检索结果-内蒙古大学图书馆

2024 Photonics and Electromagnetics Research Symposium, PIERS 2024

作者： Song, Haoming Zhang, Yifan Zhang, Biao Lv, Yanfang Zhang, Lanjie Ministry of Information Industry Beijing Information Science and Technology University Key Laboratory of Information and Communication Systems China Ministry of Education Beijing Information Science and Technology University Key Laboratory of Modern Measurement and Control Technology China

ISBN: (纸本)9798350375909

Sea surface salinity (SSS) as an important indicator of ocean water circulation, affects global ecology and climate change. However, the accuracy of L-band satellite sea surface salinity retrieval products has been severely affected in coastal regions due to factors such as Radio Frequency Interference (RFI) and Land Sea Continuation (LSC). In this study, coastal regions observational data from the Soil Motion Active Passive (SMAP) satellite, and established the LGBM model for SSS retrieval. The results indicated that LGBM performed excellently in the retrieval of SSS in coastal regions. In comparison to in-situ SSS, the LGBM SSS demonstrated a mean bias (MB) of 0.11psu, a root mean squares error (RMSE) of 0.68psu. This paper also added the bias between LGBM SSS and in situ SSS for secondary correction of LGBM. This correction reduced the MB to 0.03psu, the RMSE to 0.54psu. This study affirms the feasibility of using LGBM for SSS retrieval in coastal regions. Future efforts will focus on integrating more auxiliary data that may influence SSS in coastal regions, aiming to further enhance the precision of the coastal regions' SSS retrieval product. © 2024 IEEE.

关键词： Radio interference

来源：评论

学校读者我要写书评

暂无评论

Guided Transformative GAN: Joint Face Image Super-Resolution and Frontalization

Guided Transformative GAN: Joint Face Image Super-Resolution...

引用

International Conference on systems and Informatics (ICSAI)

作者： Minghao Mu Wei Wang Xiaobo Lu Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Southeast University Nanjing China

ISBN: (数字)9798331510138

ISBN: (纸本)9798331510145

Joint face super-resolution and frontalization of non-frontal low-resolution faces is of significant importance for many face analysis applications. However, at the same time, it is a challenging task. In this paper, a novel Guided Transformative Generative Adversarial Network (GT-GAN) is proposed to address the challenge of generating frontal high-resolution face images from non-frontal low-resolution face images. Existing methods usually treat super-resolution and frontalization as two separate tasks, leading to unsatisfactory processing results. GTG AN innovatively achieves both goals within a unified frame-work. Specifically, we propose Profile Attention Guidance (PAG) to generate landmark heatmaps that provide a priori pose information to the generative network and direct its attention to critical facial regions. In addition, an Attention Fusion Transformation Module (AFTM) is proposed to significantly improve the hallucination performance of the network by utilizing the attention mechanism and STNs, combined with sequential feature enhancement strategies. The experimental results show that GT-GAN exhibits superior performance in the joint face super-resolution and frontalization task on the public face dataset Multi-PIE, which provides new ideas and references for this challenging topic.

关键词： Heating systems Attention mechanisms Superresolution Generative adversarial networks Informatics Faces

来源：评论

学校读者我要写书评

暂无评论

Testing Intelligence: Accelerating the Verification and Validation of Intelligent Vehicles

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2023年 1-14页

作者： Wang, Fei-Yue Hu, Jia Lai, Jintao State Key Laboratory for Management and Control of Complex Systems Chinese Academy of Sciences Beijing China ZhongTe Distinguished Chair in Cooperative Automation Professor Key Laboratory of Road and Traffic Engineering of the Ministry of Education Tongji University Shanghai China Key Laboratory of Road and Traffic Engineering of the Ministry of Education Tongji University Shanghai China

来源：评论

学校读者我要写书评

暂无评论

Aperiodically Intermittent control for Prescribed-Time Synchronization of Stochastic complex Networks

Aperiodically Intermittent Control for Prescribed-Time Synch...

