检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Zhang, Zhe Ma, Shiyao Nie, Jiangtian Wu, Yi Yan, Qiang Xu, Xiaoke Niyato, Dusit School of Data Science and Technology Heilongjiang University Harbin150080 China Cryptology and Network Security Laboratory of Heilongjiang University Harbin150080 China College of Information and Communication Engineering Dalian Minzu University School of Computer Science and Engineering Nanyang Technological University WeBank Co. Ltd. China

Federated Learning (FL) allows edge devices (or clients) to keep data locally while simultaneously training a shared high-quality global model. However, current research is generally based on an assumption that the training data of local clients have ground-truth. Furthermore, FL faces the challenge of statistical heterogeneity, i.e., the distribution of the client’s local training data is non-independent identically distributed (non-IID). In this paper, we present a robust semi-supervised FL system design, where the system aims to solve the problem of data availability and non-IID in FL. In particular, this paper focuses on studying the labels-at-server scenario where there is only a limited amount of labeled data on the server and only unlabeled data on the clients. In our system design, we propose a novel method to tackle the problems, which we refer to as Federated Mixing (FedMix). FedMix improves the naive combination of FL and semi-supervised learning methods and designs parameter decomposition strategies for disjointed learning of labeled, unlabeled data, and global models. To alleviate the non-IID problem, we propose a novel aggregation rule based on the frequency of the client’s participation in training, namely the FedFreq aggregation algorithm, which can adjust the weight of the corresponding local model according to this frequency. Extensive evaluations conducted on CIFAR-10 dataset show that the performance of our proposed method is significantly better than those of the current baseline. It is worth noting that our system is robust to different non-IID levels of client data. Index Terms—Federated Learning, Semi-supervised Learning, non-IID, Aggregation Algorithm. Copyright © 2021, The Authors. All rights reserved.

关键词： Systems analysis

来源：评论

学校读者我要写书评

暂无评论

Yu-Transnet: A Cnn-Transformer-Based Hybrid U-Shape Structure for Esophagus 3d Ct Image Gross Tumor Volume Segmentation

SSRN

引用

SSRN 2024年

作者： Yu, Songli Li, Yunxiang Jiao, Pengfei Liu, Yixiu Zhao, Jianxiang Yan, Chenggang Wang, Qifeng Wang, Shuai School of Mechanical Electrical and Information Engineering Shandong University Weihai264209 China Department of Radiation Oncology UT Southwestern Medical Center Dallas75390 United States School of Cyberspace Security Hangzhou Dianzi University Hangzhou310018 China Intelligent Information Processing Laboratory Hangzhou Dianzi University Hangzhou310018 China School of Communication Engineering Hangzhou Dianzi University Hangzhou310018 China Department of Radiation Oncology Sichuan Cancer Hospital and Institution Chengdu610000 China Sichuan Cancer Center Chengdu610000 China School of Medicine University of Electronic Science and Technology of China Chengdu610000 China Radiation Oncology Key Laboratory of Sichuan Province Chengdu610000 China Suzhou Research Institute of Shandong University Suzhou215123 China Lishui Institute of Hangzhou Dianzi University Lishui323010 China

Accurate and reliable segmentation of esophageal gross tumor volume (GTV) in computed tomography (CT) is beneficial for diagnosing and treating. However, this remains a challenging task because the esophagus has a variable shape and extensive vertical range, resulting in tumors potentially appearing at any position within it. In this paper, we propose a novel CNN-Transformer-based U-shape structure to improve the segmentation accuracy of esophageal GTV. Specifically, we propose a long-range relay mechanism to converge all layer feature information by progressively passing adjacent layer feature maps in the pixel and semantic pathways. Moreover, we introduce two ready-to-use blocks to implement this mechanism concretely. The Dual FastViT block interacts with feature maps from two paths to enhance feature representation capabilities. The Dual AxialViT block acts as a secondary auxiliary bottleneck to acquire global information for more precise feature map reconstruction. We build a new esophageal tumor dataset with 1665 real-world patient CT samples annotated by five expert radiologists and employ multiple evaluation metrics to validate our model. The results demonstrate that our model outperforms the state-of-the-art models. It is of great significance to improve the accuracy and clinical application of esophageal tumor segmentation. © 2024, The Authors. All rights reserved.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

A Temporal-Spatial Spectrum Prediction Based on Homotopy Theory for UAVs with Arbitrary Flight Paths

A Temporal-Spatial Spectrum Prediction Based on Homotopy The...

