检索结果-内蒙古大学图书馆

15th Asia Conference on Mechanical and Aerospace Engineering, ACMAE 2024

作者： Liu, Yuanshuai Li, Wei Chao, Tao National Key Laboratory of Modeling and Simulation for Complex Systems Harbin Institute of Technology Harbin150001 China

ISBN: (纸本)9781643685892

This paper addresses the interception mission of hypersonic vehicles by weapon defense systems. A simulation model of the attack-defense confrontation process is constructed based on the "F2T2EA" kill chain model. Building upon this framework, a novel method combining TOPSIS, the entropy weight method, and fuzzy theory is proposed, guided by the concept of kill chain closure, to evaluate the interception effectiveness of defense systems against boost-glide hypersonic vehicles. The model's effectiveness is verified through practical examples, with consistent conclusions obtained through traditional grey correlation analysis, thus confirming the feasibility and reliability of both the model and the evaluation methodology. The results of this research offer reliable technical support for the design and combat application of defense systems and provide a reference for future optimization efforts. © 2025 The Authors.

关键词： boost-glide vehicle grey correlation performance evaluation TOPSIS

来源：评论

学校读者我要写书评

暂无评论

Multi-Targets Visiting Orbit Design Based on Numerical Method

引用

Guidance,Navigation and Control 2025年第1期05卷 139-148页

作者： Zenan Zhong Zhengxiang Sun Songyan Wang Tao Chao Ming Yang Control and Simulation Center Harbin Institute of Technology National Key Laboratory of Modeling and Simulation for Complex Systems Harbin Institute of Technology Beijing Institute of Space Long March Vehicle

In this paper, for the two/three targets in the circle orbit with the same altitude, a numerical method is presented to design an orbit for a spacecraft to visit multiple targets without maneuvering. First,for the two targets' case, an equation is established by the relationship of the two angles that both are the function of the time, one of the angles is the angle between two targets' geocentric position vectors at two times, and another one is the spacecraft flight angle during the two times. The visit time can be solved by the assumption that one of the visit times is known in the equation, and the orbit element can be transferred from the position and velocity vector determined by the solved visit time. Then, for the three targets' case, the problem is decoupled into two cases of two targets, and there is a public target in each case. Based on the method for two targets, two different orbits can be obtained by determining the visit time of the public target. The difference between two orbits can be expressed by the difference in velocity vectors of the public target at different times. A sampling method is utilized to select two velocity vectors with relatively small differences as initial values, the Newton iteration method is used to obtain visit times with higher accuracy. simulation results illustrate the effectiveness of the orbit design methods.

关键词： Orbit design method multiple targets visit circle orbit non-maneuvering

来源：评论

学校读者我要写书评

暂无评论

Road Network-based Vehicle Trajectory Imputation via Generative Adversarial Network 24

Road Network-based Vehicle Trajectory Imputation via Generat...

引用

14th International Conference on the Internet of Things, IoT 2024

作者： Shi, Yichen Zhou, Tianlong Yin, Peiyuan Wang, Zhongyu Mao, Zhaojun Rao, Weixiong Tongji University Shanghai China National Key Laboratory for Complex Systems Simulation Beijing China

ISBN: (纸本)9798400712852

Dense trajectories are important to many location-based service (LBS) applications, e.g., traffic prediction. Existing works often fail to ensure that imputed vehicle trajectories perfectly align with road networks. The two-stage approach involving first trajectory imputation and next map-matching suffers from high computation cost and may not leverage the inherent relationship between trajectories data and road networks. To address the issue, in this paper, we develop a generative adversarial networks (GAN)-based imputation framework by leveraging road networks to fill missing points, and train the GAN model by policy-based reinforcement learning (RL) for better integrity and accuracy. Our preliminary evaluation on two real datasets demonstrates that our work outperforms state-of-the-art with better effectiveness and efficiency. © 2024 Copyright held by the owner/author(s).

