检索结果-内蒙古大学图书馆

2nd IEEE International Conference on Information technology, Big Data and Artificial Intelligence, ICIBA 2021

作者： Li, Xiao Liu, Desheng Chang, Qing Space Engineering University Science and Technology on Complex Electronic System Simulation Laboratory Beijing China

ISBN: (纸本)9781665428767

Nowadays, modern warfare has changed from weapon-centric operations to network-centric system operations, which has led to the phenomenon of sea-level quantification of weaponry. It is an important research topic for combat commanders to select suitable weaponry from a large number of available resources when facing combat tasks. Recommendation technology is a solution to this problem, which can effectively solve the problem of information overload, so that combat commanders do not produce the phenomenon of 'information loss', in the shortest possible time to make the right decision. Therefore, this paper proposes a collaborative filtering recommendation algorithm for weaponry based on the knowledge graph and the idea of collaborative filtering. In this algorithm, the knowledge graph provides a clear data model with various association relationships, and the collaborative filtering algorithm can realize it without relying on professional experience, which can realize the recommendation process more actively, faster and more intelligently. © 2021 IEEE.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

ETM fusion algorithm based on log classification 2

ETM fusion algorithm based on log classification

引用

2nd IEEE International Conference on Information technology, Big Data and Artificial Intelligence, ICIBA 2021

作者： Lin, Wenxiang Liu, Desheng Science and Technology on Complex Electronic System Simulation Laboratory Space Engineering University Beijing China

ISBN: (纸本)9781665428767

With the improvement of computer computing power, the shortcomings of the computational inefficiency of the genetic mining algorithm are compensated, and the genetic mining become a research hotspot. In this paper, for the Evolutionary Tree Miner (ETM) algorithm in noise processing can not find the low-frequency effective path and remove the shortage of noise, an ETM fusion algorithm based on log classification is proposed. The algorithm performs process model mining for high-frequency and low-frequency logs separately, and get model fusion based on alignment ideas, Eventually mining the complete process model. Through the simulation of event log data verification, the improved algorithm achieves more complete process model mining than the original ETM algorithm. © 2021 IEEE.

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

A DQN-based hyperheuristic algorithm for emergency scheduling of Earth observation satellites 2

A DQN-based hyperheuristic algorithm for emergency schedulin...

引用

2nd International Conference on electronics, Communications and Information technology, CECIT 2021

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

ISBN: (纸本)9781665437578

With the surge of emergency task demand, large-scale Earth observation satellite emergency scheduling has become a practical problem which is urgent to be solved. In view of this situation, this paper analyzes the constrains and conflict relationship in this problem, and proposes a DQN-based hyperheuristic algorithm. The algorithm includes encoding and decoding, deep Q-network and several low-level heuristic operators. A Markov decision model of this problem is established and 7 low-level heuristic operators are designed according the feature of this problem. After training, DQN behaves well when selecting operators for the scheduling scheme. Finally, several groups of comparative experiments verify the algorithm's ability in solving large-scale satellite emergency scheduling problems. © 2021 IEEE.

关键词： Personnel training

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

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

引用

Neural Networks, Information and Communication Engineering (NNICE), International Conference on

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

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.

关键词： Adaptation models Training data Knowledge graphs Artificial neural networks Data models Data mining Labeling

来源：评论

学校读者我要写书评

暂无评论

Depth estimation using an improved stereo network

引用

Frontiers of Information technology & electronic Engineering 2022年第5期23卷 777-789页

作者： Wanpeng XU Ling ZOU Lingda WU Yue QI Zhaoyong QIAN Science and Technology on Complex Electronic System Simulation Laboratory Space Engineering UniversityBeijing 101416China Peng Cheng Laboratory Shenzhen 518055China Digital Media School Beijing Film AcademyBeijing 100088China

Self-supervised depth estimation approaches present excellent results that are comparable to those of the fully supervised approaches,by employing view synthesis between the target and reference images in the training ***,which serves as a backbone network,has some structural deficiencies when applied to downstream fields,because its original purpose was to cope with classification *** low-texture area also deteriorates the *** address these problems,we propose a set of improvements that lead to superior ***,we boost the information flow in the network and improve the ability to learn spatial structures by improving the network ***,we use a binary mask to remove the pixels in low-texture areas between the target and reference images to more accurately reconstruct the ***,we input the target and reference images randomly to expand the dataset and pre-train it on ImageNet,so that the model obtains a favorable general feature *** demonstrate state-of-the-art performance on an Eigen split of the KITTI driving dataset using stereo pairs.

关键词： Monocular depth estimation Self-supervised Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

A dynamic planning method for satellite imaging mission based on improved genetic algorithm

引用

Applied Mathematics and Nonlinear sciences 2024年第1期9卷

作者： Zhao, Demin Xiong, Wei Wang, Yiran Science and Technology on Complex Electronic System Simulation Laboratory University of Aerospace Engineering Beijing100000 China DFH Satellite CO. Ltd. Beijing100080 China

The ongoing enhancement of imaging satellite platforms in terms of payload capacity, coupled with the proliferation of imaging satellites, introduces new complexities to the mission planning processes. These enhancements enable broader applications and significantly increase the societal benefits derived from imaging satellites. To address these challenges, a specific kinematic model for dynamic imaging attitudes is constructed, taking into account the dynamics of satellite imaging missions. This model uses information from satellite imaging observation tasks to design constraints that govern the planning of imaging tasks. Additionally, an optimization objective function is established to ensure compliance with these planning constraints. Building on the encoding method for relative imaging moments, an adaptive genetic algorithm tailored for satellite imaging task planning is introduced. This algorithm enhances the iterative efficiency of decision variables involved in satellite imaging tasks. Empirical validation through comparative simulation experiments, using a typical satellite imaging mission as a case study, demonstrates the effectiveness of the adaptive genetic algorithm. In various phases of imaging mission planning, the algorithm achieved a 100% task completion rate. The index function gain was enhanced by 21.47%, and the maximum synthetic angular velocity of attitude maneuvers between different targets peaked at the satellite's maneuvering threshold of 7 degrees per second. By leveraging adaptive genetic algorithms, satellite imaging mission planning can optimize mission completion rates and effectively utilize the satellite's maximum attitude maneuver capabilities. © 2024 Demin Zhao et al., published by Sciendo.