引用

International Conference on communication technology (ICCT)

作者： Wenjun Zhou Shan Luo Yuwei Zhao Rongping Lin School of Aeronautics and Astronautics University of Electronic Science and Technology of China (UESTC) Chengdu China Aircraft Swarm Intelligent Sensing and Cooperative Control Key Laboratory of Sichuan Province UESTC Chengdu China School of Information and Communication Engineering UESTC Chengdu China

ISBN: (纸本)9781665432078

The higher demand for wireless communication services has promoted the widespread use of unmanned aerial vehicles (UAVs), but the spectrum resources for UAVs communication are becoming scarce. UAVs can use spectrum prediction to find available frequency bands and share spectrum with other users to solve the problem of spectrum resources shortage. However, due to the rapid speed of UAVs and constantly changing spectral environment, it is difficult to obtain the historical data of the next location in advance. Therefore, the existing methods cannot be well applied to the actual scenario of UVA flying randomly in a certain area. Based on the concept of homotopy theory (HT) and Hidden Markov model (HMM), we propose a new method that first estimates the historical information of the next location, then performs the spectrum prediction at the next moment. We conduct experiments with simulated data, and the results show that the proposed method can effectively predict the spectrum state of UAV flying in a specific area on the premise of obtaining the prior information of limited locations.

关键词： Wireless communication Conferences Hidden Markov models Predictive models Markov processes Autonomous aerial vehicles communications technology

来源：评论

学校读者我要写书评

暂无评论

A MAC Protocol Identification Approach Based on Convolutional Neural Network

A MAC Protocol Identification Approach Based on Convolutiona...

引用

International Conference on Wireless communications and Signal Processing (WCSP)

作者： Xutong Zhang Weiguo Shen Jianliang Xu Zitong Liu Guoru Ding Colledge of Electronic and Information Engineering Nanjing University of Aeronautics and Astronautics Nanjing China Key Laboratory of Dynamic Cognitive System of Electromagnetic Spectrum Space Ministry of Industry and Information Technology Science and Technology on Communication Information Security Control Laboratory No.36 Research Institute of CETC Jiaxing China College of Communication Engineering Army Engineering University Nanjing China

ISBN: (数字)9781728172361

ISBN: (纸本)9781728172378

The medium access control (MAC) protocol identification is of great application value in cognitive radio. In order to realize the MAC protocol identification with high accuracy and avoid manual feature extraction, we convert the sampled data into the form of spectrogram. Then, a graphical scheme which combines the convolutional neural network (CNN) and the spectrogram is proposed. The simulation includes CNN method and support vector machine (SVM) method. It is suggested that the CNN method has better identification performance.

关键词： Media Access Protocol Spectrogram Protocols Support vector machines Time division multiple access Feature extraction Cognitive radio

来源：评论

学校读者我要写书评

暂无评论

Observing movement of Dirac cones from single-photon dynamics

引用

Physical Review B 2021年第6期103卷 064304-064304页

作者： Yong-Heng Lu Yao Wang Yi-Jun Chang Zhan-Ming Li Wen-Hao Cui Jun Gao Wen-Hao Zhou Hang Zheng Xian-Min Jin Center for Integrated Quantum Information Technologies (IQIT) School of Physics and Astronomy and State Key Laboratory of Advanced Optical Communication Systems and Networks Shanghai Jiao Tong University Shanghai 200240 China CAS Center for Excellence and Synergetic Innovation Center in Quantum Information and Quantum Physics University of Science and Technology of China Hefei Anhui 230026 China Laboratory of Artificial Structures and Quantum Control (Ministry of Education) School of Physics and Astronomy Shanghai Jiao Tong University Shanghai 200240 China

Graphene with honeycomb structure, critically important in understanding physics of matter, exhibits exceptionally unusual half-integer quantum Hall effect and unconventional electronic spectrum with quantum relativistic phenomena. Particularly, graphenelike structure can be used for realizing topological insulator which inspires an intrinsic topological protection mechanism with strong immunity for maintaining coherence of quantum information. These various peculiar physics arise from the unique properties of Dirac cones which show high hole degeneracy, massless charge carriers, and linear intersection of bands. Experimental observation of Dirac cones conventionally focuses on the energy-momentum space with bulk measurement. Here, we demonstrate a direct observation of the movement of Dirac cones from single-photon dynamics in photonic graphene under different biaxial strains. Sharing the same spirit of wave-particle nature in quantum mechanics, we identify the movement of Dirac cones by dynamically detecting the edge modes and extracting the diffusing distance of the packets with accumulation and statistics on individual single-particle registrations. Our results of observing movement of Dirac cones from single-photon dynamics, together with the method of direct observation in real space by mapping the band structure defined in momentum space, paves a novel way to understand and explore a variety of artificial structures.