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Imp: Highly Capable Large Multimodal Models for Mobile Devices

引用

IEEE Transactions on Multimedia 2025年 27卷 2961-2974页

作者： Shao, Zhenwei Yu, Zhou Yu, Jun Ouyang, Xuecheng Zheng, Lihao Gai, Zhenbiao Wang, Mingyang Kuang, Zhenzhong Ding, Jiajun Hangzhou Dianzi University Key Laboratory of Complex Systems Modeling and Simulation School of Computer Science Hangzhou310005 China Harbin Institute of Technology Shenzhen Department of Computer Science and Technology Shenzhen China Hangzhou Dianzi University HDU-ITMO Joint Institute Hangzhou310005 China

By harnessing the capabilities of large language models (LLMs), recent large multimodal models (LMMs) have shown remarkable versatility in open-world multimodal understanding. Nevertheless, they are usually parameter-heavy and computation-intensive, thus hindering their applicability in resource-constrained scenarios. To this end, several lightweight LMMs have been proposed successively to maximize the capabilities under constrained scale (e.g., 3B). Despite the encouraging results achieved by these methods, most of them only focus on one or two aspects of the design space, and the key design choices that influence model capability have not yet been thoroughly investigated. In this paper, we conduct a systematic study for lightweight LMMs from the aspects of model architecture, training strategy, and training data. Based on our findings, we obtain Imp - a family of highly capable LMMs at the 2B$\sim$4B scales. Notably, our Imp-3B model steadily outperforms all the existing lightweight LMMs of similar size, and even surpasses the state-of-the-art LMMs at the 13B scale. With low-bit quantization and resolution reduction techniques, our Imp model can be deployed on a Qualcomm Snapdragon 8Gen3 mobile chip with a high inference speed of about 13 tokens/s. © 2025 IEEE.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Optimal Deployment of Target Localization With Distance-Dependent Noise

引用

IEEE Internet of Things Journal 2025年

作者： Tian, Junxi Yang, Ming Chao, Tao Harbin Institute of Technology Control and Simulation Center National Key Laboratory of Modeling and Simulation for Complex Systems Harbin150001 China

The cooperative localization of radio-based distance measurement is one of the methods to effectively suppress the nonline of sight (NLOS) ranging errors and as a complement to visual/global navigation satellite system (GNSS) localization for unmanned aerial vehicle (UAV) in GNSS challenging or denied environments due to its motility. Target localization can be regarded as a special case of cooperative localization. Meanwhile, the UAV can be considered as a ranging node when the ranging terminal is rigidly mounted on the UAV. To improve the target localization accuracy, the optimal deployment of anchor UAVs is one of the factors we consider when the noise characteristics are different. In this paper, the range-dependent noise in a real flight environment is considered and modeled separately according to the difference in noise characteristics. Subsequently, based on this correlation model, the Fisher information matrix (FIM) and a cost function derived from the A-optimal criterion are provided. Finally, the optimal deployment conditions and the minimum mean square error (MMSE) can be derived by minimizing the cost function as the objective. Through simulation and localization experiments, the validity of the optimal deployment conditions and the corresponding MMSE are verified. Meanwhile, it is concluded that when the noise is range-dependent, it will not affect the optimal deployment result but will significantly change the value of MMSE. © 2014 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

Research on aircraft/engine Co-simulation based on the EOEI-Kriging model

Research on aircraft/engine Co-simulation based on the EOEI-...

引用

2024 International Conference on Aerospace, Mechanical and Materials Engineering, AMME 2024

作者： Chen, Chao Shang, Linkuan An, Weiyu Zhang, Hang Key Laboratory of Complex Aeronautical Systems Simulation Beijing100039 China School of Mechanical Engineering Xi'an Jiaotong University Shaanxi Xi'an710049 China

Obtaining the characteristic parameters of the aircraft platform is the main blocking point that takes a long time in aircraft/engine co-simulation, so a fast co-simulation modeling method is proposed. In this paper, the kriging model based on the improved EOEI sampling function is used to quickly fit the lift-drag characteristics of aircraft. Combined with the lift-drag data verification test of typical high-speed aircraft shape, the flight performance of the aircraft is evaluated. The simulation results show that under the condition that the average relative error of lift-drag characteristics is not more than 5%, only 22 to 24 CFD solutions are needed to complete the construction of lift-drag characteristics for the speed range of Mach 0 to Mach 6, and the angle of attack range of-4° to 8°. © 2025 Institute of Physics Publishing. All rights reserved.

