检索结果-内蒙古大学图书馆

10th International Conference on control, automation and Information sciences, ICCAIS 2021

作者： Qu, Shaoyong Liu, Weifeng Li, Jianning Peng, Zhangming Hangzhou Dianzi University School of Automation Hangzhou China Shaanxi University of Science and Technology School of Electrical and Control Engineering Xi'an China

ISBN: (纸本)9781665440295

To solve the problem of Chinese semantic understanding and extraction, this paper presents an enhancement method for Chinese environment semantic Slot Filling based on part-of-speech(POS) tagging. Firstly, construct a special dictionary with a given task domain where each word has its own part of speech and word frequency tagging;Secondly, based on the Chinese word segmentation technique called Jieba, Chinese sentences are partitioned to obtain a finite sequence with words as the basic elements. And then, a new finite sequence is obtained by replacing the words with the same POS tagging in the finite sequence with the same symbol. Finally, the Bidirectional Long Short-Term Memory with Conditional Random Fields(BLSTM-CRF) network training model is used with a new limited sequence set and its tag sequence set as input, and the slot filling criteria based on POS tagging are appended. Applying popular data set ATIS training model, it shows that the method has high accuracy and reliability through simulation comparison experiment. © 2021 IEEE.

关键词： Filling

来源：评论

学校读者我要写书评

暂无评论

A Test Suite and An Optimizer for Dietary Nutrition Optimization Problem: From Constrained Many-Objective Perspective

A Test Suite and An Optimizer for Dietary Nutrition Optimiza...

引用

2023 IEEE Congress on Evolutionary Computation, CEC 2023

作者： Ti, Yaqi Li, Changhe Yang, Shengxiang Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China School of Computer Science and Informatics De Montfort University Leicester United Kingdom

ISBN: (纸本)9798350314588

With increasing people who suffer from diet-related diseases, providing suggestions for personal daily nutrient-dense intake is highly expected. However, current dietary nutrition models are less precise, and dietary nutrition optimizers usually fail to give satisfactory solutions. Therefore, we construct a constrained many-objective nutrition model with more precise nutrient assessments and a scalable constrained many-objective benchmark set. This test suite has great flexibility in evaluating algorithms' performance on high dimensional search and objective spaces with some feasible region fragments. We also propose a kd-tree based dynamic constrained many-objective evolutionary algorithm to search for customized food combinations according to personal daily consumption and intake preference. Experiments show that our algorithm has better diversity maintenance ability in high dimension space. © 2023 IEEE.

关键词： Nutrition

来源：评论

学校读者我要写书评

暂无评论

ADRC-Based controller with Linkage Compensation for Interleaved Parallel Converters

ADRC-Based Controller with Linkage Compensation for Interlea...

引用

Energy, Electrical and Power engineering (CEEPE), International Conference on

作者： Bo Wang Xuesong Zhou Chenyang Zhao Long Tao Youjie Ma Zhiqiang Gao School of Electrical Engineering and Automation Tianjin University of Technology Tianjin China School of Control Science and Engineering Tiangong University Tianjin China School of Electrical and Information Engineering Tianjin University Tianjin China

The microgrid is the key development direction of distributed energy. However, the performance indicators of its low-voltage side interface are often affected under complex operating conditions. To address this problem in a targeted manner, a linkage compensatory active disturbance rejection controller (LC-ADRC) that considers both the higher-order perturbation model and object model information is proposed. In this work, the extended state observer (ESO) and the feedback control law of the LC-ADRC are reconstructed according to the interleaved parallel bi-directional converter (IBC) characteristics, and the theoretical analysis shows that the dynamic response and immunity to disturbances of the IBC under typical conditions can be improved simultaneously. Finally, the experimental curves and test indexes obtained from the 300-watt test platform designed for these operating conditions verified the accuracy of the theoretical analysis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Formation control and Obstacle Avoidance Design for Networked USV Swarm With Exogenous Disturbance Under Intermittent Communication

引用

IEEE Transactions on Network science and engineering 2025年

作者： Chang, Zhenyu Zong, Guangdeng Wang, Wencheng Yue, Ming Zhao, Xudong Tiangong University School of Control Science and Engineering Tianjin300387 China Weifang University College of Machinery and Automation Weifang261061 China Dalian University of Technology School of Automotive Engineering Dalian116024 China Dalian University of Technology Faculty of Electronic Information and Electrical Engineering Dalian116024 China

