检索结果-内蒙古大学图书馆

23rd IEEE International Conference on Communication technology, ICCT 2023

作者： Mu, Rui Fan, Shaoshuai Peng, Zixiang Tian, Hui Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing100876 China

ISBN: (纸本)9798350325959

The Time of Arrival (TOA) based positioning technique has been extensively investigated and applied. Nevertheless, the presence of carrier frequency offset (CFO) and phase noise (PN) in the oscillator can significantly impair the orthogonal frequency division multiplexing (OFDM) system, consequently compromising the accuracy of TOA estimation and TOA based positioning. In this paper, we propose a TOA estimation algorithm via Kalman Filter(KF) in an OFDM system with CFO and PN present. To distinguish among different types of noise using our proposed estimator, we constructed extra measurements. The simulation demonstrates that the proposed approach exhibits higher accuracy in TOA estimation compared to the multiple signal classification algorithm method. © 2023 IEEE.

关键词： frequency offseet Kalman filter OFDM phase noise Toa estimation

来源：评论

学校读者我要写书评

暂无评论

UMCL: Unified Medical Image-Text-label Contrastive Learning With Continuous Prompt

UMCL: Unified Medical Image-Text-Label Contrastive Learning ...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Wang, Yuhao Wang, Guangyu Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing100876 China

ISBN: (纸本)9798350337488

Contrastive Language-Image Pre-training (CLIP) can leverage large dataset of unlabeled Image-Text pairs, which have demonstrated impressive performance in various downstream tasks. Given that annotating medical data is timeconsuming and laborious, Image-Text Pre-training has promising applications in exploiting large-scale medical image and radiology report dataset. However, medical Image-Text Pre-training faces several challenges, as follows: (1) Due to privacy concerns, the amount of available medical data is relatively small compared to natural data, leading to weaker generalization ability of the model. (2) Medical images are highly similar with only finegrained differences in subtleties, resulting in a large number of false-negative sample pairs in comparison learning. (3) The hand-crafted Prompt usually differs from the natural medical image report, Subtle changes in wording can lead to significant differences in performance. In this paper, we propose a unified Image-Text-label contrastive learning framework based on continuous prompts, with three main contributions. First, We unified the data of images, text, and labels, which greatly expanded the training data that the model could utilize. Second, we address the issue of data diversity and the impact of hand-crafted prompts on model performance by introducing continuous implicit prompts. Lastly, we propose a Image-Text-label contrastive Training to mitigate the problem of too many false-negative samples. We demonstrate through sufficient experiments that the Unified Medical Contrastive Learning (UMCL) framework exhibits excellent performance on several downstream tasks. © 2023 IEEE.

关键词： Medical Image Analysis Multimodal Pretrain Vision-Language Model

来源：评论

学校读者我要写书评

暂无评论

Mobility-Aware Dynamic Service Migration in Communication and Computing Integrated VNETs

Mobility-Aware Dynamic Service Migration in Communication an...

引用

2023 IEEE Globecom Workshops, GC Wkshps 2023

作者： Liu, Haoran Jiang, Ning Guo, Fengxian Yan, Shi Peng, Mugen Beijing University of Posts and Telecommunications The State Key Laboratory of Networking and Switching Technology Beijing100876 China

ISBN: (纸本)9798350370218

The Communication and computing integrated vehicular networks have emerged as a reliable platform for intelligent vehicular applications. These networks leverage mobile edge computing technology to enable computing capabilities at the network edge closer to vehicles. However, the mobility of vehicles could break service continuity and make it difficult to accomplish intelligent services within tolerant latency under communication and computing resource-constrained conditions. To overcome these challenges, this paper proposes a mobility-aware service migration approach to effectively reduce service latency under the expected migration cost constraint. The key aspect of this approach is leveraging the mobility information of vehicles to search for the best migration strategy. This paper utilizes the wireless sensing technology of the base stations to acquire real-time mobility information of vehicles. The mobility information and channel states are jointly considered to make decisions on service migration as well as resource allocation strategies via a decentralized multi-agent proximal policy optimization (MAPPO) algorithm. Simulation results demonstrate that the proposed mobility-aware service migration approach can effectively reduce the average service latency compared to other benchmark approaches. © 2023 IEEE.

