检索结果-内蒙古大学图书馆

International Conference on Autonomous Unmanned systems, ICAUS 2021

作者： Sun, Yinjiang Zhang, Rui Liu, Xiaoheng Liang, Wenbao Xu, Cheng Beijing Electro-Mechanical Engineering Institute Beijing China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

ISBN: (纸本)9789811694912

Unmanned aerial vehicle (UAV) plays an increasingly important role both in civil and military fields. As a typical mission, area coverage search is a primary measure for reconnaissance and surveillance of unknown areas. Due to the limited information about the mission area, UAV needs adaptiveness to the dynamic changes of the area and makes decisions based on local observation. It puts higher demands on the response speed of UAV, and traditional planning methods are tough to be directly applied. The problem becomes more noticeable for multiple UAV because of the heterogeneous function and large scale, and new solutions are urgently required. In this paper, the feasibility of reinforcement learning (RL) for performing area coverage search is explored, and an environment is designed for RL training and evaluation. Simulation results show that multiple UAV can cooperate and perform the mission with pretty high coverage. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Adversarial Example Attack and Defence of Object Recognition: A Survey

Adversarial Example Attack and Defence of Object Recognition...

引用

2022 IEEE International Conference on Unmanned systems, ICUS 2022

作者： Tan, Wei Zhao, Jiajia Liang, Xinkai Lu, Hanchen Song, Baogang Guan, Hao Science and Technology On Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China Beijing Mechano-Electronic Engineering Institute Beijing China

ISBN: (数字)9781665484565

ISBN: (纸本)9781665484565

Deep learning-based intelligent object recognition algorithm has been widely applied in object detection, auto driving, ect. However, deep neural network is very vulnerable because of its high-dimensional linearization. The object recognition results can be easily mis-leaded through a tiny disturbance in the original image. This kind of sample that adds tiny disturbance to the original image is called adversarial example. The adversarial example attack is a factor that must be considered in the design of robust object recognition algorithm, that is, the need for adversarial defence. An in-depth understanding of adversarial attack can help the model defend successfully. In this survey, an introduction of adversarial attack and defense aiming to object recognition algorithm at the present stage is summarized, and the challenges to be faced and the development trend in the future are pointed out. © 2022 IEEE.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Solving Ascent Trajectory Optimization Problems by Radua Pseudospectral Method

Solving Ascent Trajectory Optimization Problems by Radua Pse...

引用

2022 International Symposium on Intelligent Robotics and systems, ISoIRS 2022

作者： Deng, Liaochao Xu, Cheng You, Weishuai Beijing Institute of Mechanical and Electrical Engineering Beijing China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

ISBN: (纸本)9781665455213

Ascent trajectory optimization problem of air-breathing hypersonic vehicles is a highly nonlinear and nonconvex problems. Most of the early works focus on the traditional indirect method, which needs to derive the complete first-order necessary conditions of the trajectory optimization problem. The derivation process is too complicated and error-prone. Additionally, indirect method has a high demand on the initial guess, and it needs to give the initial guess of covariant variables without physical significance. In this paper, we solve the ascent trajectory optimization problem directly using Radau Pseudospectral Method (RPM). Firstly, the complex three-dimensional ascent trajectory optimization problem is established in detail. Conmmon inequality path constraints including those on dynamic pressure and aerodynamic bending moment are taken into account. The performance index is given as maximizing the final mass considering minimizing the fuel consumption. Subsequently, the ascent trajectory optimization problem is transformed into a nonlinear programming problem (NLP) by RPM. Finally, the ascent trajectory optimization for Generic Hypersonic Aerodynamic Model Example (GHAME) is solved by RPM and the optimal results demonstrate the rapidity, effectiveness and high precision of RPM. The comparison between optimal trajectories with and without path constraints shows that path constraints increase fuel consumption. © 2022 IEEE.

关键词： Hypersonic vehicles

来源：评论

学校读者我要写书评

暂无评论

FedCrowd: Towards Promoting the Concurrency of the Server in Asynchronous Federated Learning 2

FedCrowd: Towards Promoting the Concurrency of the Server in...