关键词： Phase transitions Quantum optics Topological phases of matter Graphene

来源：评论

学校读者我要写书评

暂无评论

EDMAE: An Efficient Decoupled Masked Autoencoder for Standard View Identification in Pediatric Echocardiography

arXiv

引用

arXiv 2023年

作者： Liu, Yiman Han, Xiaoxiang Liang, Tongtong Dong, Bin Yuan, Jiajun Hu, Menghan Liu, Qiaohong Chen, Jiangang Li, Qingli Zhang, Yuqi Department of Pediatric Cardiology Shanghai Children's Medical Center School of Medicine Shanghai Jiao Tong University Shanghai200127 China Shanghai200127 China Shanghai Key Laboratory of Multidimensional Information Processing School of Communication and Electronic Engineering East China Normal University Shanghai200241 China School of Health Science and Engineering University of Shanghai for Science and Technology Shanghai200093 China Shanghai Minhang Center for Disease Control and Prevention Shanghai201101 China School of Medical Instruments Shanghai University of Medicine and Health Sciences Shanghai201318 China

This paper introduces the Efficient Decoupled Masked Autoencoder (EDMAE), a novel self-supervised method for recognizing standard views in pediatric echocardiography. EDMAE introduces a new proxy task based on the encoderdecoder structure. The EDMAE encoder is composed of a teacher and a student encoder. The teacher encoder extracts the potential representation of the masked image blocks, while the student encoder extracts the potential representation of the visible image blocks. The loss is calculated between the feature maps output by the two encoders to ensure consistency in the latent representations they extract. EDMAE uses pure convolution operations instead of the ViT structure in the MAE encoder. This improves training efficiency and convergence speed. EDMAE is pre-trained on a large-scale private dataset of pediatric echocardiography using self-supervised learning, and then fine-tuned for standard view recognition. The proposed method achieves high classification accuracy in 27 standard views of pediatric echocardiography. To further verify the effectiveness of the proposed method, the authors perform another downstream task of cardiac ultrasound segmentation on the public dataset CAMUS. The experimental results demonstrate that the proposed method outperforms some popular supervised and recent self-supervised methods, and is more competitive on different downstream tasks. Copyright © 2023, The Authors. All rights reserved.

关键词： Pediatrics

来源：评论

学校读者我要写书评

暂无评论

Visual Text Processing: A Comprehensive Review and Unified Evaluation

arXiv

引用

arXiv 2025年

作者： Shu, Yan Zeng, Weichao Zhao, Fangmin Chen, Zeyu Li, Zhenhang Yang, Xiaomeng Zhou, Yu Rota, Paolo Bai, Xiang Jin, Lianwen Yin, Xu-Cheng Sebe, Nicu VCIP & TMCC & DISSec College of Computer Science Nankai University China Department of Information Engineering and Computer Science University of Trento Italy Institute of Information Engineering Chinese Academy of Sciences China School of Cyber Security University of Chinese Academy of Sciences China Department of Electrical and Computer Engineering Northeastern University United States School of Software Engineering Huazhong University of Science and Technology China School of Electronic and Information Engineering South China University of Technology China Department of Computer Science and Technology The Beijing Key Laboratory of Materials Science Knowledge Engineering School of Computer and Communication Engineering University of Science and Technology Beijing China

Visual text is a crucial component in both document and scene images, conveying rich semantic information and attracting significant attention in the computer vision community. Beyond traditional tasks such as text detection and recognition, visual text processing has witnessed rapid advancements driven by the emergence of foundation models, including text image reconstruction and text image manipulation. Despite significant progress, challenges remain due to the unique properties that differentiate text from general objects. Effectively capturing and leveraging these distinct textual characteristics is essential for developing robust visual text processing models. In this survey, we present a comprehensive, multi-perspective analysis of recent advancements in visual text processing, focusing on two key questions: (1) What textual features are most suitable for different visual text processing tasks? (2) How can these distinctive text features be effectively incorporated into processing frameworks? Furthermore, we introduce VTPBench, a new benchmark that encompasses a broad range of visual text processing datasets. Leveraging the advanced visual quality assessment capabilities of multimodal large language models (MLLMs), we propose VTPScore, a novel evaluation metric designed to ensure fair and reliable evaluation. Our empirical study with more than 20 specific models reveals substantial room for improvement in the current techniques. Our aim is to establish this work as a fundamental resource that fosters future exploration and innovation in the dynamic field of visual text processing. The relevant repository is available at https://***/shuyansy/Visual-Text-Processing-survey. Copyright © 2025, The Authors. All rights reserved.