关键词： communication and computing integrated vehicular networks mobility-aware resource allocation Service migration

来源：评论

学校读者我要写书评

暂无评论

MDFL: Model-Distance Federated Learning on Non-IID data 9

MDFL: Model-Distance Federated Learning on Non-IID data

引用

9th International Conference on Communication and Information Processing, ICCIP 2023

作者： Chen, Ze Tian, Hui Gao, Tianrun Li, Lihua State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Haidian Beijing China

ISBN: (纸本)9798400708909

Federated learning (FL) is an emerging approach in the field of Artificial Intelligence of Things (AIoT) that enables collaborative model training across multiple edge devices or IoT nodes while protecting data privacy. However, FL faces significant challenges, particularly regarding the non-Independent and Identically Distributed (non-IID) data across IoT devices. Despite the considerable efforts dedicated to address this issue, existing approaches seriously impact on the speed of convergence in FL. In this paper, we propose MDFL, a novel FL framework that incorporates a distance-based participant selection strategy to enhance the overall performance and efficiency. MDFL eliminates the consistency among clients regarding the epochs of local training and the weighted coefficient of server aggregation. Specifically, our method allows strong participants to achieve more training epochs and gain a larger weighting proportion during the aggregation. We evaluate the effectiveness of our approach on the MNIST and FashionMNIST datasets. Experimental results demonstrate that MDFL achieves superior performance, improving the test accuracy from 0.9% to 1.8% on MNIST and from 0.6% to 1.0% on FashionMNIST, respectively. © 2023 Copyright held by the owner/author(s)

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

Improving Performance of Docker Instance via Image Reconstruction

Improving Performance of Docker Instance via Image Reconst...

引用

International Conference on Big Data Intelligence and Computing, DataCom 2022

作者： Jiang, Qingyuan State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing100876 China

ISBN: (纸本)9789819922321

Docker has become a key paradigm for application deployment in cloud computing. A running Docker instance need to access its corresponding docker image for searching the required file from time to time. The more layers a docker image has, the longer the search time is. The number of image layers has significant impact on the efficiency of the application. However, reducing the number of image layers via layer merging will reduce the shareability of image layers and increase the storage occupation. To address the above issue, we exploit image reconfiguration to achieve a trade-off between the operation efficiency and storage occupation. We formulate the image reconstruction problem as a knapsack problem, and design a dynamic programming-based offline image reconstruction algorithm named DPOIRA to solve it. We conduct experiments on the busybox and crate, and the experiment results show the effectiveness of our algorithm. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Quantum Computing Catalyzes Future Quantum Networks: Efficiency and Inherent Privacy

引用

IEEE NETWORK 2025年第1期39卷 124-131页

作者： Ju, keyi Zhong, Hui Zhang, Xinyue Qin, Xiaoqi Pan, Miao Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China Univ Houston Dept Elect & Comp Engn Houston TX 77204 USA Kennesaw State Univ Dept Comp Sci Marietta GA 30060 USA

Quantum networks show promise in enhancing the overall functional advantages of the Internet and enabling applications that are incomparable in the classical world. Supported by quantum communication, quantum networks are expected to offer almost unconditional security. However, securing personal privacy within quantum networks is of paramount importance. The aim of this paper is to extend the differential privacy (DP) framework to quantum networks, addressing the issue of personal privacy security in the future quantum networks. We begin by discussing the fundamental principles of quantum computing and DP. Additionally, in the current noisy intermediate-scale quantum (NISQ) era, unavoidable noise is inherent in quantum computing. We explore in detail how this inherent noise can be utilized to protect personal privacy while also enhancing the utility of data. Finally, we analyze several pressing challenges and open research directions in personal privacy protection within future quantum networks.

关键词： Quantum computing Noise Quantum networks Privacy Protection Quantum state Qubit quantum computing quantum differential privacy quantum noise

来源：评论

学校读者我要写书评

暂无评论

Semi-Swinderain: Semi-Supervised Image Deraining Network Using SWIN Transformer 48

Semi-Swinderain: Semi-Supervised Image Deraining Network Usi...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Ren, Chun Yan, Danfeng Cai, Yuanqiang Li, Yangchun Bupt State Key Laboratory of Networking and Switching Technology China Chinese Academy of Cyberspace Studies China

ISBN: (纸本)9781728163277

Currently, single image deraining lacks paired rain/clean images in real world and most studies use synthetic data. Real rain image deraining is still a challenge. To solve this problem, we propose a semi-supervised image deraining network using Swin Transformer, which can both use features of synthetic data and real data to get a better result. Specifically, the network is divided into supervised branch and unsupervised branch. Supervised and unsupervised branches are trained using synthetic data and real data, respectively. The network architecture is based on Swin Transformer, which adds a self-supervised memory module between encoder and decoder to store rain information. In the unsupervised branch, contrastive loss is added to ensure restored real rain image in features space is close to clear image, away from real rain image. In addition, we propose a real rain dataset RealRain11k. Experiments show our method has better result in real rain image deraining. The source code and RealRain11k are available at https://***/imissrc/Semi-SwinDerain. © 2023 IEEE.

关键词： Contrastive Loss Deraining Memory Semi-suprivised Swin Transformer

来源：评论

学校读者我要写书评

暂无评论

A Dual Channel MAC Protocol with IRS Relay Selection Mechanism for Terahertz Communication 9

A Dual Channel MAC Protocol with IRS Relay Selection Mechani...