引用

2nd International Symposium on Electrical, Electronics and Information Engineering, ISEEIE 2022

作者： Xi, Wen Liao, Yuying Zhou, Bin Wang, Haiyang Gao, Liqun College of Computer Science and Technology National University of Defence Technology Changsha China National University of Defence Technology Key Lab. of Software Engineering for Complex System Changsha China

ISBN: (数字)9781665468749

ISBN: (纸本)9781665468749

Federated learning is a privacy-preserving machine learning paradigm where a global model is trained collaboratively across resource-limited devices such as mobile phones, wearable devices, and sensors while the training data remains on these devices. Recently proposed asynchronous federated learning framework FedAsync has addressed the problems occurred in synchronous federated learning such as wasting time waiting for all nodes to finish uploading or losing parts of the contribution of nodes due to some unexpected reasons. However, on the server-side, it is not suitable for concurrency due to the data race on the global model. We proposed a method named FedCrowd, where the server's concurrency is improved by elaborately coordinating the working threads to relieve the data race on the global model. Several experiments are performed to show that our method could effectively increase concurrency of the server and reduce the training time. © 2022 IEEE.

关键词： Concurrent computing Training Wearable computers Training data Machine learning Collaborative work Data models

来源：评论

学校读者我要写书评

暂无评论

Recognition of Continuous Phase Modulation Signals Based on Synchrosqueezing Wavelet Transform

Recognition of Continuous Phase Modulation Signals Based on ...

引用

2022 International Applied Computational Electromagnetics Society Symposium, ACES-China 2022

作者： Ruan, Guangxin Zhao, Liu Liu, Zheng College of Electronic Science and Technology National University of Defense Technology State Key Lab. of Complex Electromagnetic Environment Effects on Electronics and Information System Changsha China

ISBN: (纸本)9781665452366

We present a new algorithm that can solve the problem of recognition of continuous phase modulation (CPM) signals to phase shift keying (PSK) signals. The algorithm uses synchrosqueezing wavelet transform (SWT) to extract the instantaneous frequency (IF) of the signal. On this basis, a recognition characteristic parameter is proposed. This paper verifies the parameter is suitable for PSK and CPM signals with different modulation parameters. Finally, the simulation shows that the algorithm can fully recognize CPM signals to BPSK and QPSK signals when signal-to-noise ratio (snr) is above 6dB. Compared with the existing algorithms, the algorithm proposed in this paper has a higher recognition rate in the low snr environment. © 2022 IEEE.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Direct Differentiation Sensitivity Analysis Based on Reduced Multibody system Transfer Matrix Method 2nd

Direct Differentiation Sensitivity Analysis Based on Reduced...

引用

2nd International Conference of Mechanical system Dynamics, ICMSD 2023

作者： Wang, Guoping Tu, Tianxiong Miao, Yunfei Rui, Xiaoting Institute of Launch Dynamics Nanjing University of Science and Technology Nanjing China National Key Laboratory of Complex Multibody System Dynamics Nanjing University of Science and Technology Nanjing China Chongqing Hongyu Precision Industry Group Co. Ltd. Chongqing China College of Mechanical & Electrical Engineering Nanjing University of Aeronautics and Astronautics Nanjing China

ISBN: (纸本)9789819980475

Dynamics analysis has always been an important foundation for improving the dynamics performance of mechanical systems. The effectiveness and efficiency of multibody system dynamics (MSD) analysis method depend on the modelling method of multibody system dynamics. In this paper, a new direct differential sensitivity analysis method for MSD based on RMSTMM and direct differential method is proposed. Combining sensitivity analysis theory and direct differential formulas, the differential form of recurrence relationship of the element is derived, and the solution flow is given. This method has the advantages of no requiring the global dynamics equations of the system and high programming. The numerical examples are carried out to verify the correctness and effectiveness of the proposed method. Compared with the DMM and AVM based on the Lagrange method, the results show that this method has low matrix order, fast computational speed, and higher analysis efficiency. Compared with the DDM based on the NV-MSTMM, the proposed method is more stable for a large system, which provides a new means for rapid analysis of multibody system dynamics. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Launching ceremony of the International Society of Mechanical system Dynamics Convened in Beijing, China

引用

International Journal of Mechanical system Dynamics 2023年第4期3卷 283-299页

作者： Tong Zhang Qinbo Zhou Yanni Zhang Hang Zhang Editorial Office of International Journal of Mechanical System Dynamics Nanjing University of Science and TechnologyNanjingChina Institute of Launch Dynamics Nanjing University of Science and TechnologyNanjingChina Frontiers Science Center for System Dynamics of Complex Equipment Nanjing University of Science and TechnologyNanjingChina

The First General Assembly and the First Session of the First Executive Board Meeting of International Society of Mechanical system Dynamics(ISMSD),the ISMSD Launching Ceremony,the Second International Conference on Mechanical system Dynamics(ICMSD),the Second ICMSD Standing Steering Committee Meeting,the Third Editorial Board Meeting of the International Journal of Mechanical system Dynamics(IJMSD),and the IJMSD Expert Symposium 2023 were held as a series of international activities on mechanical system dynamics,during the period from August 31 to September 4,2023,at the Wyndham Beijing North,Beijing,China.

