作者： Xu, Jianming Li, Yunfei He, Li Li, Jun The Guangdong Provincial Key Laboratory of Urbanization and Geosimulation Center of Integrated Geographic Information Analysis School of Geography and Planning Sun Yatsen University Guangzhou510275 China The School of Computer Science China University of Geosciences Wuhan430078 China The Hubei Key Laboratory of Intelligent Geo-Information Processing China University of Geosciences Wuhan430078 China The School of Automation Science and Engineering South China University of Technology Guangzhou510640 China

Recent occlusion scene classification focuses on extracting occlusion-invariant features by considering class separability, unsupervised learning, and generalization ability, separately. Considering them together is profitable to address real-world occlusion problem. In this work, we propose cascade supervised contrastive learning to accommodate those considerations simultaneously. First, the pretext task uses rectangles to occlude the original images. Second, we use the siamese residual network to extract the features of original images, and pretext task augmented images. Third, compute the cascade supervised contrastive loss of the intermediate layers and final layer of the network. By optimizing the cascade supervised contrastive loss, the network can learn pretext-task invariant features. Besides, the pretext task-invariant features can adapt to the downstream occlusion-invariant feature extraction task due to the outstanding generalization ability of contrastive learning. Finally, a multilayer perceptron is used to perform scene classification on the extracted features. The proposed method is validated on two simulated datasets and tends to achieve performance improvement compared with typical unsupervised occlusion scene classification methods. The first application of contrastive learning for remote sensing image occlusion scene classification is the innovative contribution of this paper. This method can achieve accurate remote sensing scene classification with any degree and type of occlusion. © 2022, CC BY-NC-SA.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Efficiently Retrieving Differences between Remote Sets using Counting Bloom Filter

引用

International Journal of Performability Engineering 2019年第7期15卷 1947-1954页

作者： Tian, Xiaomei Zhao, Huihuang Sun, Yaqi Liang, Xiaoman College of Computer Science and Technology Hengyang Normal University Hengyang421002 China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang421002 China

Retrieving differences between remote sets is widely used in set reconciliation and data deduplication. Set reconciliation and data deduplication between two nodes are widely used in various network applications. The basic idea of the difference retrieving problem is that each member of a node pair has an object set and seeks to find all differences between the two remote sets. There are many methods for retrieving difference sets, such as the standard Bloom filter (SBF), counting Bloom filter (CBF), and invertible Bloom filter (IBF). In these methods, based on the standard Bloom filter or its variants, each node represents its objects using a standard Bloom filter or other Bloom filter, which is then exchanged. A receiving node retrieves different objects between the two sets according to the received SBF, CBF, or IBF. We propose a new algorithm for retrieving differences that finds differences between remote sets using counting Bloom filters' deletion operation. The theoretical analyses and experimental results show that the differences can be retrieved efficiently. Only a very small number of differences are missing in the retrieving process, and this false negative rate can be decreased to 0% by adjusting the counting Bloom filter's parameters. © 2019 Totem Publisher, Inc. All rights reserved.

关键词： Data structures

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：