检索结果-内蒙古大学图书馆

10th IEEE Smart World Congress, SWC 2024

作者： Cheng, Long Yan, Huiru Zhou, Hanlin Wang, Ying Tang, Haichuan Fang, Fang North China Electric Power University State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources School of Control and Computer Engineering Beijing China Institute of Computing Technology Chinese Academy of Sciences Beijing China Ai Lab of Crrc Academy Beijing China

ISBN: (纸本)9798331520861

Preventing network attacks and protecting user privacy are consistently hot research topics in the Internet of Things (IoT) and edge computing fields. Recent advancements in Federated Learning (FL) have shown promise in addressing these challenges. FL allows various clients to collaboratively build an intrusion detection system (IDS) without sharing their private data. However, most existing methods train a single intrusion detection model for all clients and assume that the training and test data distribution are identical, leading to unsatisfactory detection accuracy and generalization abilities in practice. To overcome these challenges, this paper introduces a prototype-guided personalized FL approach named PG-FedIDS. We propose two novel mechanisms within this method. Firstly, we utilize class prototypes as auxiliary information carriers to generate personalized models for each client, rather than generating a single global model as in previous works. Secondly, we propose a prototype-guided ensemble learning strategy, which can leverage the global knowledge in prototypes to enhance detection accuracy and generalization abilities for each client. We conduct extensive experiments on two benchmark datasets with different evaluation test settings. The results demonstrate that our PG-FedIDS achieves promising detection accuracy and consistently outperforms other FL baselines. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Smart Contract Vulnerability Detection Based on Mixed Channel Attention 36

Smart Contract Vulnerability Detection Based on Mixed Channe...

引用

36th International Conference on Software engineering and Knowledge engineering, SEKE 2024

作者： Wang, Jiao Ran Zeng, Cheng Ba, Kai Yang Quan, Qing Yu Wang, Yi Feng School of Computer Science and Information Engineering Hubei University Wuhan China School of Artificial Intelligence Hubei University Wuhan China School of Cyberspace Security Hubei University Wuhan China Key Laboratory of Intelligence Sensing System and Security Hubei University Ministry of Education Wuhan China

ISBN: (纸本)1891706594

As blockchain technology progresses, the deployment of smart contracts has become increasingly prevalent. Despite their growing popularity, smart contracts introduce substantial security risks and vulnerabilities. Present detection methodologies predominantly analyze the entirety of a contract’s source code, a process that tends to indiscriminately extract uniform features, leading to inadequate detection capabilities. Addressing these concerns, we propose a novel vulnerability detection method for smart contracts, predicated on a mixed channel attention mechanism. This approach focuses on extracting multifaceted features from pivotal code segments of smart contracts, utilizing a combination of spatial and frequency domain channel attention mechanisms. These mechanisms dynamically modulate the weights of feature channels during visualization, allowing the model to allocate greater emphasis to features of higher significance and enhance feature differentiation. This strategy is instrumental in capturing salient information within the data, thereby augmenting the model’s performance and accuracy. Empirical results substantiate that our proposed method substantially surpasses the baseline model, evidencing improvements of 5.55%, 5.42%, and 5.49% in the detection of timestamp vulnerabilities, and 4.12%, 4.29%, and 4.20% in the identification of reentrancy vulnerabilities, respectively. Our method offers a significant advancement in the efficacy of smart contract vulnerability detection and presents valuable implications for future research. © 2024 Knowledge systems Institute Graduate School. All rights reserved.

关键词： channel attention key code slicing multiple features smart contracts vulnerability detection

来源：评论

学校读者我要写书评

暂无评论

Dynamic Searchable Scheme with Forward Privacy for Encrypted Document Similarity 22

Dynamic Searchable Scheme with Forward Privacy for Encrypted...

