检索结果-内蒙古大学图书馆

6th International Conference on Robotics, Intelligent Control and Artificial Intelligence, RICAI 2024

作者： Xiong, Rongling National Key Laboratory of Complex Aviation System Simulation Chengdu610036 China The 10th Research Institute of China Electronics Technology Group Corporation Chengdu610036 China

ISBN: (纸本)9798331541699

Specific emitter identification plays a pivotal role in electronic countermeasures within the realm of complex electromagnetic environments. This study introduces a novel method for specific emitter identification, leveraging the capabilities of BiGRU-Attention (BiGRU-Att). The process begins with the segmentation of steady-state signal slices from the targeted emitter. Subsequently, six distinct features, including wavelet entropy and amplitude skewness within the time-frequency domain, are meticulously extracted. These extracted sequence feature data are then employed to train the model, culminating in the acquisition of the identification outcome. The methodology was rigorously tested using TETRA communication signals from nine distinct emitters. Experimental findings affirm that the model proficiently harnesses the timing information inherent in the specific emitter's signal, substantially enhancing the identification accuracy. This approach not only underscores the effectiveness of integrating BiGRU and attention mechanisms for signal classification but also sets a precedent for future research in specific emitter identification under intricate electromagnetic conditions. © 2024 IEEE.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Security Analysis Framework Based on Threat Matrix 8

Machine Learning Security Analysis Framework Based on Threat...

引用

8th International Conference on Data science in Cyberspace, DSC 2023

作者： Li, Hu Ma, Qiongmin Zhang, Ming Kuang, Xiaohui National Key Laboratory of Science and Technology on Information System Security Beijing China National Key Laboratory for Complex Systems Simulation Beijing China

ISBN: (纸本)9798350331035

Machine Learning and Artificial Intelligence technology accelerates technological progress and promotes social development, but also brings many security problems. Machine learning models may be affected, deceived, controlled or destroyed at different stages, e.g. training and inference, which may lead to serious consequences. In view of the main stages of the life cycle of machine learning, we summarizes the related attack and defense technologies based on threat matrix, makes a comprehensive and systematic analysis on the security issues of machine learning, and puts forward several security protection suggestions for intelligent information systems. © 2023 IEEE.

关键词： Artificial Intelligence Machine Learning Security Analysis Threat Matrix

来源：评论

学校读者我要写书评

暂无评论

Network Security Situation Prediction Based on TCAN-BiGRU Optimized by SSA and IQPSO

引用

Computer systems science & Engineering 2023年第10期47卷 993-1021页

作者： Junfeng Sun Chenghai Li Yafei Song Peng Ni Jian Wang College of Air and Missile Defence Air Force Engineering UniversityXi’an710051China Science and Technology on Complex Aviation Systems Simulation Laboratory Beijing100076China

The accuracy of historical situation values is required for traditional network security situation prediction(NSSP).There are discrepancies in the correlation and weighting of the various network security *** solve these problems,a combined prediction model based on the temporal convolution attention network(TCAN)and bi-directional gate recurrent unit(BiGRU)network is proposed,which is optimized by singular spectrum analysis(SSA)and improved quantum particle swarmoptimization algorithm(IQPSO).This model first decomposes and reconstructs network security situation data into a series of subsequences by SSA to remove the noise from the ***,a prediction model of TCAN-BiGRU is established respectively for each *** uses the TCN to extract features from the network security situation data and the improved channel attention mechanism(CAM)to extract important feature information from *** learns the before-after status of situation data to extract more feature information from sequences for ***,IQPSO is proposed to optimize the hyperparameters of ***,the prediction results of the subsequence are superimposed to obtain the final predicted *** the one hand,IQPSO compares with other optimization algorithms in the experiment,whose performance can find the optimum value of the benchmark function many times,showing that IQPSO performs *** the other hand,the established prediction model compares with the traditional prediction methods through the simulation experiment,whose coefficient of determination is up to 0.999 on both sets,indicating that the combined prediction model established has higher prediction accuracy.

关键词： Network security situation prediction SSA IQPSO TCAN-BiGRU

来源：评论

学校读者我要写书评

暂无评论

Recommendation Based on Knowledge Graph and Graph Neural Network 7th

Recommendation Based on Knowledge Graph and Graph Neural Net...

