检索结果-内蒙古大学图书馆

2023 IEEE/CIC International Conference on Communications in China, ICCC 2023

作者： Zhang, Peng Min, Minghui Xiao, Jiayang Li, Shiyin Zhang, Hongliang China University of Mining and Technology School of Information and Control Engineering Xuzhou221116 China Xuzhou First People's Hospital Xuzhou221116 China Ministry of Education School of CyberScience and Engineering Wuhan University Key Laboratory of Aerospace Information Security and Trusted Computing Wuhan430072 China Peking University School of Electronics Beijing100871 China

ISBN: (纸本)9798350345384

Recent years have witnessed a growing interest in implementing mobile edge computing (MEC) into mine Internet of Things (IoT) networks to enable real-time monitoring and safety management. However, the spatial blockage and limited transmitting power pose challenges to signal coverage and efficient computation offloading. To address these issues, we propose incorporating intelligent reflecting surfaces (IRSs) in the MEC system for underground mines (MMEC) to resolve wireless coverage problems in mine communication scenarios and enhance the channel gains of offloading links. Given the time-varying and complex channel conditions in mines and the multiple coupled variables involved in IRSs' reflecting coefficient matrix, we utilize Deep Reinforcement Learning (DRL) to acquire the optimal IRS-assisted computation offloading strategy in dynamic mine environments. Specifically, we propose a Deep Deterministic Policy Gradient (DDPG)-based IRS-aided computation offloading scheme to jointly optimize the IRS elements' reflection coefficients and the computation offloading rate. Simulation results demonstrate that introducing an IRS into the MMEC system yields outstanding benefits and significantly exceeds benchmarks in enhancing energy efficiency and decreasing computational latency. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Review on Assured Deletion of Cloud Data Based on Cryptography

引用

Procedia Computer Science 2021年 187卷 580-585页

作者： Guan Wang Yehong Luo Faculty of Information Technology Beijing University of Technology Beijing 100124 Beijing Key Laboratory of Trusted Computing Beijing 100124

In the cloud computing environment, storage is used for users to provide data outsourcing services. After users outsource data to the cloud, privacy protection has become a key concern. As far as we know, there is no systematic analysis of the assured deletion of cloud storage data based on cryptography from the perspective of having a third-party key management center (TKMC) and no TKMC. Our work focuses on analyzing and evaluating the fine-grained, safety, and performance of these schemes, and we also point out that researches can use trusted computing to securely strengthen TKMC in the future, making assured deletion more secure and reliable.

关键词： Cloud storage assured deletion cryptography third-party key management center trusted computing

来源：评论

学校读者我要写书评

暂无评论

An automated method with anchor-free detection and U-shaped segmentation for nuclei instance segmentation 2

An automated method with anchor-free detection and U-shaped ...

引用

2nd ACM International Conference on Multimedia in Asia, MMAsia 2020

作者： Feng, Xuan Duan, Lijuan Chen, Jie Faculty of Information Technology Beijing University of Technology Beijing100124 China Beijing Key Laboratory of Trusted Computing Beijing100124 China Natl. Engineering Laboratory of Critical Technologies of Information Security Classified Protection Beijing100124 China Peng Cheng Laboratory Shenzhen518055 China

ISBN: (纸本)9781450383080

Nuclei segmentation plays an important role in cancer diagnosis. Automated methods for digital pathology become popular due to the developments of deep learning and neural networks. However, this task still faces challenges. Most of current techniques cannot be applied directly because of the clustered state and the large number of nuclei in images. Moreover, anchor-based methods for object detection lead a huge amount of calculation, which is even worse on pathological images with a large target density. To address these issues, we propose a novel network with an anchor-free detection and a U-shaped segmentation. An altered feature enhancement module is attached to improve the performance in dense target detection. Meanwhile, the U-Shaped structure in segmentation block ensures the aggregation of features in different dimensions generated from the backbone network. We evaluate our work on a Multi-Organ Nuclei Segmentation dataset from MICCAI 2018 challenge. In comparisons with others, our proposed method achieves state-of-the-art performance. © 2021 ACM.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

The Controlled Sharing Mechanism for Private Data Based on Blockchain 6

The Controlled Sharing Mechanism for Private Data Based on B...

