检索结果-内蒙古大学图书馆

CBA: multi source fusion model for fast and intelligent target intention identification

Journal of Systems Engineering and Electronics 2024年第2期35卷 406-416页

作者： WAN Shichang LI Qingshan WANG Xuhua LU Nanhua School of Computer Science and Technology Xidian UniversityXi’an 710071China School of Mathematics and Computer Application Shangluo UniversityShangluo 726000China

How to mine valuable information from massive multisource heterogeneous data and identify the intention of aerial targets is a major research focus at present. Aiming at the longterm dependence of air target intention recognition, this paper deeply explores the potential attribute features from the spatiotemporal sequence data of the target. First, we build an intelligent dynamic intention recognition framework, including a series of specific processes such as data source, data preprocessing,target space-time, convolutional neural networks-bidirectional gated recurrent unit-atteneion (CBA) model and intention recognition. Then, we analyze and reason the designed CBA model in detail. Finally, through comparison and analysis with other recognition model experiments, our proposed method can effectively improve the accuracy of air target intention recognition,and is of significance to the commanders’ operational command and situation prediction.

关键词： intention massive data deep network artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based open API recommendation for Mashup development

引用

Science China(Information Sciences) 2023年第7期66卷 94-111页

作者： Ye WANG Junwu CHEN Qiao HUANG Xin XIA Bo JIANG School of Computer and Information Engineering Zhejiang Gongshang University Software Engineering Application Technology Lab

Mashup developers often need to find open application programming interfaces(APIs) for their composition application development. Although most enterprises and service organizations have encapsulated their businesses or resources online as open APIs, finding the right high-quality open APIs is not an easy task from a library with several open APIs. To solve this problem, this paper proposes a deep learning-based open API recommendation(DLOAR) approach. First, the hierarchical density-based spatial clustering of applications with a noise topic model is constructed to build topic models for Mashup clusters. Second,developers' requirement keywords are extracted by the Text Rank algorithm, and the language model is built. Third, a neural network-based three-level similarity calculation is performed to find the most relevant open APIs. Finally, we complement the relevant information of open APIs in the recommended list to help developers make better choices. We evaluate the DLOAR approach on a real dataset and compare it with commonly used open API recommendation approaches: term frequency-inverse document frequency, latent dirichlet allocation, Word2Vec, and Sentence-BERT. The results show that the DLOAR approach has better performance than the other approaches in terms of precision, recall, F1-measure, mean average precision,and mean reciprocal rank.

关键词： Mashup development open API recommendation deep learning neural network service discovery

来源：评论

学校读者我要写书评

暂无评论

Heap Memory Vulnerability Detection and Protection in Embedded Real-Time Operating Systems 24

Heap Memory Vulnerability Detection and Protection in Embedd...

引用

8th International Conference on Electronic Information technology and computer Engineering, EITCE 2024

作者： Zhang, Jinyuan Yao, Rui Zhang, Yang Beijing Institute of Computer Technology and Application Beijing China

ISBN: (纸本)9798400710094

In application software development, memory defects are difficult to detect. Traditional memory defect detection tools generally face issues of high performance overhead and excessive memory consumption, which limits their applicability in embedded operating systems. To address this, a method called EHD (Embedded Heap Detect) is proposed. This method combines memory defect detection technology with the memory management mechanisms of embedded operating systems to effectively and quickly detect heap memory vulnerabilities, selecting appropriate times for detection to reduce the number of detections and lower performance overhead. © 2024 Copyright held by the owner/author(s).

关键词： Dynamic Detection

来源：评论

学校读者我要写书评

暂无评论

UniTrans:Unified Parameter-Efficient Transfer Learning and Multimodal Alignment for Large Multimodal Foundation Model

引用

computers, Materials & Continua 2025年第4期83卷 219-238页

作者： Jiakang Sun Ke Chen Xinyang He Xu Liu Ke Li Cheng Peng Chengdu Institute of Computer Application Chinese Academy of SciencesChengdu610213China School of Computer Science and Technology University of Chinese Academy of SciencesBeijing101499China

With the advancements in parameter-efficient transfer learning techniques,it has become feasible to leverage large pre-trained language models for downstream tasks under low-cost and low-resource ***,applying this technique to multimodal knowledge transfer introduces a significant challenge:ensuring alignment across modalities while minimizing the number of additional parameters required for downstream task *** paper introduces UniTrans,a framework aimed at facilitating efficient knowledge transfer across multiple *** leverages Vector-based Cross-modal Random Matrix Adaptation to enable fine-tuning with minimal parameter *** further enhance modality alignment,we introduce two key components:the Multimodal Consistency Alignment Module and the Query-Augmentation Side Network,specifically optimized for scenarios with extremely limited trainable *** evaluations on various cross-modal downstream tasks demonstrate that our approach surpasses state-of-the-art methods while using just 5%of their trainable ***,it achieves superior performance compared to fully fine-tuned models on certain benchmarks.