引用

Youth Academic Annual Conference of Chinese Association of Automation (YAC)

作者： Haoyu Zhou Lei Xue Jian Liu Tong Wu Yongbao Wu Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Southeast University Nanjing China

ISBN: (数字)9798350379228

ISBN: (纸本)9798350390780

This paper tackles the challenge of achieving prescribed-time synchronization (PTS) for stochastic complex networks (SCNs) under the framework of aperiodically intermittent control (AIC). The adoption of a time-varying function ensures all states of the SCNs reach synchronization at the preset time. Compared with the PTS under the framework of deterministic systems, the introduction of stochastic disturbances has more practical significance. Introducing an auxiliary function makes the Lyapunov method mentioned in this paper valid under the AIC framework. Moreover, the AIC proposed in this paper relies on the average control rate instead of the infimum control rate, leading to less conservative results. At last, the viability of the theoretical results is confirmed by a simulation of a strongly connected digraph.

关键词： Automation Delay effects Directed graphs complex networks Synchronization Lyapunov methods Convergence

来源：评论

学校读者我要写书评

暂无评论

Enabling Few-Shot Learning with PID control: A Layer Adaptive Optimizer 41

Enabling Few-Shot Learning with PID Control: A Layer Adaptiv...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Yu, Le Li, Xinde Zhang, Pengfei Zhang, Zhentong Dunkin, Fir School of Automation Southeast University Nanjing China Nanjing Center for Applied Mathematics Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing China Southeast University Shenzhen Research Institute Shenzhen China

Model-Agnostic Meta-Learning (MAML) and its variants have shown remarkable performance in scenarios characterized by a scarcity of labeled data during the training phase of machine learning models. Despite these successes, MAML-based approaches encounter significant challenges when there is a substantial discrepancy in the distribution of training and testing tasks, resulting in inefficient learning and limited generalization across domains. Inspired by classical proportional-integral-derivative (PID) control theory, this study introduces a Layer-Adaptive PID (LA-PID) Optimizer, a MAML-based optimizer that employs efficient parameter optimization methods to dynamically adjust task-specific PID control gains at each layer of the network, conducting a first-principles analysis of optimal convergence conditions. A series of experiments conducted on four standard benchmark datasets demonstrate the efficacy of the LA-PID optimizer, indicating that LA-PID achieves state-of-the-art performance in few-shot classification and cross-domain tasks, accomplishing these objectives with fewer training steps. Code is available on https://***/yuguopin/LA-PID. Copyright 2024 by the author(s)

关键词：

来源：评论

学校读者我要写书评

暂无评论

Impact Angle control Guidance Law Against Maneuvering Targets

Impact Angle Control Guidance Law Against Maneuvering Target...

引用

International Conference on Guidance, Navigation and control, ICGNC 2024

作者： Du, He Yang, Ming Wang, Songyan Chao, Tao National Key Laboratory of Modeling and Simulation for Complex Systems Harbin Institute of Technology Heilongjiang150001 China Control and Simulation Center Harbin Institute of Technology Heilongjiang150001 China

ISBN: (纸本)9789819622313

To delineate a planar engagement scenario through mathematical expressions, the paper first establishes the connection between the desired line-of-sight and flight-path angle. Unlike conventional guidance laws that assume zero target maneuvering, which often results in significant impact angle errors, this approach employs an extended state observer to enhance tracking performance. Utilizing the error of angle, a sliding mode is devised to design the guidance law, with the stability of the proposed method validated through Lyapunov theory. The effectiveness and robustness of the method are demonstrated through numerical scenarios. This method offers precise estimation of target maneuvering and facilitates interception. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

A Image steganography Technique based on Denoising Diffusion Probabilistic Models

A Image steganography Technique based on Denoising Diffusion...

引用

Youth Academic Annual Conference of Chinese Association of Automation (YAC)

作者： Enzhi Xu Yang Cao Le Hu Chenxing Wang School of Automation Southeast University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Nanjing China

ISBN: (数字)9798350379228

ISBN: (纸本)9798350390780

Image steganography is the process of hiding secret information into an image while still keeping its original appearance intact. It plays a crucial role in secure communication and data storage. While deep learning-based techniques have shown notable progress in the field of image steganography, they still face challenges in extraction accuracy and robust security. This paper introduces an innovative image steganography method utilizing the diffusion model, which is the most powerful technique of image generation. Our method utilizes the sampling process of the diffusion model to hide the secret image in the generated image, and the receiver uses the secret key to extract the secret data accurately. The results of our experiments validate the effectiveness of our approach, outperforming existing methods in security, capacity, and extraction precision, which shows the potential for practical applications.