关键词： Angle of attack

来源：评论

学校读者我要写书评

暂无评论

Mask-guided Multi-scale Spatial-Spectral Transformer for Snapshot Compressive Imaging

Mask-guided Multi-scale Spatial-Spectral Transformer for Sna...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Yin, Heyuan Yang, Jingxiang Liu, Jia Xiao, Liang School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Key Laboratory of Analysis of Mathematical Theory and Modeling of Complex Systems Ministry of Industry and Information Technology China

ISBN: (纸本)9798350368741

Effectively reconstructing 3D hyperspectral images (HSIs) from 2D measurements presents a significant challenge in Coded Aperture Snapshot Spectral Imaging (CASSI) systems. While recent transformers exhibit potential in HSI reconstruction, they often suffer from inadequate exploration of multi-scale spatial-spectral self-similarity, leading to mean effects and information loss. Additionally, these methods struggle with insufficient modeling of the degradation inherent in the compressive imaging process. To address these issues, we propose a novel Mask-guided Multi-scale Spatial-Spectral Transformer (MMSST). Specifically, we introduce a Degradation Aware Mask Attention (DAMA) module to incorporate degradation information of the compressive imaging process. Furthermore, MMSST leverages Local-Regional SpAtial attention (LRSA) and Global-Regional SpEctral attention (GRSE) to effectively exploit multi-scale self-similarity across spatial and spectral dimensions. Extensive experimental results demonstrate the effectiveness of our MMSST. © 2025 IEEE.

关键词： hyperspectral reconstruction Snapshot Compressive Imaging spatial-spectral transformer

来源：评论

学校读者我要写书评

暂无评论

Enhancing realism in LiDAR scene generation with CSPA-DFN and linear cross-attention via Diffusion Transformer model

引用

Neural Networks 2025年 189卷 107503页

作者： Ye, Shaoxun Di, Xiaoguang Liao, Ming Li, Ximing Control and Simulation Center Harbin Institute of Technology Harbin150080 China National Key Laboratory of Modeling and Simulation for Complex Systems Harbin150080 China

Point cloud diffusion models have found extensive applications in autonomous driving and robotics. However, there is still a big gap between their generated LiDAR scene samples and real-world data in terms of visual quality. This discrepancy primarily arises from the loss of detailed information during the decoding process from latent space and the lack of guidance from global 3D structural information in the point cloud generation process, leading to distortions and artifacts in LiDAR scene samples. In this paper, we propose a novel LiDAR Diffusion Transformer Model that integrates Channel-Spatial Parallel Attention and Dilation Fusion Network (CSPA-DFN) with a linear cross-attention post-processing module to refine the generated LiDAR scene samples. Specifically, CSPA-DFN is designed to simultaneously emphasize detailed features across different channels and spatial locations in parallel, leveraging multi-scale dilated convolutions and channel grouping to preserve and enhance these detailed features. In order to provide global 3D structural information and balance performance and efficiency, we design a post-processing module that fuses voxelized features and range images using a linear ReLU cross-attention mechanism. Our approach is evaluated on the unconditional generation task using the KITTI-360 and nuScenes datasets, achieving the state-of-the-art results in LiDAR scene's generation quality. Furthermore, by incorporating semantic labels and camera views into the latent space, in addition to enhancing the model's semantic understanding capability for LiDAR scenes, our method also demonstrates additional performance improvements compared to previous works in terms of LiDAR scene's visual quality. The code implementation has been released on https://***/HITysx/LiDAR-Scene-Generation. © 2025 Elsevier Ltd

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

The co-evolution of East Asian subtropical westerly jet and East Asian summer monsoon during different time periods in the Holocene and its influence on precipitation patterns in China