关键词： Parameter-efficient transfer learning multimodal alignment image captioning image-text retrieval visual question answering

来源：评论

学校读者我要写书评

暂无评论

Research of Military Cyber Operation Forensic and Analysis in Russia-Ukraine Conflict 24

Research of Military Cyber Operation Forensic and Analysis i...

引用

24th IEEE International Conference on Software Quality, Reliability and Security Companion, QRS-C 2024

作者： Liu, Shiyu Li, Dongfang Yang, Guang Su, Mingyue Shen, Wei Beijing Institute of Computer Technology and Application Beijing China

ISBN: (纸本)9798350365658

The Russia-Ukraine conflict represents the first regional military confrontation between major (and external) powers that is thoroughly interspersed with cyber operations throughout the main military theater. In essence, the conflict has served as a testing ground for examining the impact of cyber actions on military operations, with its characteristics in cyber forensics and analysis yet to be fully explored. Firstly, this paper delves into the cyber operations and typical military cyber actions observed in the Russia-Ukraine conflict. Secondly, drawing upon the report issued by the Ukrainian National Security Service titled 'Cyber Operation Of Russian Intelligence Services As A Component Of Confrontation On The Battlefield,' this paper conduct a study on the forensic investigation and analysis of these typical military cyber actions. Lastly, this paper summarizes the characteristics of military cyber actions and their forensic analysis in the Russia-Ukraine conflict, highlighting the challenges faced in cyber forensics in a real-world war scenario. © 2024 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Research on the Impact of Tester's Technical and Cognitive Factors on Aerospace Software Test Quality 24

Research on the Impact of Tester's Technical and Cognitive F...

引用

24th IEEE International Conference on Software Quality, Reliability and Security Companion, QRS-C 2024

作者： Hu, Yadi Tao, Jinlong Liang, Yu Xu, Zhewei Jia, Zhangtao Beijing Institute of Computer Technology and Application Beijing China

ISBN: (纸本)9798350365658

This paper primarily analyzes the impact of tester capabilities on the quality of aerospace software testing and elaborates on how to assess tester abilities from both technical and cognitive perspectives. The research was supported by the Aerospace Software Testing Center of the China Aerospace Science and Industry Corporation (CASIC), which allowed researchers to collect data on the center's testing personnel and conduct interviews with relevant testers. The findings of this research have been used by the center to coordinate the efforts to improve quality and human resource management. This paper provides valuable insights and guidance for the field of aerospace software testing, contributing to the enhancement of tester capabilities and software testing quality, and ultimately promoting the reliability and safety of aerospace software. © 2024 IEEE.

关键词： Software reliability

来源：评论

学校读者我要写书评

暂无评论

A Efficient DNN Sparsity Framework with Data Pruning and Auxiliary Network 5

A Efficient DNN Sparsity Framework with Data Pruning and Aux...

引用

5th International Conference on Artificial Intelligence and computer Engineering, ICAICE 2024

作者： Guo, Enping Beijing Institute of Computer Technology and Application Beijing China

ISBN: (纸本)9798331528911

Model compression frequently leverages model pruning, an approach aimed at minimizing neural network size without compromising performance. Prior research has demonstrated the effectiveness of iterative pruning combined with retraining in producing high-quality compressed models. To gain insights into how the training set size influences the pruned model's generalization capability, we undertake an investigation that can facilitate rapid and efficient deep model pruning. Consequently, we devise a dual-model architecture that harnesses the synergy between two models to carry out simultaneous model pruning and coreset selection. Specifically, model pruning guided by an entropy-based criterion is adopted within this framework. The primary model is tasked with creating a pruned version and generating signals for selecting a retraining subset. Meanwhile, the secondary model plays a dual role: it provides supervisory signals via knowledge distillation to aid in training the primary model and offers subset selection insights during the final fine-tuning phase. We evaluate our approach using two popular backbone networks, namely ResNet and Swin Transformer, across two benchmark datasets: CIFAR-10 and Tiny-ImageNet. The outcomes validate that our framework successfully prunes a dense model while preserving the accuracy of the resultant pruned model. © 2024 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Adaptive coupled-sliding-variable-based finite-time control of composite formation for multi-robot systems

