检索结果-内蒙古大学图书馆

9th CCF International Conference on Natural Language Processing and Chinese Computing, NLPCC 2020

作者： Wu, Hanqian Cheng, Siliang Wang, Jingjing Li, Shoushan Chi, Lian School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University Nanjing China School of Computer Science and Technology Soochow University Suzhou China Nanjing University of Information Science and Technology Nanjing China

ISBN: (纸本)9783030604493

Fueled by the rise of social media, documents on these platforms (e.g., Twitter, Weibo) are increasingly multimodal in nature, with images in addition to text. To well automatically analyze the opinion information inside multimodal data, its crucial to perform aspect term extraction (ATE) on them. However, until now, the researches focus on multimodal ATE are rare. In this study, we take a step further than previous studies by proposing a Region-aware Alignment network (RAN) that aligns text with object regions that show in an image for the multimodal ATE task. Experiments on the Twitter dataset showcase the effectiveness of our proposed model. Further researches prove that our model has better performance when extracting emotion polarized aspect terms. © 2020, Springer Nature Switzerland AG.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Modeling and application of service relationships 3

Modeling and application of service relationships

引用

3rd IEEE International Conference on Civil Aviation Safety and information Technology, ICCASIT 2021

作者： Shaoxi, Liu Jun, Shen Jie, Ren Ying, Huang Southeast University Key Laboratory of Computer Network & Information Integration of Ministry of Education Nanjing China AVIC Chengdu Aircraft Design and Research Institute Chengdu China Nanjing Origin Information Technology Co. Ltd Nanjing China

ISBN: (纸本)9781665425186

In some new network architectures, in order to improve the scalability of services, scholars in recent years have been trying their best to explore the strategy of combining several small-grained services into large-grained services that can respond to user needs. In response to this problem, this paper studies and analyzes the relationship between services, and proposes a service relationship model based on fragmented logic. The model defines the service relationship structure and its related relationship operations. Then the model is applied in the SDEN network to complete the system requirements of service dynamic combination, thereby verifying that the model can improve the flexibility and scalability of the actual application system. © 2021 IEEE

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

An open-source project for real-time image semantic segmentation

引用

Science China(information Sciences) 2019年第12期62卷 246-247页

作者： Quan ZHOU Yu WANG Jia LIU Xin JIN Longin Jan LATECKI National Engineering Research Center of Communication and Network Technology Nanjing University of Posts and Telecommunications Key Laboratory of Ministry of Education for Broadband Wireless Communication and Sensor Network Technology Nanjing University of Posts and Telecommunications Beijing Electronic Science and Technology Institute State Key Laboratory of Virtual Reality Technology and Systems Beihang University Department of Computer and Information Sciences Temple University

Recent years have witnessed great progress of deep convolutional neural networks (DCNNs) for solving scene understanding tasks [1–3]. These advances prefer to construct deeper and larger net-

关键词： image An open-source project for real-time image semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Multi-class Bitcoin mixing service identification based on graph classification

引用

Digital Communications and networks 2024年第6期10卷 1881-1893页

作者： Xiaoyan Hu Meiqun Gui Guang Cheng Ruidong Li Hua Wu School of Cyber Science&Engineering Southeast UniversityNanjing 211189China Purple Mountain Laboratories for Network and Communication Security Nanjing 211111China Jiangsu Provincial Engineering Research Center of Security for Ubiquitous Network Nanjing 211189China Key Laboratory of Computer Network and Information Integration Southeast UniversityMinistry of EducationChina Research Base of International Cyberspace Governance Southeast UniversityNanjing 211189China Institute of Science and Engineering Kanazawa UniversityKakumaKanazawa920-1192Japan

Due to its anonymity and decentralization,Bitcoin has long been a haven for various illegal *** generally legalize illicit funds by Bitcoin mixing ***,it is critical to investigate the mixing services in cryptocurrency anti-money *** studies treat different mixing services as a class of suspicious Bitcoin ***,they are limited by relying on expert experience or needing to deal with large-scale *** far,multi-class mixing service identification has not been explored *** is challenging since mixing services share a similar procedure,presenting no sharp ***,mixing service identification facilitates the healthy development of Bitcoin,supports financial forensics for cryptocurrency regulation and legislation,and provides technical means for fine-grained blockchain *** paper aims to achieve multi-class Bitcoin Mixing Service Identification with a Graph Classification(BMSI-GC)***,BMSI-GC constructs 2-hop ego networks(2-egonets)of mixing services based on their historical ***,it applies graph2vec,a graph classification model mainly used to calculate the similarity between graphs,to automatically extract address features from the constructed ***,it trains a multilayer perceptron classifier to perform classification based on the extracted ***-GC is flexible without handling the full-size network and handcrafting address ***,the differences in transaction patterns of mixing services reflected in the 2-egonets provide adequate information for *** experimental study demonstrates that BMSI-GC performs excellently in multi-class Bitcoin mixing service identification,achieving an average identification F1-score of 95.08%.