引用

22nd IEEE International Conference on Trust, Security and Privacy in Computing and Communications, TrustCom 2023

作者： Al Sibahee, Mustafa A. Luo, Chengwen Zhang, Jin Huang, Yijing Abduljabbar, Zaid Ameen Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen518060 China Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China Iraq University College Computer Technology Engineering Department Basrah61004 Iraq University of Basrah College of Education for Pure Sciences Department of Computer Science Basrah61004 Iraq Huazhong University of Science and Technology Shenzhen Institute Shenzhen518000 China

ISBN: (纸本)9798350381993

Document retrieval plays an essential role in many real-world applications especially when the data storage is outsourced. Due to the great advantages offered by cloud computing, clients tend to outsource their personal data to remote servers maintained by external service providers. This raises serious privacy concerns about outsourced data because such providers are usually considered untrusted entities. The majority of previous schemes of document similarity search share the same limitation: they focus mainly on static collections. Dynamic searchable schemes (DSE) allow adding or removing documents at the expense of more leakage than static schemes. To thwart certain attacks, DSE schemes should support forward privacy property, which ensures that newly added documents cannot be related to previously issued search queries. We design and implement dynamic secure similarity search schemes with forward privacy for textual documents utilizing simhash method for hamming similarity. Our scheme provides an efficient search time and a sufficient level of privacy. To show the practicality of our proposed scheme, we performed excremental results with large document collections. © 2023 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Multi-modal Natural Man–Machine Interaction Technology and Its Application for Lunar Robot 23rd

Multi-modal Natural Man–Machine Interaction Technology and ...

引用

23rd IFToMM China International Conference on Mechanism and Machine Science and engineering, IFToMM CCMMS 2022

作者： Chen, Meng Zhang, Chongfeng Qin, Xiaofei Ma, Jia Zhang, Wenqi Shanghai Key Laboratory of Spacecraft Mechanism Shanghai201108 China Institute of Aerospace System Engineering Shanghai Shanghai201109 China Shanghai Academy of Spaceflight Technology Shanghai201109 China School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai200093 China

ISBN: (纸本)9789811993978

For the requirements of multi-modal man–machine interaction between astronauts and robots in lunar surface exploration, research on three interaction modes and test system based on speech, body posture and tactile recognition are carried out. An improved speech feature classification and recognition algorithm based on Mel-scale Frequency Cepstral Coefficients (MFCC), a three-stage body posture recognition algorithm based on target detection—node recognition—skeleton action recognition, and a tactile recognition algorithm based on Radial Basis Function network (RBF) are proposed. In the body posture recognition algorithm, a lightweight CVC-Net model is developed based on the classical HourglassNet algorithm. Deep separable convolution, attention mechanism and improved up-sampling method are introduced. A lightweight network and adaptive graph convolution module for skeleton action recognition are designed by introducing the information of human body joints and skeleton vectors. Above algorithm is suitable for the embedded computing platform and can greatly reduce the number of module parameters while ensuring the detection accuracy. Based on the simulated lunar surface environment, lunar robot and simulated space suit, the ground test verification of three modes of command recognition is realized, which can meet the low power consumption, lightweight and real-time requirements of lunar robot for recognition algorithms and the embedded computing platform. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Digital-Based Inverse Design for Ultra-Compact Power Splitter on LNOI

Digital-Based Inverse Design for Ultra-Compact Power Splitte...

引用

2023 Asia Communications and Photonics Conference/2023 International Photonics and Optoelectronics Meetings, ACP/POEM 2023

作者： Zhou, Lingjun Ma, Hansi Nie, Xiaomin Li, Yunchen He, Zhixue Wang, Lei Li, Ke Zhang, Fan Peng Cheng Laboratory Shenzhen China School of Electronic and Computer Engineering Peking University Shenzhen China Center of Material Science National University of Defense Technology Changsha China State Key Laboratory of Advanced Optical Communication System and Networks School of Electronics Peking University Beijing China

ISBN: (纸本)9798350312614

We propose and experimentally demonstrate an ultra-compact and efficient power splitter on LNOI. The device is realized through the inverse design of a digital meta-structure and occupies a small footprint of only 4.8×4.8μm2. The measured results show that the insertion losses are below 2.5dB across the wavelength band of 1500-1560 nm, and the power imbalance between the two output ports is within 0.3 dB. © 2023 IEEE.