关键词： Resistance Steganography Visualization Accuracy Noise reduction Receivers Diffusion models

来源：评论

学校读者我要写书评

暂无评论

PVTimesNet: A Hybrid Deep Learning Method for Enhancing Ultra-short-term PV Power Forecasting

PVTimesNet: A Hybrid Deep Learning Method for Enhancing Ultr...

引用

2024 China Automation Congress, CAC 2024

作者： Wu, Ji Wang, Kai Ma, Wenwen Zhang, Jingxin Wang, Shibo China Electric Power Research Institute Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Southeast University Nanjing210096 China State Grid Shandong Electric Power Research Institute Jinan China

ISBN: (纸本)9798350368604

Accurate ultra-short-term photovoltaic (PV) power forecasting is crucial for the real-time scheduling of grid systems. However, the inherent variability of solar energy makes this task extremely challenging. To enhance PV power forecasting, this paper introduces a novel hybrid model named PVTimesNet, designed to harness the strengths of Convolutional Neural Network (CNN) and Long Short-Term Memory Network (LSTM) for effective feature extraction. PVTimesNet consists of two parallel branches: the CNN1d branch, which captures correlations between multiple variables and adjacent time steps, and the LSTM branch, which learns the temporal dependencies within the PV power sequences. The features extracted by both branches are then concatenated and passed through a fully connected layer to generate multi-step PV power forecasts. Experimental results demonstrate that for forecast horizons of 1 to 4 hours, the proposed model significantly outperforms individual models and other CNN-LSTM hybrid structures. Additionally, it exhibits superior performance compared to related methods for longer forecast horizons. © 2024 IEEE.

关键词： Hybrid power

来源：评论

学校读者我要写书评

暂无评论

Autonomous Vehicle Path Planning Algorithm Based on Improved Q-learning

Autonomous Vehicle Path Planning Algorithm Based on Improved...

引用

International Conference on Guidance, Navigation and control, ICGNC 2024

作者： Wang, Yuelong Wang, Songyan Chao, Tao Control and Simulation Center Harbin Institute of Technology Harbin150080 China National Key Laboratory of Modeling and Simulation for Complex Systems Harbin Institute of Technology Harbin150001 China

ISBN: (纸本)9789819622115

In the context of the rapid evolution of autonomous driving technology, the deployment of autonomous vehicle systems has witnessed significant expansion, underscoring the paramount importance of their path planning capabilities. This study proposes an improved Q-learning, specifically designed for the path planning of autonomous vehicles. Initially, the algorithm is enhanced with an advanced artificial potential field method for initializing the Q-table, thereby integrating prior knowledge and increasing the efficiency of the initial iterations. Further, the integration of eligibility traces as a memory mechanism within the algorithm ensures the prolonged influence of state-action pairs throughout the iterative process, thus boosting learning efficiency. Additionally, this paper introduces a dynamic λ adjustment strategy, tailored to meet the exploratory demands of autonomous vehicles and based on the simulated annealing algorithm. This strategy dynamically modulates the decay factor λ in accordance with the frequency of successful arrivals at the destinations, promoting more effective adaptation to varying environmental conditions. The empirical findings confirm the efficacy of the proposed Q-learning, particularly highlighting its utility in the path planning for autonomous vehicles. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

eVTOL Performance Analysis: A Review From control Perspectives

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年第5期9卷 1-13页

作者： Su, Jiangcheng Huang, Hailong Zhang, Hong Wang, Yutong Wang, Fei-Yue Department of Aeronautical and Aviation Engineering Hong Kong Polytechnic University Hong Kong China Co. Ltd. Guangzhou China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

Electric Vertical Takeoff and Landing (eVTOL) aircraft has gained significant attention as a basic element of urban air mobility (UAM), a potential solution for urban transportation challenges using low-altitude urban airspace. Ensuring the safe operation of eVTOL is crucial for UAM applications, which are related to various professional fields such as aerodynamics, control, structures, and power systems. This article systematically analyzes the characteristics of different design configurations, including multi-rotor, lift+cruise, and tilt-rotor types of eVTOL. The advantages and limitations of each type of eVTOL are analyzed. After that, the overall design problems are analyzed, and challenges of eVTOL control system design are discussed from aspects of overall control structure and subsystems, such as controller, sensors, actuators, and command generator. This article tries to fill the gap in the eVTOL design from a control perspective and provides some resolutions for the eVTOL application. IEEE

关键词： Air mobility

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：