检索结果-内蒙古大学图书馆

8th International Conference on Big Data and information Analytics, BigDIA 2022

作者： Qideng, Tang Chaofan, Dai National University of Defense Technology Science and Technology on Information Systems Engineering Laboratory Changsha China

ISBN: (数字)9781665487962

ISBN: (纸本)9781665487962

Fingerprint is one of the most widely used biometric features to identify a person. Fingerprint matching is to compare an input fingerprint with fingerprints within the database to find the most similar fingerprints. However, existing fingerprint matching technologies face two major challenges: data quantity and data quality. From the perspective of data quantity, the existing fingerprint database stores hundreds of millions of data, so the traditional iterative matching method is not practical due to huge time consumption. From the data quality point, existing fingerprint products have a small collection area for aesthetics and portability, resulting in a low quality of the captured finger-print image, which seriously affects the accuracy of the matching algorithms. To address the above problems, we present a two-stage fingerprint matching method, which not only improves the efficiency of fingerprint matching, but also ensures the accuracy of fingerprint matching. The first stage utilizes a convolutional neural network trained with triplet loss to extract the overall feature of a fingerprint image. The cosine similarity between features can be used to identify possible fingerprint matches. The second stage compares fingerprint matches acquired in the first stage using a minutiae points comparing algorithm to get a more precise result. The experiment result shows that our method is satisfactory in both speed and accuracy. © 2022 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Research on Trusted Data Sharing Method for Multi-party Edge Terminals

Research on Trusted Data Sharing Method for Multi-party Edge...

引用

2022 IEEE International Conference on Unmanned systems, ICUS 2022

作者： Pan, Yongqi Cheng, Ziwen Liu, Yi Wang, Bowen Wang, Wenhao Zhu, Cheng National University of Defense Technology Science and Technology on Information Systems Engineering Laboratory Changsha China

ISBN: (数字)9781665484565

ISBN: (纸本)9781665484565

In recent years, Internet of Things technology (IoT) has developed rapidly and is widely used in various fields including military. The modern warfare has a new operational style of precision strike and targeted killing, among which is supported by IoT. However, during such operations, communication is not disrupted and data transmission and distribution are carried out through a centralized mode. While warfare environments are often communication constrained, with central servers facing disconnection or attack. In this study, we develop a multi-party edge terminal data sharing scheme based on blockchain technology, which improves the security and robustness of data sharing. What's more, the paper proposes a double chain storage mechanism, which improves the data sharing efficiency to a certain extent. In this paper, the proposed scheme is applied to a certain scenario for the simulation experiment. The experimental results show that the scheme can effectively support data sharing and provide a basis for the construction of reconnaissance and strike integration system. © 2022 IEEE.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

Ontology-Based APT Attack Detection and Defense Countermeasures 4

Ontology-Based APT Attack Detection and Defense Countermeasu...

引用

4th International Conference on High Performance Big Data and Intelligent systems, HDIS 2022

作者： Wang, Fei Liu, Kai Ding, Zhaoyun Liu, Bin Zhao, Yu National University of Defense Technology Science and Technology on Information Systems Engineering Laboratory Changsha China

ISBN: (数字)9781665491440

ISBN: (纸本)9781665491440

Cyberspace security has risen to the height of national strategies, represented by APT attacks, threatening important industries in various countries. In order to ensure cyberspace security, it is urgent to develop situational awareness of APT attacks. In view of the multi-step attack characteristics of APT, this paper proposes a series of questions that need to be answered in cyberspace threat situational awareness, and constructs the APT attack ontology. And through the representation and reasoning of a case, the consistency and effectiveness of the APT attack ontology are verified. It is proved that the ontology can realize the automatic correlation and reasoning of APT attack multi-source intelligence, find the weaknesses and loopholes exploited by each step of the attack, and deduce the corresponding mitigation measures. At the same time, we will find the causal relationship between various weaknesses and mitigation measures, and provide support for the auxiliary decision-making of country's cyberspace asset protection. © 2022 IEEE.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Integrating R-Drop and Pre-trained Language Model for Short Text Classification 8

Integrating R-Drop and Pre-trained Language Model for Short ...

引用

8th International Conference on Big Data and information Analytics, BigDIA 2022

作者： Liu, Dengfeng Cai, Fei Pan, Zhiqiang Zheng, Jianming Mao, Yanying Wang, Mengru Science and Technology on Information Systems Engineering Laboratory National University of Defense Technology Changsha China

ISBN: (数字)9781665487962

ISBN: (纸本)9781665487962

At present, the rapid development of computer technology has led to the emergence of massive short text data represented by e-commerce user comments. Due to the sparse feature and fast update speed of short text data, effective classification methods of short text have been widely concerned and applied. In this paper, a short text classification method integrating R-Drop and pre-trained language model IRDP-STC is proposed. The original data and generated data are input into the pre-trained language model Bert with Dropout, and KL divergence loss is added to approximate the two outputs. IRDP-STC makes full use of short text information, takes into account the robustness of the model on the basis of ensuring the high classification performance of the model, and is more suitable for low training sample scenarios. The experimental results on THUCNews dataset are better than the baseline model, which verifies the effectiveness and universality of the proposed method. © 2022 IEEE.