关键词： Bitcoin Anti-money laundering Mixing service Ego network Graph classification

来源：评论

学校读者我要写书评

暂无评论

An Effective Differential Fault Analysis on the Serpent Cryptosystem in the Internet of Things

引用

China Communications 2014年第6期11卷 129-139页

作者： LI Wei TAO Zhi GU Dawu SUN Li QU Bo LIU Zhiqiang LIU Ya School of Computer Science and Technology Donghua University Department of Computer Science and Engineering Shanghai Jiao Tong University State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Shanghai Key Laboratory of Integrate Administration Technologies for Information Security Network Architectures and Services Delft University of Technology Mekelweg 4 2628 CD Delft The Netherlands ESAT/COSIC and IBBT Katholieke Universiteit Leuven Department of Computer Science and Engineering University of Shanghai for Science and Technology

Due to the strong attacking ability, fast speed, simple implementation and other characteristics, differential fault analysis has become an important method to evaluate the security of cryptosystem in the Internet of Things. As one of the AES finalists, the Serpent is a 128-bit Substitution-Permutation network(SPN) cryptosystem. It has 32 rounds with the variable key length between 0 and 256 bits, which is flexible to provide security in the Internet of Things. On the basis of the byte-oriented model and the differential analysis, we propose an effective differential fault attack on the Serpent cryptosystem. Mathematical analysis and simulating experiment show that the attack could recover its secret key by introducing 48 faulty ciphertexts. The result in this study describes that the Serpent is vulnerable to differential fault analysis in detail. It will be beneficial to the analysis of the same type of other iterated cryptosystems.

关键词： internet of things cryptanalysis differential fault analysis serpent.

来源：评论

学校读者我要写书评

暂无评论

Multi-threshold image segmentation through an improved quantum-behaved particle swarm optimization algorithm 1st

Multi-threshold image segmentation through an improved quant...

引用

1st International Conference on Cloud Computing and Security, ICCCS 2015

作者： Jiali, Wang Hongshen, Liu Yue, Ruan School of Computer Science Anhui University of Technology Maanshan243005 China School of Computer Science and Engineering Southeast University Nanjing210096 China Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University Nanjing210096 China

ISBN: (纸本)9783319270500

Multi-threshold segmentation is a basic and widely used technique in image segmentation. The key step of accomplishing this task is to find the optimal multi-threshold value, which in essence can be reduced to multi-objective optimization problem. The quantum particle-behaved swarm algorithm (QPSO) is an effective method to resolve the problem of this class. However in practice, we found the original QPSO has imperfections, such as the excessive dropping of the diversity of the population and trapping in local optimum. In order to improve the ability of searching the global optimum and accelerate the speed of convergence, we proposed an improved quantum-behaved particle swarm algorithm (IQPSO). The experiments showed that IQPSO was superior to PSO and QPSO on the searching of multi-threshold value in image segmentation under the premise of ensuring the accuracy of solutions. © Springer International Publishing Switzerland 2015.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Research on ECG classification based on transfer learning

引用

The Journal of China Universities of Posts and Telecommunications 2022年第6期29卷 83-96页

作者： Jiang Fan Chen Jiajun Gao Youjun Sun Changyin Shaanxi Key Laboratory of Information Communication Network and Security Xi'an University of Posts and TelecommunicationsXi'an 710121China China Mobile System Integration Co. Ltd.Beijing 100052China China Mobile Xiong'an Information Communication Technology Co. Ltd.Beijing 100052China

Concerning current deep learning-based electrocardiograph(ECG) classification methods, there exists domain discrepancy between the data distributions of the training set and the test set in the inter-patient paradigm. To reduce the negative effect of domain discrepancy on the classification accuracy of ECG signals, this paper incorporates transfer learning into the ECG classification, which aims at applying the knowledge learned from the training set to the test set. Specifically, this paper first develops a deep domain adaptation network(DAN) for ECG classification based on the convolutional neural network(CNN). Then, the network is pre-trained with training set data obtained from the famous Massachusetts Institute of Technology-Beth Israel Hospital(MIT-BIH) ECG arrhythmia database. On this basis, by minimizing the multi-kernel maximum mean discrepancy(MK-MMD) between the data distributions of the training set and the test set, the pre-trained network is adjusted to learn transferable feature representations. Finally, with the low-density separation of unlabeled target data, the feature representations are more transferable. The extensive experimental results show that the proposed domain adaptation method has reached a 7.58% improvement in overall classification accuracy on the test set, and achieves competitive performance with other state-of-the-arts.