This study addresses the formation control problem of under-actuated unmanned surface vehicle (USV) swarm systems and designs an obstacle avoidance strategy for navigating in obstacle environments. The intermittent communication scheme, consisting of the working period and the rest period, is introduced to reduce the communication burden and the consumption of control resources. A distributed formation control strategy is designed to guarantee the realization of the desired formation configuration. Considering the potential impact of obstacles in the operating environment, the artificial potential field repulsion obstacle avoidance method is embedded into the formation control strategy. To eliminate the impact of exogenous disturbances, a disturbance observer is established using the partially known disturbance information. Sufficient conditions are provided to ensure the uniformly ultimate boundedness of the formation error and disturbance observation error. In addition, an energy function related to the obstacle position information is designed to verify that the desired obstacle avoidance behavior can be achieved. The feasibility of theoretical analysis is validated by applying the developed control strategy to surface formation cruise missions. © 2013 IEEE.

关键词： Unmanned surface vehicles

来源：评论

学校读者我要写书评

暂无评论

Audio-visual Speech Enhancement by Using the Correlation Deeply 21

Audio-visual Speech Enhancement by Using the Correlation Dee...

引用

Proceedings of the 2021 4th International Conference on Algorithms, Computing and Artificial Intelligence

作者： Xiaolong Wang Jing Zhang Wei Li School of Electrical Engineering and Automation Anhui University China School of Control Science and Engineering Shandong University China

ISBN: (纸本)9781450385053

Audio-visual speech separation aims to separate distinct voice from an audio mixture of multiple simultaneous speakers. The problem is that visual information can’t be fully utilized. We propose a network which can improve the functioning of speech enhancement by using the correlation between audio and vision deeply. We propose that we could extract visual feature information by utilizing speech before using visual information to improve speech enhancement performance. We make a continuous dataset, CRF, to fit the network at the same time. The results demonstrate that the combination of them can improve the performance of speech enhancement effectively.

关键词： speech separation speech enhancement audio-visual correlation

来源：评论

学校读者我要写书评

暂无评论

Fog Images Generation About Unmanned Surface Vessels with Improved Generative Adversarial Network 42

Fog Images Generation About Unmanned Surface Vessels with Im...

引用

42nd Chinese control Conference, CCC 2023

作者： Tang, Yifeng Huang, Zhihui Tang, Chuancong Luo, Chuanshang Xu, Yifan Liu, Bin Zhang, Hai-Tao School of Artificial Intelligence and Automation The Engineering Research Center of Autonomous Intelligent Unmanned Systems The Key Laboratory of Image Processing and Intelligent Control Wuhan430074 China The State Key Laboratory of Digital Manufacturing Equipment and Technology Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9789887581543

This paper proposes a fog weather data augmentation method for the unmanned surface vessels (USVs) via improved Generative Adversarial Network(GAN) model. First, a generator scheme for GAN is proposed with the guided generation of the atmospheric scattering model in this paper. A Laplacian Pyramid Based Depth Residuals model is added to the generator which reduces the difficulty of generating fog images caused by the degradation of water surface image and improves the quality of generated images. Finally, fog images are generated from sunny weather images collected with HUST-12C by LPBDR-GAN model and experiments show that generated images are very close to real fog images. © 2023 Technical Committee on control Theory, Chinese Association of automation.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Covariance Intersection-based Invariant Kalman Filtering(DInCIKF) for Distributed Pose Estimation

arXiv

引用

arXiv 2024年

作者： Li, Haoying Li, Xinghan Huang, Shuaiting Yang, Chao Wu, Junfeng School of Data Science The Chinese University of Hong Kong Shenzhen China College of Control Science and Engineering Zhejiang University Hangzhou China Department of Automation East China University of Science and Technology Shanghai China

This paper presents a novel approach to distributed pose estimation in the multi-agent system based on an invariant Kalman filter with covariance intersection. Our method models uncertainties using Lie algebra and applies object-level observations within Lie groups, which have practical application value. We integrate covariance intersection to handle correlated estimates and use the invariant Kalman filter to merge independent data sources. This strategy allows us to effectively tackle the complex correlations of cooperative localization among agents, ensuring our estimates are neither too conservative nor overly confident. Additionally, we examine the consistency and stability of our algorithm, providing evidence of its reliability and effectiveness in managing multi-agent systems. © 2024, CC0.

关键词： Wiener filtering

来源：评论

学校读者我要写书评

暂无评论

INN: A Deep Correction Network for High-Dynamic Inertial Navigation

INN: A Deep Correction Network for High-Dynamic Inertial Nav...