关键词： Satellites

来源：评论

学校读者我要写书评

暂无评论

Analysis of node importance of satellite network based on triangular motif 23

Analysis of node importance of satellite network based on tr...

引用

Proceedings of the 2023 International Conference on Communication Network and Machine Learning

作者： Zhongmin Pei Boren Hu Zhangkai Luo Jie Ding Science and Technology on Complex Electronic System Simulation Laboratory Space Engineering University China Department of Electronics and Optical Engineering Space Engineering University China

ISBN: (纸本)9798400716683

Motif provides a local high-order substructure angle for the analysis of network structure evolution, which is of great significance for the study of the interaction between satellite network structure and function. Taking the time scrambling null motif in steady state as a reference, the stability analysis of satellite network structure is carried out from the perspective of the local structure of the motif characteristics; define the temporal degree of satellite network, and propose a satellite network node importance analysis method based on the number of node-constructed triangle motifs, and compare the changes of motifs characteristics under the deliberate attack of temporal degree and based on triangle motifs. simulation experiments are conducted on 46-node GPS constellations containing satellites and ground stations, and it is found that the network with higher initial triangle concentration showed higher stability. In GPS satellite network where the number of node triangle motif is positively correlated with their temporal degree, the attack strategy based on the triangle motif accelerates the attenuation of the triangle subgraph, and the node importance analysis method of the satellite network has higher accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Antenna Position and Power Allocation Design for Shared Aperture Sparse Linear Array 10

Antenna Position and Power Allocation Design for Shared Aper...

引用

10th International Conference on Control, Automation and Information sciences, ICCAIS 2021

作者： Liu, Ruitao Wei, Wenqiang Yu, Xianxiang Lu, Qinghui Cui, Guolong Fang, Xueli Zhang, Lei University of Electronic Science and Technology of China Chengdu China Key Laboratory of Complex Aeronautical System Simulation Beijing China

ISBN: (纸本)9781665440295

This paper considers the joint design of the antenna position and power allocation in a shared aperture sparse phased array. We introduce a new optimization model relying on the minimization of the Peak Sidelobe Levels (PSL) of beampattern under the antenna position constraints, mainlobe constraints and transmit power constraints. In order to tackle the non-convex problem, we resort to a Modified Membrane Algorithm based on P systems (MMAPS) along with its each iteration executed in parallel. Finally, numerical simulations verify the effectiveness of the proposed algorithm. The results highlight that MMAPS can obtain a better beampattern in terms of the PSL in comparison with the available methods. © 2021 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

DOA Estimation of Distributed mmWave Radar system via Fast Iterative Adaptive Approach 10

DOA Estimation of Distributed mmWave Radar System via Fast I...

引用

10th International Conference on Control, Automation and Information sciences, ICCAIS 2021

作者： Wei, Wenqiang Liu, Ruitao Yu, Xianxiang Lu, Qinghui Cui, Guolong Fang, Xueli Zhang, Lei University of Electronic Science and Technology of China Chengdu China Key Laboratory of Complex Aeronautical System Simulation Beijing China

ISBN: (纸本)9781665440295

In this paper, we propose a fast algorithm based on iterative adaptive approach to address the DOA estimation for the distributed mmWave radar system under the challenging conditions of a single snapshot and coherent sources. In order to improve angular resolution, let each transmit sensor emit the same signal in time-sharing to construct a large aperture virtual array. We first roughly derive azimuth angles with one mmWave radar using conventional beamforming. Then, resorting to iterative adaptive approach, we search for the accurate DOA estimations within a very small region based on the estimated azimuth to improve computational efficiency and angular resolution. Finally, numerical simulation results are provided to demonstrate superior performance of the proposed algorithm over some counterparts. © 2021 IEEE.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Target Identity Fusion Method Based on Improved DS Evidence Theory

Target Identity Fusion Method Based on Improved DS Evidence ...

引用

electronic Information Engineering and Computer technology (EIECT), International Conference on

作者： Yi Wang Desheng Liu Yang Yang Jiatong Liu Science and Technology on Complex Electronic System Simulation Laboratory Space Engineering University Beijing China Space Engineering University Beijing China

Target data detected by multi-sensors often differ from each other due to different sensor performances, resulting in uncertainty of target identity information. Traditional Dempster-Shafer (DS) evidence theory may achieve counter-intuitive outcomes facing evidence conflicts caused by the uncertainty. Aiming for this, a novel target identity fusion method based on improved DS evidence theory is proposed in this paper. Specifically, the method considers the correlation between evidences and the importance of evidences integrally. First, an improved conflict measurement method based on Pearson correlation coefficient matrix is devised to measure the evidence credibility. Next the information volume of evidences is measured by Deng-entropy to indicate the evidence uncertainty. Then the credibility and uncertainty are weighted and combined to modify the basic probability assignment (BPA) of evidences. Ultimately, the modified evidences are fused by Dempster’s combination rule to acquire the final results. Through three numerical analysis examples, this paper demonstrates the superiority of the proposed method over typical previous approaches, which can effectively process evidence conflicts in multi-sensors information fusion.

关键词：

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：