关键词： Drops

来源：评论

学校读者我要写书评

暂无评论

Protecting Multi-Domain Command and Control information System Network Traffic with Segment Routing 1

引用

10th China Conference on Command and Control, C2 2022

作者： Yuan, Zongyang Chen, Tao Ren, Bangbang Luo, Lailong The Science and Technology on Information Systems Engineering Laboratory National University of Defence Technology Changsha China

ISBN: (数字)9789811960529

ISBN: (纸本)9789811960512

In the Multi-Domain Command and Control information System (MDCCIS), data security and privacy protection play key roles in improving network security. However, some network devices may be illegally hijacked, which may result in data leakage. To solve this problem, Avoidance Routing (AR) which bypasses the untrusted network devices has been proposed to protect the traffic. However, existing methods have to deploy agent nodes in the network, which confines the selection of routing paths and degrades the flexibility of the network Recently, a new source routing technology, Segment Routing (SR), has been proposed to steer flows along any path as network operators expected. In this paper, we leverage a new mechanism of SR to find proper avoidance routing paths for traffic protection. We formulate this problem as an integer programming model and propose two algorithms to get a feasible solution with different security Service Level Agreement (SLA) constraints. Experimental results show that our C-SAR algorithm protects the traffic with a 95 % success rate in low-risk networks and the P-SAR algorithm can realize a 50 % success rate even in uncertain networks. © 2022, Chinese Institute of Command and Control.

关键词： Integer programming

来源：评论

学校读者我要写书评

暂无评论

Brain-Conditional Multimodal Synthesis: A Survey and Taxonomy

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第5期6卷 1080-1099页

作者： Mai, Weijian Zhang, Jian Fang, Pengfei Zhang, Zhijun South China University of Technology School of Automation Science and Engineering Guangzhou510640 China Southeast University School of Computer Science and Engineering Nanjing210096 China South China University of Technology Key Library of Autonomous Systems and Network Control Ministry of Education The School of Automation Science and Engineering Guangzhou510640 China Institute for Super Robotics Huangpu Guangzhou510555 China Nanchang University Jiangxi Thousand Talents Plan Nanchang330031 China Jishou University College of Computer Science and Engineering Jishou416000 China Guangdong Artificial Intelligence and Digital Economy Laboratory Pazhou Lab Guangzhou510335 China Shaanxi University of Technology Shaanxi Provincial Key Laboratory of Industrial Automation School of Mechanical Engineering Hanzhong723001 China Changsha Normal University School of Information Science and Engineering Changsha410100 China Guangdong University of Petrochemical Technology School of Automation Science and Engineering Institute of Artificial Intelligence and Automation Maoming525000 China

In the era of artificial intelligence generated content (AIGC), conditional multimodal synthesis technologies (e.g., text-to-image) are dynamically reshaping the natural content. Brain signals, serving as potential reflections of how the brain interprets external information, exhibit a distinctive one-to-many correspondence with various external modalities. This correspondence makes brain signals emerge as a promising guiding condition for multimodal synthesis (e.g., image, text, and audio), which is crucial for developing practical brain–computer interface systems and unraveling complex mechanisms underlying human perception. This survey comprehensively examines the emerging field of brain-conditional multimodal synthesis, termed AIGC-brain, to delineate the current landscape and future directions. To begin, related neuroimaging datasets and generative models are introduced as the foundation of AIGC-brain decoding and analysis. Next, we present a comprehensive taxonomy according to AIGC-brain methodologies, followed by task-specific representative work and implementation details to facilitate in-depth comparison and analysis. Quality assessments are then introduced for both qualitative and quantitative evaluation. Finally, this survey explores insights gained, outlining current challenges and prospects of AIGC-brain. As a pioneering survey, this article paves the way for future advances in AIGC-brain research. © 2020 IEEE.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

VFLChain: Blockchain-enabled Vertical Federated Learning for Edge Network Data Sharing

VFLChain: Blockchain-enabled Vertical Federated Learning for...

引用

2022 IEEE International Conference on Unmanned systems, ICUS 2022

作者： Cheng, Ziwen Pan, Yongqi Liu, Yi Wang, Bowen Deng, Xin Zhu, Cheng National University of Defense Technology Science and Technology on Information Systems Engineering Laboratory Changsha China

ISBN: (数字)9781665484565

ISBN: (纸本)9781665484565

With the widespread use of Internet of things(IoT), a large amount of data will be generated in the edge of network, which can facilitate a significant transformation in edge intelligent services by integrating with edge computing, 5G and artificial intelligence. However, since the intelligent edge services seriously rely on big data and computing resource, it challenges the traditional centralized data processing model. Data sharing is a promising way to tackle this problem, but some critical technical challenges still remain, such as fragile data privacy protection, inefficient data exchange and low quality of data fusion. To address these problems, a privacy-enhanced and intelligence-preserved data sharing system, name VFLChain, is proposed in this article. The proposed VFLChain is designed based on consortium blockchain and vertical federated learning, which can ensure trustworthy and secure data sharing without relying on any center platforms or third parties. Furthermore, a blockchain-assisted decentralized vertical federated learning is presented to adapt to the decentralized system and support privacy-preserved, intelligent and efficient edge data sharing, while improving quality of data through learning with different characteristic data samples. Then, a data sharing processing workflow in VFLChain is also described to demonstrated details of data sharing. The simulation experiments confirm that the proposed system and mechanism have good accuracy and stability, and guarantee an effective data sharing. © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Cascading Dynamics of Invulnerable Complex Networks Based on Markov Decision

Cascading Dynamics of Invulnerable Complex Networks Based on...