关键词： electrocardiograph(ECG)classification transfer learning domain adaptation convolutional neural network(CNN)

来源：评论

学校读者我要写书评

暂无评论

Weakly Secure Summation with Colluding Users

引用

IEEE Transactions on information Theory 2025年

作者： Li, Zhou Zhao, Yizhou Sun, Hua Electronics and Information at Guangxi University Guangxi Key Laboratory of Multimedia Communications and Network Technology School of Computer Nanning530004 China Southwest University College of Electronic and Information Engineering Chongqing400715 China University of North Texas Department of Electrical Engineering DentonTX76203 United States

In secure summation, K users, each holds an input, wish to compute the sum of the inputs at a server without revealing any information about all the inputs even if the server may collude with an arbitrary subset of users. In this work, we relax the security and colluding constraints, where the set of inputs whose information is prohibited from leakage is from a predetermined collection of sets (e.g., any set of up to S inputs) and the set of colluding users is from another predetermined collection of sets (e.g., any set of up to T users). For arbitrary collection of security input sets and colluding user sets, we characterize the optimal randomness assumption, i.e., the minimum number of key bits that need to be held by the users, per input bit, for weakly secure summation to be feasible, which generally involves solving a linear program. © 1963-2012 IEEE.

关键词： Capacity Secure Summation Weak Security

来源：评论

学校读者我要写书评

暂无评论

Spectrum efficiency maximization with trajectory design in UAV-enabled mobile relaying

引用

The Journal of China Universities of Posts and Telecommunications 2019年第4期26卷 17-24页

作者： Sun Chuanzhi Hu Zhiqun Wen Xiangming Lu Zhaoming Qi Hang Beijing Laboratory of Advanced Information Networks Beijing University of Posts and TelecommunicationsBeijing 100876China Beijing Key Laboratory of Network System Architecture and Convergence Beijing University of Posts and TelecommunicationsBeijing 100876China School of Computer and Information Engineering Hubei UniversityWuhan 430062China

With the advantages of low cost and high mobility,unmanned aerial vehicles(UAVs)have played an important role in wireless *** investigate a UAV-enabled mobile relaying system,where a UAV is used as a mobile relay to assist in the communication from a ground source to a ground destination since their direct link is *** the conventional mobile relay in which the UAV adopts straight line or circular trajectory,we consider a more general elliptical trajectory and use realistic channel *** assuming that the UAV employs time-division duplexing(TDD)based decode-and-forward(DF)relaying,we jointly optimize the time allocations and the UAV trajectory to formulate the maximization of spectrum efficiency(SE).The simulation results show that the trajectory we designed achieves a higher SE than the optimal circular trajectory and static relaying.

关键词： UAV mobile relay time allocations elliptical trajectory

来源：评论

学校读者我要写书评

暂无评论

Qubit-Based Distributed Frame Synchronization for Quantum key Distribution

引用

Journal of Lightwave Technology 2024年第11期43卷 5032-5039页

作者： Chen, Ye Huang, Chunfeng Lin, Guangshen Huang, Shuyi Zhang, Zhenrong Wei, Kejin Guangxi University Guangxi Key Laboratory for Relativistic Astrophysics School of Physical Science and Technology Nanning530004 China Guangxi University Guangxi Key Laboratory of Multimedia Communications and Network Technology School of Computer Electronics and Information Nanning530004 China

Quantum key distribution (QKD) is a method that enables two remote parties to share a secure key string. Clock synchronization between two parties is a crucial step in the normal operation of QKD. Qubit-based synchronization can achieve clock synchronization by transmitting quantum states between two remote parties, eliminating the necessity for hardware synchronization and thereby greatly reducing the hardware requirements of a QKD system. Nonetheless, classical qubit-based synchronization exhibits poor performance in continuous and high-loss systems, hindering its wide applicability in various scenarios. Here, we propose a qubit-based distributed frame synchronization method that can achieve time recovery in a continuously running system and resist higher losses. Experimental results show that the proposed method outperforms the advanced qubit-based synchronization method Qubit4Sync in a continuously running system. Particularly, the results demonstrate that our method surpasses all previous works in key parameters, including frequency and the synchronization length. We believe our method is applicable to a broad range of QKD scenarios, including drone-based QKD and quantum network construction. © 1983-2012 IEEE.

关键词： Qubits

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：