关键词： Launching system dynamics

来源：评论

学校读者我要写书评

暂无评论

Static Unstable STT Overload Control on High-order Fully Actuated system Theory

Static Unstable STT Overload Control on High-order Fully Act...

引用

International Symposium on Autonomous systems (ISAS)

作者： Xinyu Liu Mingrui Hao Yan Zhen Yu Fan Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

This article proposes a joint overload controller for pitch and yaw channels on the high-order fully actuated system theory for a nonlinear lateral and longitudinal static unstable STT aircraft model. Firstly, a second-order fully actuated system model for aircraft overload was derived, and an optimal control method for lateral and longitudinal overload was designed. Through mathematical simulation verification of this controller and traditional PID controller, it is shown that the PID control method has significant shortcomings in nonlinear aircraft with coupling. However, high-order fully actuated system theory control method can better adapt to nonlinear and static instability problems, achieve stable tracking of aircraft overload commands, and have better rapidity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Identity Re recognition technology Based on Improved Lightweight ConvNetx Model 42

Identity Re recognition Technology Based on Improved Lightwe...

引用

42nd Chinese Control Conference, CCC 2023

作者： Siting, Peng Lei, Li Zhu, Hongbo Jun, Ren Zhichao, Song Yang, Jiabing The Beijing Electro-Mechanical Engineering Institute Beijing China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China Beihang University School of Electronics and Information Engineering Beijing China

ISBN: (纸本)9789887581543

In the engineering field, there is a requirement for re recognition, including the identity recognition of cooperative and non-cooperative targets, that is, different sensors shoot targets in the same scene, and the identity recognition of targets from two perspectives is required, also known as target accurate retrieval. This method is widely used in fields such as automatic driving and military strikes. In the actual application scenario, deploying the re-recognition algorithm on the embedded processor needs to ensure the real-time computing speed and accuracy, so the complexity of the deep learning algorithm must be reduced, and pruning and lightweight processing are required. In the engineering field, when the image acquired by the sensor is subject to natural interference such as cloud and fog weather or fire and smoke, the difficulty of re-recognition increases. This paper adopts the lightweight improvement of ConvNeXt network model, and fine-tuned it on the basis of its original feature extraction function, so that it can successfully migrate to infrared image classification and also complete the extraction of infrared image target detail distinguishing features, and at the same time introduce the alignment of similar targets in infrared cross-view recognition. In the original similarity calculation, the average value is directly obtained from the spatial dimension of the output feature layer, which is replaced by the weight of the position in each space for estimation. The feature information of the multi-view marine ship target is extracted from the multi-sensor marine image, and its similarity is calculated, so as to determine the identity, thus reducing the support conditions and reconnaissance costs, and improving the accurate detection and tracking ability under the diverse dynamic reconnaissance conditions. © 2023 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Decomposing Visual and Semantic Correlations for Both Fully Supervised and Few-Shot Image Classification

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第4期5卷 1658-1668页

作者： Zhang, Chunjie Zheng, Xiaolong Beijing Jiaotong University Institute of Information Science Beijing100044 China Beijing Jiaotong University Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing100044 China University of Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems The State of Key Laboratory of Management and Control for Complex System Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence Beijing100190 China

Most image classification methods are designed to either boost the classification accuracies with abundant supervision, or cope with the shortage of supervision information. This is often achieved by using the visual and semantic information of other sources. However, these methods use the visual and semantic information within the same class independently, leaving their intrinsic correlations unconsidered. Objects and disturbing components as well as noise exist on the same image. Besides, semantic representations also contain noisy information. To solve the problems mentioned above, we propose a novel method for both fully supervised image classification and few-shot image classification by decomposing visual and semantic correlations. We jointly explore the intrinsic correlations of visual and semantic information of images within the same class. For each class, we decompose its visual and semantic correlations using low-rank and sparse constraint respectively. The decomposed low-rank parts character the intrinsic correlations of images can be used in a linear transformation way. Using the decomposed parts of each class, Classification can be achieved by reconstruction error minimization. We conduct experiments on several datasets for both fully supervised image classification and few-shot image classification. Experimental results well show the effectiveness of the proposed method. © 2020 IEEE.

关键词： Semantics

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：