引用

7th Chinese Conference on Swarm Intelligence and Cooperative Control, CCSICC 2023

作者： Shen, Hongjie Guo, Qiuhao Xu, Hongfeng Jiang, Jixiang Chen, Linxiu Zhejiang Huzhou Aviation Intelligent Technology Research Center Hangzhou310000 China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

ISBN: (纸本)9789819733231

The recommendation system based on knowledge graph assistance has more advantages than the traditional recommendation system, mainly reflected in: accurate, efficient and explainable. Most of the recommendation methods of existing studies use knowledge graph representation learning for information mining of entity features, but some of them ignore the neighborhood information of knowledge graph entities, resulting in the loss of high-order feature information. Considering the above problem, this study proposes a recommendation method based on graph neural network for the problem that the existing recommendation methods ignore the overall information in the process of knowledge graph entity information mining. The graph attention network is introduced to carry out neighborhood information aggregation to make up for the neighborhood information of missing entities in the process of extracting the features of the knowledge graph in existing research. In this study, the prediction experiments of click rate and top-k recommendation scenarios were carried out on the data under the four backgrounds of movies, books, online courses and music, and the influence of some key parameters and structures in the model on the model was analyzed, compared and discussed. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

An efficient adaptive space partitioning algorithm for electromagnetic scattering calculation of complex 3D models

引用

Journal of systems Engineering and Electronics 2021年第5期32卷 1071-1082页

作者： HUANG Minjie ZHOU Yaoming WANG Yongchao LIU Zhongtie School of Aeronautic Science and Engineering Beihang UniversityBeijing 100191China Key Laboratory of Complex Aviation System Simulation Beijing 100076China

The space partitioning algorithm based on the rounding and addressing operations has been proved to be an efficient space partitioning algorithm with the potential for real-time *** improvement on this kind of space partitioning algorithms for solving complex 3D models is *** examples show that the efficiency of the improved algorithm is better than that of the original *** the size of most target elements is smaller than the size of spatial grids,the efficiency of the improved method can be more than four times of that of the original *** adaptive method of space partitioning based on the improved algorithm is developed by taking the surface element density or the curvature as the threshold for deep partitioning and conducting the deep partitioning using the octree method.A computer program implementation for applying the method in some typical applications is discussed,and the performance in terms of the efficiency,reliability,and resource use is *** testing shows that the results of the adaptive spacing partitioning are more convenient for the follow-up use than that of the basic uniform space ***,when it is used to calculate the electromagnetic scattering of complex targets by the ray tracing(RT)method,the adaptive space partitioning algorithm can reduce the calculation time of the RT process by more than 40%compared with the uniform space segmentation algorithm.

关键词： adaptive space partitioning computer graphics binary space partitioning ray tracing(RT)method stealth technology

来源：评论

学校读者我要写书评

暂无评论

Agent Optimization Decision-making Method Based on Self-Play

Agent Optimization Decision-making Method Based on Self-Play

引用

2024 IEEE International Conference on Unmanned systems, ICUS 2024

作者： Duan, Chunyi Xiong, Rongling Zhang, Luyou Ran, Huaming Yang, Qing National Key Laboratory of Complex Aviation System Simulation China Electronics Technology Group Corporation Tenth Research Institute Chengdu China Unit 93216 People's Liberation Army of China Beijing China

ISBN: (纸本)9798350384185

Aiming at the problem that the traditional deep reinforcement learning algorithm has poor generalization ability of generating strategies when solving complex game problems such as real-time strategy games, an agent strategy optimization method based on the combination of expert knowledge and self-play is ***, the opponent strategy of the agent is designed based on expert knowledge, and the corresponding strategy is generated by the proximal policy optimization algorithm (PPO), and the generated strategy is continuously put into the opponent strategy pool to provide a variety of opponent strategies for the agent in the training *** continuous iterative confrontation, the agent's autonomous decision-making ability in the face of different opponent strategies is *** simulation results show that compared with the traditional deep reinforcement learning algorithm, the introduction of the self-play training framework can significantly improve the average confrontation rate of the agent strategy, improve the robustness and generalization ability of the agent confrontation strategy, guide the agent to learn more effective tactical strategy, and achieve the adversarial advantage of "Priority first enemy discovery, Priority enemy launch". © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A credibility allocation approach of complex simulation systems 35

A credibility allocation approach of complex simulation syst...

引用

35th European Modeling and simulation Symposium, EMSS 2023

作者： Zhang, Huan Li, Wei Geng, HuaPin Ma, Ping Yang, Ming Control and Simulation Center Harbin Institute of Technology Harbin150080 China National Key Laboratory of Modeling and Simulation for Complex Systems Harbin150080 China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

ISBN: (纸本)9788885741881

complex simulation systems usually need to satisfy the credibility requirements and the credibility of complex simulation systems is inextricably linked to the credibility of simulation sub-systems. Hence, in order to guarantee the credibility of complex simulation systems meets requirements, it is necessary to allocate the credibility of simulation sub-systems. complex simulation systems are composed of several correlative simulation sub-systems and their credibility has correlation relationships, which makes it difficult to obtain the credibility of simulation sub-systems quickly. The existing works mostly ignore the relationships between the sub-systems and are difficult to generate the credibility allocation results of simulation sub-systems. In this paper, we model the credibility allocation problem as a probabilistic inference problem based on the pairwise Markov random field (PMRF). In addition, we apply several inference algorithms to perform the inference exactly and approximately in the credibility PMRF. Finally, experiments are conduted on the air defense combat complex simulation system, and the experiment results demonstrate that the proposed method can obtain the credibility allocation results quickly and accurately. © 2023 The Authors.