引用

6th IEEE International Conference on Data Science in Cyberspace, DSC 2021

作者： Wenqing, Li Wenjie, Dong Xu, Zhang Yueming, Lu School Of Cyberspace Security Beijing University Of Posts And Telecommunications Beijing China Beijing Aerospace Automatic Control Institute Beijing China Beijing University Of Posts And Telecommunications Ministry Of Education Key Laboratory Of Trusted Distributed Computing And Service Beijing China

ISBN: (纸本)9781665418157

In order to solve the problems that private information is easy to be leaked and privacy violations are difficult to be traced in the process of data cross-domain transferring, we propose a blockchain-based controlled sharing mechanism for private data, which has the merits such as decentralization, tamper-proof, and traceability. By combining smart contract technology and cryptographic algorithms, we realize the user authentication and private data rights determination. On the basis of that, we extract privacy protection metadata by using technologies such as hash function and digital signature and then store it on the blockchain, which realizes the depositing and tracing of data transferring records. At the same time, we encrypt the original data and store it in a distributed file system to alleviate the problem of limited storage space in blockchain while ensuring the security of data storage. © 2021 IEEE.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

A Survey of Deep Visual Cross-Domain Few-Shot Learning

arXiv

引用

arXiv 2023年

作者： Wang, Wenjian Duan, Lijuan Wang, Yuxi Fan, Junsong Gong, Zhi Zhang, Zhaoxiang Faculty of Information Technology Beijing University of Technology China Beijing Key Laboratory of Trusted Computing Beijing China National Engineering Laboratory for Key Technologies of Information Security Level Protection Beijing China Centre for Artificial Intelligence and Robotics HKISI_CAS Institute of Automation Chinese Academy of Sciences [NLPR CASIA UCAS China

Few-Shot transfer learning has become a major focus of research as it allows recognition of new classes with limited labeled data. While it is assumed that train and test data have the same data distribution, this is often not the case in real-world applications. This leads to decreased model transfer effects when the new class distribution differs significantly from the learned classes. Research into Cross-Domain Few-Shot (CDFS) has emerged to address this issue, forming a more challenging and realistic setting. In this survey, we provide a detailed taxonomy of CDFS from the problem setting and corresponding solutions view. We summarise the existing CDFS network architectures and discuss the solution ideas for each direction the taxonomy indicates. Furthermore, we introduce various CDFS downstream applications and outline classification, detection, and segmentation benchmarks and corresponding standards for evaluation. We also discuss the challenges of CDFS research and explore potential directions for future investigation. Through this review, we aim to provide comprehensive guidance on CDFS research, enabling researchers to gain insight into the state-of-the-art while allowing them to build upon existing solutions to develop their own CDFS models. Copyright © 2023, The Authors. All rights reserved.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

BPN: Bidirectional Path Network for Instance Segmentation 1st

BPN: Bidirectional Path Network for Instance Segmentation

引用

1st CAAI International Conference on Artificial Intelligence, CICAI 2021

作者： Xu, Fan Duan, Lijuan Qiao, Yuanhua Faculty of Information Technology Beijing University of Technology Beijing China Peng Cheng Laboratory Beijing University of Technology Beijing China Beijing Key Laboratory of Trusted Computing Beijing University of Technology Beijing China National Engineering Laboratory for Key Technologies of Information Security Level Protection Beijing University of Technology Beijing China College of Mathematics and Physics Beijing University of Technology Beijing China

ISBN: (纸本)9783030930486

The feature pyramid network (FPN) has achieved impressive results in the field of object detection and instance segmentation by aggregating features of different scales, especially the detection of small objects. However, for some special large objects (such as tables, chairs, etc.), It is difficult to achieve good results for FPN. In this paper, we propose a new simple but effective network, the Bidirectional Path Network (BPN), for the problems that FPN cannot solve. In simple terms, it consists of a top-to-down FPN and bottom-to-up FPN. This bidirectional network structure can greatly enrich high-level semantic information and improve the detection effect of these large objects. And we also introduce dense connections to enrich the output features further. We tested our method on the COCO dataset. Firstly, on the object detection task, our method obtains comparable results with the state-of-the-art benchmark. Then, on the instance segmentation task, our method also achieved good results. © 2021, Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A Survey of Deep Models for Cross-Domain Few-Shot Visuallearning

SSRN

引用

SSRN 2023年

作者： Wang, Wenjian Duan, Lijuan Wang, Yuxi Fan, Junsong Gong, Zhi Zhang, Zhaoxiang Faculty of Information Technology Beijing University of Technology China Beijing Key Laboratory of Trusted Computing Beijing China National Engineering Laboratory for Key Technologies of Information Security Level Protection Beijing China Centre for Artificial Intelligence and Robotics HKISI CAS Hong Kong Institute of Automation Chinese Academy of Sciences NLPR CASIA UCAS China

Few-Shot transfer learning uses limited labeled data to recognise the new classes. Current researches assume that train and test data have the same data distribution. But this setting is strict and difficult to guarantee due to the various transfer scenarios in reality. When the new class distribution different from the learned classes significantly, the model transfer effect will be seriously decreased. To relieve this problem, the existing Few-Shot research has begun to focus on cross-domain research, hoping the model can still complete Few-Shot learning when facing the domain shift, namely Cross-Domain Few-Shot (CDFS). Compared with standard Few-Shot learning, CDFS is more challenging and suitable to actual scenarios. We summarized recent research on Cross-Domain Few-Shot. Our survey provide the detailed taxonomy from the view of problem setting and corresponding solutions. We introduced the typical CDFS network in detail in each taxonomy direction and summarized the solution ideas. Meanwhile, we introduce the various CDFS downstream application. Furthermore, we outlined the classification, detection, and segmentation of the corresponding CDFS benchmark and give the corresponding standards for subsequent research. Finally, we summarized the challenges of CDFS in the future and the related technical direction, hoping to provide corresponding guidance for future CDFS research. © 2023, The Authors. All rights reserved.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