引用

9th International Conference on Computer and Communications, ICCC 2023

作者： Zhai, Jianing Ma, Nan Liu, Shaoyi Zheng, Shaofei Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing100876 China

ISBN: (纸本)9798350317251

The demand for high-speed data transmission in 6G networks has triggered the urgent need for research on terahertz (THz) communication frequency bands. However, the THz directional transmission and rapid attenuation in the air pose a challenge to the design of Medium Access Control (MAC) protocols. In this paper, a novel Terahertz Dual Channel MAC Protocol based on IRS Relay Selection (RS-MAC) is proposed, which leverages GHz frequency band for control signaling and employs THz beams for data transmission. Firstly, we introduce a Joint Judging Line-of-Sight (LoS) Algorithm Based on Location and Angle Information (LA-LoS) to determine whether LoS exist between the transmitter and receiver. Moreover, we capitalize on the unique reflection characteristics of Intelligent Reflection Surface (IRS) technology to introduce IRS relay paths at the MAC layer, reducing relay delay and enhancing data transmission efficiency. In the end, numerical simulations were conducted to analyze the performance improvements. The results indicate that, compared with some existing MAC relay protocols, the proposed protocol exhibits a substantial reduction in THz transmission delay and an improvement in achievable throughput. © 2023 IEEE.

关键词： Medium access control

来源：评论

学校读者我要写书评

暂无评论

SeTemAPR: Incorporating Semantic Knowledge in Template-based Neural Program Repair

SeTemAPR: Incorporating Semantic Knowledge in Template-based...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Zhang, Yanbo Wang, Yawen Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing Peoples R China Guangxi Key Lab Cryptog & Informat Secur Guilin Guangxi Peoples R China

ISBN: (纸本)9798350359329;9798350359312

Automated program repair has been widely studied in recent years. Template-based and NMT-based program repair methods have achieved promising outcomes. However, templatebased methods only consider syntax structure and lack semantic information. NMT-based methods lack type information for variables or functions with the same name in different code snippets. At the same time, studies have also shown that NMT-based methods have the problem of over-reliance on faulty statements. Subsequent studies have integrated templates and NMT by generating templates and key information instead of directly producing repair codes. However, the generated templates do not consider the code semantics, leading to a significant number of failed fixes that lack semantic coherence with the faulty statement. In this paper, we propose SeTemAPR, a template-based neural program repair method that fuses semantic information. Specifically, SeTemAPR proposes semantic embedding to provide type information to variables and functions. Then, SeTemAPR proposes a rule-based semantic filter with an extra loss to learn the semantic differences between input code snippets and selected fix templates. At the same time, we set external placeholders to solve the OOV (out-of-vocabulary) problem and ensure the efficiency of generation. Finally, we train an additional model by masking the faulty statements. We combine the model with an ordinary trained model using a joint inference mechanism to solve the problem of over-reliance on faulty statements. We evaluate SeTemAPR on the widely used benchmark Defects4j. EExperimental results show that SeTemAPR can effectively learn semantic and type information, and repair 6 more faults than the state of the art methods. Meanwhile, we conduct extensive experiments on SeTemAPR to verify its effectiveness.

关键词： Automated Program Repair Fix Templates Neural Machine Translation Deep Learning

来源：评论

学校读者我要写书评

暂无评论

Quantum algorithm for neighborhood preserving embedding

引用

Chinese Physics B 2022年第6期31卷 192-203页

作者： Shi-Jie Pan Lin-Chun Wan Hai-Ling Liu Yu-Sen Wu Su-Juan Qin Qiao-Yan Wen Fei Gao State Key Laboratory of Networking and Switching Technology Beijing University of Posts and TelecommunicationsBeijing 100876China State Key Laboratory of Cryptology P.O.Box 5159Beijing 100878China

Neighborhood preserving embedding(NPE)is an important linear dimensionality reduction technique that aims at preserving the local manifold *** contains three steps,i.e.,finding the nearest neighbors of each data point,constructing the weight matrix,and obtaining the transformation *** et *** a variational quantum algorithm(VQA)for NPE[***.A 101032323(2020)].The algorithm consists of three quantum sub-algorithms,corresponding to the three steps of NPE,and was expected to have an exponential speedup on the dimensionality ***,the algorithm has two disadvantages:(i)It is not known how to efficiently obtain the input of the third sub-algorithm from the output of the second one.(ii)Its complexity cannot be rigorously analyzed because the third sub-algorithm in it is a *** this paper,we propose a complete quantum algorithm for NPE,in which we redesign the three sub-algorithms and give a rigorous complexity *** is shown that our algorithm can achieve a polynomial speedup on the number of data points m and an exponential speedup on the dimensionality n under certain conditions over the classical NPE algorithm,and achieve a significant speedup compared to Liang et al.’s algorithm even without considering the complexity of the VQA.

关键词： quantum algorithm quantum machine learning amplitude amplification

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：