关键词： inverse design LNOI power splitter

来源：评论

学校读者我要写书评

暂无评论

An adaptive representation model for geoscience knowledge graphs considering complex spatiotemporal features and relationships

引用

Science China Earth Sciences 2023年第11期66卷 2563-2578页

作者： Yunqiang ZHU Kai SUN Shu WANG Chenghu ZHOU Feng LU Hairong LV Qinjun QIU Xinbing WANG Yanmin QI State Key Laboratory of Resources and Environmental Information System Institute of Geographic Sciences and Natural Resources ResearchChinese Academy of SciencesBeijing 100101China Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application Nanjing 210023China Department of Automation Tsinghua UniversityBeijing 100084China School of Computer Science China University of GeosciencesWuhan 430074China Department of Electronic Engineering Shanghai Jiao Tong UniversityShanghai 200240China School of Computer Science University of Nottingham Ningbo ChinaNingbo 315100China

Geoscience knowledge graph(GKG)can organize various geoscience knowledge into a machine understandable and computable semantic network and is an effective way to organize geoscience knowledge and provide knowledge-related *** a result,it has gained significant attention and become a frontier in *** knowledge is derived from many disciplines and has complex spatiotemporal features and relationships of multiple scales,granularities,and ***,establishing a GKG representation model conforming to the characteristics of geoscience knowledge is the basis and premise for the construction and application of ***,existing knowledge graph representation models leverage fixed tuples that are limited in fully representing complex spatiotemporal features and *** address this issue,this paper first systematically analyzes the categorization and spatiotemporal features and relationships of geoscience *** this basis,an adaptive representation model for GKG is proposed by considering the complex spatiotemporal features and *** the constraint of a unified spatiotemporal ontology,this model adopts different tuples to adaptively represent different types of geoscience knowledge according to their spatiotemporal *** model can efficiently represent geoscience knowledge,thereby avoiding the isolation of the spatiotemporal feature representation and improving the accuracy and efficiency of geoscience knowledge *** can further enable the alignment,transformation,computation,and reasoning of spatiotemporal information through a spatiotemporal ontology.

关键词： Geoscience Knowledge graph Representation model Spatiotemporal features Spatiotemporal relationships

来源：评论

学校读者我要写书评

暂无评论

Online Computation Offloading and Trajectory Scheduling for UAV-Enabled Wireless Powered Mobile Edge Computing

引用

China Communications 2022年第4期19卷 257-273页

作者： Han Hu Xiang Zhou Qun Wang Rose Qingyang Hu The Jiangsu Key Laboratory of Wireless Communications Nanjing University of Posts and TelecommunicationsNanjing 210003China The Engineering Research Center of Health Service System Based on Ubiquitous Wireless Networks Ministry of EducationNanjing University of Posts and TelecommunicationsNanjing 210003China The Department of Electrical and Computer Engineering Utah State UniversityLoganUTUSA.

The unmanned aerial vehicle(UAV)-enabled mobile edge computing(MEC) architecture is expected to be a powerful technique to facilitate 5 G and beyond ubiquitous wireless connectivity and diverse vertical applications and services, anytime and anywhere. Wireless power transfer(WPT) is another promising technology to prolong the operation time of low-power wireless devices in the era of Internet of Things(IoT). However, the integration of WPT and UAV-enabled MEC systems is far from being well studied, especially in dynamic environments. In order to tackle this issue, this paper aims to investigate the stochastic computation offloading and trajectory scheduling for the UAV-enabled wireless powered MEC system. A UAV offers both RF wireless power transmission and computation services for IoT devices. Considering the stochastic task arrivals and random channel conditions, a long-term average energyefficiency(EE) minimization problem is *** to non-convexity and the time domain coupling of the variables in the formulated problem, a lowcomplexity online computation offloading and trajectory scheduling algorithm(OCOTSA) is proposed by exploiting Lyapunov optimization. Simulation results verify that there exists a balance between EE and the service delay, and demonstrate that the system EE performance obtained by the proposed scheme outperforms other benchmark schemes.

关键词： energy efficiency mobile edge computing UAV-enabled wireless power transfer trajectorys cheduling

来源：评论

学校读者我要写书评

暂无评论

Attention-enhanced Relation Network for Few-shot Image Classification 23

Attention-enhanced Relation Network for Few-shot Image Class...