关键词： Text mining

来源：评论

学校读者我要写书评

暂无评论

Retinal Disorder Diagnosis Based on Hybrid Deep Learning Models

SSRN

引用

SSRN 2022年

作者： Sedik, Ahmed El-Hag, Noha A. El-Hoseny, Heba M. El-Banby, Ghada M. Khalaf, Ashraf A.M. Abd El-Samie, Fathi E. El-Shafai, Walid Department of the Robotics and Intelligent Machines Faculty of Artificial Intelligence Kafrelsheikh University Egypt Menoufia University Egypt Department of Electronics and Electrical Communication Engineering Al-Obour High Institute for Engineering and Technology Egypt Department of Industrial Electronics and Control Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Deptartment of Electronics and Electrical Communication Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University Riyadh84428 Saudi Arabia Security Engineering Lab Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia

Anomaly detection from medical images is badly needed for automated diagnosis. For example, medical images obtainedwith several modalities such as magnetic resonance (MR) and confocal microscopy need to be classified for anomaly *** MR images may contain tumors that need to be detected with anomaly detection techniques. In MR imaging, braintumors are represented as areas composed of abnormal cells that need to be detected. In addition, confocal microscopy can be used for retinal imaging. Hence, there is a need to apply classification techniques for diagnosing diseases of the eye such as Diabetic Retinopathy (DR), which leads to exudates in different regions of the retina. The detection of exudates is necessary for the diagnosis of DR. In this paper, two models are presented for the classification of MR and retinal images. Much research has been done in this area, but it did not achieve high accuracy of classification in an acceptable time. In addition, the previous models did not consider both types of image modalities considered in this paper. The suggested models are Convolutional Neural Network (CNN) and Convolutional Long Short-Term Memory (Conv-LSTM). They are used to classify © 2022, The Authors. All rights reserved.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

Congestion control of Multi-layer Cellular Networks based on Modeling of Transmit Power

引用

Journal of Physics: Conference Series 2021年第1期1746卷

作者： Jiahao Dai Yongqun Chen Yucheng Chen Aodong Meng Science and Technology on Communication Information Security Control Laboratory China Electronic Group Corporation NO.36 Institute Zhejiang Jiaxing China

The explosive growth of network traffic and the limited storage node resources make the existing network architecture bear great pressure, and network congestion appears in work and life from time to time. In order to ensure the timeliness and effectiveness of the network, we propose a congestion control method based on transmission power. Different from previous work, we built a multi-layer cellular network consisting of multiple macro stations, small base stations and mobile terminals. On this basis, we establish a congestion control model based on the mixed queuing model of service window and calculate the input/output rate and congestion. Finally, we use simulation to verify the effectiveness of the congestion model. The network builder can use our model to set the appropriate power of macro stations and small base stations to ensure network stability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

High-throughput GPU layered decoder of multi-edge type low density parity check codes in continuous-variable quantum key distribution systems

arXiv

引用

arXiv 2020年

作者： Li, Yang Zhang, Xiaofang Li, Yong Xu, Bingjie Ma, Li Yang, Jie Huang, Wei Institute of Southwestern Communication Science and Technology on Security Communication Laboratory Chengdu610041 China Chongqing University of Posts and Telecommunications School of Communication and Information Engineering Chongqing400065 China Chongqing University College of Computer Science Chongqing400044 China

The decoding throughput in the postprocessing is one of the bottlenecks for a continuous-variable quantum key distribution (CV-QKD) system. In this paper, we propose a layered decoder to decode quasi-cyclic multi-edge type LDPC (QC-MET-LDPC) codes based on graphic processing unit (GPU) in continuous-variable quantum key distribution (CV-QKD) systems. We optimize the storage method of the parity check matrix, merge the sub-matrices which are unrelated, and decode multiple codewords in parallel on GPU. Simulation results demonstrate that the average decoding speed of LDPC codes with three typical code rates, i.e., 0.1, 0.05 and 0.02, is up to 64.11Mbits/s, 48.65Mbits/s and 39.51Mbits/s, respectively, when decoding 128 codewords of length 106 simultaneously without early termination. Copyright © 2020, The Authors. All rights reserved.

关键词： Decoding

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：