关键词： Inference engines

来源：评论

学校读者我要写书评

暂无评论

A Region Preference-based Optimization Algorithm for Satellite Mission Planning Problem 2

A Region Preference-based Optimization Algorithm for Satelli...

引用

2021 2nd International Conference on Modeling, Big Data Analytics and simulation, MBDAS 2021

作者： Xiong, Minghui Xiong, Wei Science and Technology on Complex Electronic System Simulation Laboratory Space Engineering University China

For the earth observation satellite mission planning problem, objectives such as observed target quantity, observation profit, energy consumption, image quality should be considered simultaneously, which is a many-objective optimization problem. Classical optimization-based mission planning algorithms obtain a set of non-dominated solutions in the entire search space, while only a single satisfy final plan is desired by decision maker. In this paper, a five-objective optimization model for satellite mission planning problem is constructed, then a region preference-based evolutionary algorithm, HMOEA-T, is applied to obtain the desired solutions. The decision makers describe the preference on each objective in target region form, then the algorithm guides a more detailed search within the preference region rather than the entire Pareto front. Comparative studies with preference-based methods (T-NSGA-III) and classical methods (NSGA-III) are conducted. We have exemplified the proposed method manage to obtain the solutions satisfying the mission planning preference and achieve better performance in convergence and diversity. © Published under licence by IOP Publishing Ltd.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

MTL-JER: Meta-Transfer Learning for Low-Resource Joint Entity and Relation Extraction 3

MTL-JER: Meta-Transfer Learning for Low-Resource Joint Entit...

引用

3rd International Conference on Neural Networks, Information and Communication Engineering, NNICE 2023

作者： Peng, Da Pei, Zhongmin Mo, Delin Space Engineering University Science and Technology on Complex Electronic System Simulation Laboratory Beijing China Institute of War Studies Academy of Military Sciences

ISBN: (纸本)9798350335972

Joint entity and relation extraction has achieved impressive advances in NLP, such as document understanding and knowledge graph construction. The typical methods for entity and relation extraction typically break down the joint task into several smaller components or stages for ease of implementation, but this leads to a loss of the interconnected knowledge in the triple. Hence, we propose to model the triple in one module jointly. Furthermore, the labeling of a joint entity and relation extraction tasks is costly and domain-specific;therefore, it is important to improve its performance on low-resource data and domain adaption. To address this issue, we suggest using two sources that are rich in information, namely pre-trained models on large data and multi-domain text corpora. Pretraining allows us to provide the model with the fundamental ability to perform joint entity and relationship extraction. Second, through meta-learning on multi-domain text, we can improve the model's generalization capabilities, enabling it to perform well even with limited data. We present MTL-JER, a Meta-Transfer Learning method for Joint Entity and Relation Extraction in low-resource settings in this paper. Using exhaustive experiments on five datasets, we prove that our model obtains optimal results. © 2023 IEEE.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

LEO Satellite Network Traffic Forecasting based on ARIMA-BPNN Model 3

LEO Satellite Network Traffic Forecasting based on ARIMA-BPN...

引用

3rd International Conference on Electronic Information Engineering and Computer Communication, EIECC 2023

作者： Han, Chi Xiong, Wei Yu, Ronghuan Fu, Jingyu Space Engineering University Science and Technology on Complex Electronic System Simulation Laboratory Beijing China Jiuquan Satellite Launch Center Jiuquan China

ISBN: (纸本)9798350359961

Satellite network traffic forecasting provides key information for routing and resource allocation, which is important for the efficient operation of satellite network. However, due to the self-similarity and long-range dependence (LRD) of satellite network traffic, traditional linear or non-linear network traffic forecasting models cannot achieve sufficient forecasting accuracy. A combined model of satellite network traffic forecasting based on BPNN and ARIMA is proposed. BPNN is adopted to forecast the residuals. EMD-ARIMA and BPNN forecasting results are combined to achieve satellite network traffic forecasting. Experimental results on the satellite network traffic data generated by the ON/OFF model show that forecast accuracy of the proposed method is better than traditional model, which verifies the effectiveness of the proposed satellite network traffic forecast model. © 2023 IEEE.

关键词： BP neural network empirical mode decomposition intrinsic mode function long-range dependence satellite network

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：