引用

Science China(Information Sciences) 2024年第10期67卷 244-260页

作者： Xinru MA Hengyu LI Jun LIU Yueying WANG Shaorong XIE Jun LUO School of Mechatronic Engineering and Automation Shanghai University School of Mathematics and Computer Application Technology Jining University School of Computer Science Shanghai University College of Mechanical and Vehicle Engineering Chongqing University

This paper focuses on the finite-time control(FTC) of the composite formation consensus(CFC)problems for multi-robot systems(MRSs). The CFC problems are firstly proposed for MRSs under the complex network topology of cooperative or cooperative-competitive networks. Regarding the problems of FTC and CFC on multiple Lagrange systems(MLSs), coupled sliding variables are introduced to deal with the robustness and consistent convergence. Then, the adaptive finite-time protocols are given based on the displacement approaches. With the premised FTC, tender-tracking methods are further developed for the problems of tracking information disparity. Stability analyses of those MLSs mentioned above are clarified with Lyapunov candidates considering the coupled sliding vectors, which provide new verification for tender-tracking systems. Under the given coupled-sliding-variable-based finite-time protocols, MLSs distributively adjust the local formation error to achieve global CFC and perform uniform convergence in time-varying tracking. Finally, simulation experiments are conducted while providing practical solutions for the theoretical results.

关键词： composite formation time-vary tracking information disparity tender-tracking finite-time control nonlinear robots complex networks symmetry consensus

来源：评论

学校读者我要写书评

暂无评论

Platform-specific code generation method for the tyche embedded operating system based on AADL models 3

Platform-specific code generation method for the tyche embed...

引用

3rd International Conference on Algorithms, Network, and Communication technology, ICANCT 2024

作者： Chen, Li Jia, Zhangtao An, Heng Li, Haoyu Beijing Computer Technology and Application Research Institute Beijing China

ISBN: (数字)9781510688902

ISBN: (纸本)9781510688896

The Tyche Embedded Operating System is a highly customized real-time embedded operating system, widely applied in fields such as aerospace, medical devices, and industrial automation. Renowned for its robust support for real-time tasks and efficient resource management, this system has become a core technology in embedded system development. The Architecture Analysis and Design Language (AADL), as a stringent standardized modeling language, possesses powerful expressiveness and scalability. This paper proposes a method for generating platform-specific code for the Tyche Embedded Operating System based on AADL models, which involves describing complex systems through AADL modeling and generating safety-critical software suitable for the Tyche Embedded Operating System. Firstly, the paper elaborates on the key aspects of the AADL standard and adheres to these aspects for modeling safety-critical systems. Secondly, an intermediate layer is introduced, outlining the mapping rules from the AADL common subset to the intermediate code, generating intermediate code for each component within the system architecture, and ultimately compiling it into C code applicable to the Tyche platform. Finally, a prototype tool for code generation is provided, and the effectiveness of the proposed method is validated through a case study of a temperature control system. © 2025 SPIE.

关键词： Program compilers

来源：评论

学校读者我要写书评

暂无评论

A Blockchain-Based Key Management Scheme in FANETs 4

A Blockchain-Based Key Management Scheme in FANETs

引用

4th International Conference on Electronic Information Engineering and computer Science, EIECS 2024

作者： Yin, Datong Han, Lei Beijing Institute of Computer Technology and Application Beijing China

ISBN: (纸本)9798331531409

Flying Ad-Hoc Networks (FANETs) enable the deployment of Unmanned aerial vehicles (UAVs) in a clustered manner to execute complex missions, yet their inherent openness poses significant challenges to communication security. However, as a crucial part of ensuring communication security, most existing FANET key management schemes rely on base stations or other infrastructures. This reliance not only complicates communication between UAVs and base stations but also makes the system vulnerable to single point of failure. To address these issues, we introduce a key management scheme based on Blockchain. This scheme in-tegrates the key tree with the secret sharing scheme, which achieves the autonomous generation and updating of group keys, the dynamic joining or exiting of UAVs, and the withdraw of malfunctioning UAVs. Security and performance analyses demonstrate that our scheme effectively resists a variety of security threats, exhibits lower computational overhead and energy consumption compared to similar schemes, making it well-suited for heterogeneous FANET environments. © 2024 IEEE.

关键词： Unmanned aerial vehicles (UAV)

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：