引用

2022 International Conference on Machine Learning, Cloud Computing and Intelligent Mining, MLCCIM 2022

作者： Wang, Siyuan Cai, Fei Science and Technology on Information Systems Engineering Laboratory National University of Defense Technology Changsha China

ISBN: (数字)9781665498586

ISBN: (纸本)9781665498586

This paper proposes a new cascading failure model that introduces a transition probability matrix in Markov Decision to characterize the dynamic process of load flow. And following the inherent logic of betweenness centrality, the degree of nodes and the distance between nodes are used to define the initial load distribution of edges in the network, which satisfies the actual load migration preference and load conservation law. The model is tested on nine actual and artificial networks, the effectiveness and generalization of which have been verified. In addition, we found the intrinsic relationship between cascading failures and network capacity, and the existence of a cascading failures threshold, from which some enlightenments are obtained for the invulnerability of realistic complex networks. © 2022 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Backtracing Social Events of Interest via Logical Correlation Using GDELT 9

Backtracing Social Events of Interest via Logical Correlatio...

引用

9th International Conference on Big Data and information Analytics, BigDIA 2023

作者： Zhao, Dongxu Zhang, Xin Pan, Yan Shi, Honglin Qian, Liwei Yang, Guang National University of Defense Technology Science and Technology on Information Systems Engineering Laboratory Changsha China National University of Defense Technology Laboratory for Big Data and Decision Changsha China National University of Defense Technology College of Systems Engineering Changsha China

ISBN: (纸本)9798350330076

In response to the inability of mainstream methods in existing social event backtracing studies to address the logical correlation problem, the insufficient and inaccurate utilization of event characteristics for implementing logical association backtracing events, we propose a backtracing method for social events of interest. The basic idea is to obtain a set of related events given a small amount of labeled data on interested events, and to construct the causal chain of event occurrence through their merging and fusion. Specifically, we design a node feature construction strategy to select topic and title information from various elements of events to construct node features, thereby addressing the problem of insufficient and inaccurate node feature composition. We also design an adjacency relationship construction strategy, which uses the co-occurrence of participants in event records as the basis for constructing adjacency relationships, and completes the final construction of adjacency relationships by considering time elements comprehensively, thereby resolving the problem of inaccurate construction of inter-event correlation relationships. We construct a multi-layer graph convolutional network to learn the associated features and achieve node classification through a normalization function, thereby solving the problem of logical association inference between events. Experimental results demonstrate that LC-BTE is effective in backtracing analysis of events related to social events of interest. Additionally, this paper explores the performance changes of the method under semi-supervised mode and conducts experimental analysis. Finally, this paper provides the causal chain of events based on the backtracing results. © 2023 IEEE.

关键词： backtracing GDELT logical correlation social events

来源：评论

学校读者我要写书评

暂无评论

Real-time road occupancy and traffic measurements using unmanned aerial vehicle and fundamental traffic flow diagrams

引用

Personal and Ubiquitous Computing 2023年第5期27卷 1669-1680页

作者： Ahmed, Afzal Outay, Fatima Farooq, Muhammad Umer Saeed, Sehrish Adnan, Muhammad Ismail, Muhammad Ali Qadir, Adnan Department of Urban & Infrastructure Engineering NED University of Engineering & Technology Karachi Pakistan Zayed University Dubai United Arab Emirates Department of Computer Science and Information Technology NED University of Engineering & Technology Karachi Pakistan Exascale Open Data Analytics Lab NED University of Engineering & Technology Karachi Pakistan Hasselt University Diepenbeek Belgium

The technologies and sensors developed for standard traffic streams often fail to accurately measure the heterogeneous traffic with no lane discipline. This research proposes an efficient framework to measure traffic flow parameters in real-time using an unmanned aerial vehicle (UAV). The proposed framework in this research estimates road area occupancy from the images extracted from the video recorded using a UAV by applying the image segmentation technique. The road area occupancy is converted into traffic density using an occupancy-density model developed for the local heterogeneous traffic. A speed-density fundamental diagram is developed, which estimates the average speed corresponding to the measured traffic density. The fundamental relation between flow rate, average speed, and density is applied to compute traffic flow rate using the estimated average speed and density. The proposed framework is computationally less demanding in comparison with other computer vision and artificial intelligence–based techniques. The proposed framework accurately measured road area occupancy with an average accuracy of 97.6%. Traffic density was measured with an average accuracy of 88.8%. Similarly, the average speed and flow rate were measured with an average accuracy of 85.4% and 84.2%, respectively. © 2023, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature.

关键词： Image segmentation

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：