引用

6th International Conference on Image and Graphics Processing, ICIGP 2023

作者： Li, Jinyang Tong, Jiahui Gao, Guangyu Xu, Wenbin School of Computer Science and Technology Beijing Institute of Technology China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing Electro-Mechanical Engineering Institute Beijing China Science and Technology on Optical Radiation Laboratory Beijing Institute of Environmental Characteristics Beijing100854 China

ISBN: (纸本)9781450398572

Traditional deep learning models firmly rely on a large amount of labeled data during pre-training. Whereas it lacks generalization in the face of unfamiliar categories. Recently, few-shot learning is a hot topic in computer vision to classify unseen classes with limited labels. A representative approach is to extract features from the support and query sets, respectively, and compare similarities via metric learning. However, convolutional neural networks often focus only on a local region and ignore the global region, which severely reduces the accuracy of the matching. Specifically, in this paper, we pile lightweight attention-based blocks in the embedding module, which combines an adaptive kernel size 2D convolutional network with a cross-channel attention mechanism to encode multi-scale features and implicitly increase the receptive field. The SE-relation module chooses to construct learnable non-linear comparators to compare the relationship utilizing channel information. Finally, we show experimental results on standard few-shot testing benchmarks such as mini-ImageNet and tiered-ImageNet to demonstrate effectiveness. © 2023 ACM.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

TCSloT: Text Guided 3D Context and Slope Aware Triple Network for Dental Implant Position Prediction

TCSloT: Text Guided 3D Context and Slope Aware Triple Networ...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Yang, Xinquan Xie, Jinheng Li, Xuechen Li, Xuguang Shen, Linlin Deng, Yongqiang Shenzhen University College of Computer Science and Software Engineering Shenzhen China National University of Singapore Show Lab Singapore Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen China Shenzhen University General Hospital Department of Stomatology Shenzhen China

ISBN: (纸本)9798350337488

In implant prosthesis treatment, the surgical guide of implant is used to ensure accurate implantation. However, such design heavily relies on the manual location of the implant position. When deep neural network has been proposed to assist the dentist in locating the implant position, most of them take a single slice as input, which do not fully explore 3D contextual information and ignores the influence of implant slope. In this paper, we design a Text Guided 3D Context and Slope Aware Triple Network (TCSloT) to integrate the perception of contextual information from multiple adjacent slices and awareness of variation of implant slopes. A Texture Variation Perception (TVP) module is correspondingly design to process the multiple slices and capture the texture variation among slices and a Slope-Aware Loss (SAL) is proposed to dynamically assign adaptive weights for the regression head. Additionally, we design a conditional text guidance (CTG) module to integrate the text condition (i.e., left, middle and right) from the CLIP to assist the implant position prediction. Extensive experiments on a dental implant dataset through five-fold cross-validation, demonstrated that the proposed TCSloT achieves superior performance than existing methods. © 2023 IEEE.

关键词： Dental Implant Multi-module Detection Multi-slice Learning Text Guided Detection Transformer

来源：评论

学校读者我要写书评

暂无评论

Broadband and repetition rate tunable frequency comb based on electro-optic time lens with AlGaAsOl waveguide 49

Broadband and repetition rate tunable frequency comb based o...

引用

49th European Conference on Optical Communications, ECOC 2023

作者： Ma, Chunyang Wang, Chaopeng Pi, Yazhi Wang, Lei He, Zhixue Bowers, John E. Chnag, Lin Zizheng Cao, Lin Yu, Shaohua Research Center of Circuits and Systems Peng Cheng Laboratory Guangdong Shenzhen518055 China Department of Electrical and Computer Engineering University of California Santa BarbaraCA93106 United States State Key Laboratory of Advanced Optical Communications System and Networks Peking University Beijing100871 China

ISBN: (纸本)9781839539954

We present a tunable repetition rate frequency comb realized by cascaded electro-optical modulators with a high nonlinear AlGaAs-on-isolator waveguide. 18-26.5 GHz comb spacing tunability with broadband spectra was achieved. All the devices can be integrated onto a single chip, which makes this work useful for many applications. © The Institution of engineering & Technology 2023.

关键词： Aluminum gallium arsenide

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：