BackCache: Mitigating Contention-Based Cache Timing Attacks by Hiding Cache Line Evictions

arXiv

引用

arXiv 2023年

作者： Wang, Quancheng Zhang, Xige Wang, Han Gu, Yuzhe Tang, Ming Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University Wuhan430072 China Beijing Smartchip Microelectronics Technology Co. Ltd. Beijing100192 China

Caches are used to reduce the speed gap between the CPU and memory to improve the performance and efficiency of modern processors. However, attackers can use contention-based cache timing attacks to steal sensitive information from victim processes through carefully designed cache eviction sets. L1 data cache attacks are widely exploited and pose a significant privacy and confidentiality threat. Existing hardware-based countermeasures mainly focus on cache partitioning, randomization, and cache line flushing, which unfortunately either incur high overhead or can be circumvented by sophisticated attacks. In this paper, we propose a novel hardware-software co-design called BackCache with the idea of always achieving cache hits instead of cache misses to mitigate contention-based cache timing attacks on the L1 data cache. BackCache places the evicted cache lines from the L1 data cache into a fully associative backup cache to hide the evictions. To improve the security of BackCache, we introduce a randomly used replacement policy (RURP) and a dynamic backup cache resizing mechanism. Our evaluation on the gem5 simulator shows that BackCache can degrade the performance by 2.61%, 2.66%, and 3.36% For OS kernel, single-thread, and multi-thread benchmarks. Copyright © 2023, The Authors. All rights reserved.

关键词： Timing circuits

来源：评论

学校读者我要写书评

暂无评论

Classification of epilepsy period based on combination feature extraction methods and spiking swarm intelligent optimization algorithm

Classification of epilepsy period based on combination featu...

引用

作者： Duan, Lijuan Lian, Zhaoyang Chen, Juncheng Qiao, Yuanhua Miao, Jun Li, Mingai Faculty of Information Technology Beijing University of Technology Beijing China Beijing Key Laboratory of Trusted Computing Beijing University of Technology Beijing China National Engineering Laboratory for Key Technologies of Information Security Level Protection Beijing University of Technology Beijing China Applied Sciences Beijing University of Technology Beijing China School of Computer Science Beijing Information Science and Technology University Beijing China

Epilepsy seriously damages the physical and mental health of patients. Detection of epileptic EEG signals in different periods can help doctors diagnose the disease. The change of frequency components during epilepsy seizures is obvious, and there may be noises in epilepsy EEG signals. Moreover, epileptic seizures are closely related to the release of neuronal spiking in the brain. In this paper, we propose an approach for epilepsy period classification based on combination feature extraction methods and spiking swarm intelligent optimization classification algorithm. First, combination feature extraction methods take in account both the time-frequency features and principal component features of epilepsy. The time-frequency features are obtained by WPT or STFT-PSD, and noises are removed while extracting principal component features by PCA. Second, spiking swarm intelligent optimization classification algorithm takes advantage of individual cooperation and information interaction with strong robustness. Its simulated neurons are closer to reality, which consider more information and obtain stronger computing power. The experimental results show that the average classification accuracy of the proposed method can reach 98.95% and the highest classification accuracy can reach 100%. Compared with other methods, the proposed method has the best classification performance. © 2020 John Wiley & Sons, Ltd.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Research on Cross-Chain Technology Architecture System Based on Blockchain 8th

Research on Cross-Chain Technology Architecture System Based...

引用

8th International Conference on Communications, Signal Processing, and Systems, CSPS 2019

作者： Zhang, Jianbiao Liu, Yanhui Zhang, Zhaoqian Faculty of Information Technology Beijing University of Technology Beijing100124 China Beijing Key Laboratory of Trusted Computing Beijing100124 China

ISBN: (纸本)9789811394089

With the development of blockchain technology, blockchain technology has strong vitality in various industries due to its characteristics of dispersion, anti-mite modification and traceability. Blockchain technology allows trusted parties to trust transactions and realize value streams. Since there are different values in different chains, will the values of different chains also flow? This is a problem that needs to be solved in the cross-chain interaction. Under the scenario for cross-chain interaction between private chain or alliance chain between enterprises, this paper proposes an alliance chain model that can realize cross-chain interaction between enterprises. On this basis, it analyzes the difficulties of cross-chain interaction technology and analyzes the model. At last, we summarize the paper. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Blockchain

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：