引用

Science China Earth Sciences 2025年第4期68卷 1100-1115页

作者： Yawen LIU Mi YAN Jian LIU Sumin WANG Zhengyu LIU Liang NING Ziyi WANG Key Laboratory for Virtual Geographic Environment Ministry of Education/State Key Laboratory Cultivation Base of Geographical Environment Evolution and Regional Response/Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and ApplicationSchool of GeographyNanjing Normal UniversityNanjing210023China Jiangsu Provincial Key Laboratory for Numerical Simulation of Large Scale Complex Systems School of Mathematical SciencesNanjing Normal UniversityNanjing210023China Nanjing Institute of Geography and Limnology Chinese Academy of SciencesNanjing210008China Department of Geography The Ohio State UniversityColumbusOH43210USA

Generally,the interaction between the East Asian subtropical westerly jet(EASWJ)and the East Asian summer monsoon(EASM)is regarded as a critical dynamic factor in the evolution of precipitation patterns in *** simulation results from the transient climate evolution since the last glacial maximum,this study applies the multivariate empirical orthogonal function(MVEOF)analysis method to investigate the co-evolution relationships of the EASWJ and the EASM during the early,middle,and late Holocene,as well as their influence on precipitation patterns in *** results indicate that all the first MVEOF modes in different time periods of the Holocene display an out-of-phase relationship in the intensity anomaly between the EASWJ and the ***,the jet stream is wider and more tilted in the late *** the influence of secondary circulations formed during their co-evolution,a north-south dipolar precipitation pattern in eastern China(“flood in the south and drought in the north”or“drought in the south and flood in the north”)and an east-west dipolar pattern in northern China(“wet in the west and dry in the east”or“wet in the east and dry in the west”)are found in the early and middle Holocene,while in the late Holocene a regionally-consistent precipitation pattern is witnessed across the whole *** this mode,the precipitation in the middle and late Holocene is primarily dominated by trend *** second MVEOF mode reveals that the EASM weakens when the EASWJ shifts eastward and the jet steam axis shortens during the early Holocene,resulting in a north-south dipolar precipitation pattern in eastern China and a regionally-consistent pattern in northern *** the middle Holocene,dipolar precipitation patterns are also observed in both eastern China and northern China when the EASWJ moves northward and the EASM strengthens,while the moisture condition in North China is less pronounced,and vice *** the late Holocene,the intensity anomali

关键词： Holocene East Asian subtropical westerly jet East Asian summer monsoon Co-evolution Precipitation pattern

来源：评论

学校读者我要写书评

暂无评论

Lightweight design and deployment of object detection model for low-light scenes 4

Lightweight design and deployment of object detection model ...

引用

4th International Conference on Computer Vision, Application, and Algorithm, CVAA 2024

作者： Sun, Kangjian Huo, Ju Jiang, Xiaona Gao, Yichao Cai, Chen School of Electrical Engineering and Automation Harbin Institute of Technology Harbin China National Key Laboratory of Modeling and Simulation for Complex Systems Harbin China China FAW Corporation Limited Changchun China College of Design and Engineering National University of Singapore Singapore Signal and Communication Research Institute China Academy of Railway Sciences Beijing China

ISBN: (数字)9781510687622

ISBN: (纸本)9781510687615

Low-light scenes are common in fields such as autonomous driving, which tests the robustness of intelligent systems. This paper tests the performance of object detection in low-light scenes based on the YOLOv8n model. In order to solve the constraint of limited computing power of embedded devices, the YOLOv8n model is adjusted through model pruning and knowledge distillation. The complexity of the model is reduced through these lightweight operations. While ensuring the detection performance as much as possible, the multiply-accumulate operations (MACs) and parameters of the model decreased by about 40% and 27% respectively. The proposed model is evaluated on the Exclusively Dark (ExDARK) dataset and achieves a mean average precision (mAP) value of 0.672. In addition, the proposed model is migrated to the embedded platform NVIDIA Jetson Xavier NX. The deployment process is optimized by multi-process scheduling and multi-thread scheduling. Experiments are also conducted on real data, and the results show that the proposed model can provide a feasible solution for vision-based nighttime autonomous driving. © 2025 SPIE.

关键词： Object detection Deep learning Image processing

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：