引用

Industrial automation, Robotics and control engineering (IARCE), International Conference on

作者： Tao Gu Li Cong Jing Yang Yuzhu Guo Lina Wang School of Automation Science and Electrical Engineering Beihang University Beijing China Engineering dept. name of organization School of Electronic Information Beihang University Beijing China National Key Laboratory of Science and Technology on Aerospace Intelligence Control Beijing China

ISBN: (数字)9798350380323

ISBN: (纸本)9798350380330

Inertial navigation has gained extensive application because it solely relies on built-in Inertial Measurement Unit (IMU) devices. Nevertheless, due to its inherent accumulative integral error, inertial navigation is often integrated with other external devices in practical situations, which unfortunately leads to unavoidable privacy breaches. To address these issues, an Inertial Navigation Neural Network (INN) is designed to generate high-precision position estimations without relying on any other auxiliary information. The INN model consists of attitude correction and velocity regression modules. The attitude module employs a convolutional network to correct the attitude information, and the obtained rotation matrices are then fed into a recurrent neural network to regress incremental velocities and produce high-precision positions. The proposed model is validated on the simulated trajectories based on the Precise Strapdown Inertial Navigation System (PSINS) toolbox. Experimental studies demonstrated that the proposed method has a significant corrective effect on high-dynamic strapdown inertial navigation settings. The accumulated position errors are an order of magnitude smaller than those of traditional track reckoning algorithms and achieved a comparable performance with integrated navigation.

关键词： Deep learning Measurement units Recurrent neural networks control engineering Service robots Estimation Inertial navigation Privacy breach Trajectory Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Impact angle control guidance for a moving target with general field-of-view constraints

Impact angle control guidance for a moving target with gener...

引用

第42届中国控制会议

作者： Xiangyu Tang Jianglong Yu Siting Peng Xiwang Dong Qingdong Li Zhang Ren School of Automation Science and Electrical Engineering Science and Technology on Aircraft Control Laboratory Beihang University Beijing Electro-Mechanical Engineering Institute Institute of Artificial Intelligence Beihang University

This paper studies the impact angle control guidance problem with general field-of-view(FOV) constraints for a moving target. Firstly, the control Lyapunov function(CLF) is constructed based on the state-dependent Riccati equation(SDRE)technique, and a nominal controller is designed to intercept the moving target at the desired impact angle without FOV *** control barrier functions(CBFs) are designed according to the FOV constraints. Secondly, the CLF that guarantees stability is combined with the CBFs that guarantee forward invariance of the constraint sets. The minimum modification framework is used to numerically solve the guidance command through quadratic programming to ensure that the look angle of the missile always remains within the constraint interval during the interception process. Finally, the effectiveness of the proposed guidance law is verified by numerical examples.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Novel Regression Model Based on Shallow-to-Deep Correlation Network Representation for Monitoring MIQ-related Ironmaking Processes

Novel Regression Model Based on Shallow-to-Deep Correlation ...

引用

第34届中国过程控制会议

作者： Siwei Lou Chunjie Yang Hanwen Zhang Xiongzhuo Zhu Ping Wu State Key Laboratory of Industrial Control Technology (SKLICT) Zhejiang University School of Automation and Electrical Engineering University of Science and Technology Beijing School of Information Science and Engineering Zhejiang Sci-Tech University

Ironmaking process(IP) is indispensable to modern iron and steel industry,where real-time monitoring is demanded to achieve high molten iron quality(MIQ) with low energy *** deep neural network models have been promising in this regard,generally,they are limited by non-negligible drawbacks such as interpretability issues of feature learning and model *** address these issues,we propose a novel concept based on the shallow-to-deep correlation network representation regression(Sh-to-De CNRR) *** approach,ShCNRR,combines neural network-and canonical correlation analysisbased thoughts to generate explainable features via shallow correlation network representation(CNR).A twin inverse network is then derived to obtain the explicit model output,leveraging the shallow *** capture deeper nonlinear information,we extend ShCNRR into a hierarchical DeCNRR model that features stacked neural networks,enabling us to learn deeper CNR of process *** feasibility and merits of our proposals are validated by theoretical derivations and practical IP cases,which contain one MIQ regression and three MIQ-related fault detection *** results reveal that highly fused statistical and neural network models yield superior monitoring performance compared to current state-of-the-art models while remaining interpretability and thus enabling convincing feature mining.

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：