检索结果-内蒙古大学图书馆

Non-Line-of-Sight Multipath Classification Method for BDS Using Convolutional Sparse Autoencoder with LSTM

Tsinghua Science and Technology 2025年第1期30卷 68-86页

作者： Yahang Qin Zhenni Li Shengli Xie Bo Li Ming Liu Victor Kuzin School of Automation Guangdong University of Technologyand also with Guangdong-Hong Kong-Macao Joint Laboratory for Smart Discrete ManufacturingGuangzhou 510006China School of Automation Guangdong University of TechnologyGuangdong Key Laboratory of IoT Information TechnologyGuangzhou 510006China 111 Center for Intelligent Batch Manufacturing Based on IoT Technology Key Laboratory of Intelligent Information Processing and System Integration of IoTMinistry of EducationGuangzhou 510006China Department of Electronic and Computer Engineering Hong Kong University of Science and TechnologHong Kong 999077China Academician of Russian Engineering Academy Moscow Moscow 125009Russia

Multipath signal recognition is crucial to the ability to provide high-precision absolute-position services by the BeiDou Navigation Satellite system(BDS).However,most existing approaches to this issue involve supervised machine learning(ML)methods,and it is difficult to move to unsupervised multipath signal recognition because of the limitations in signal *** by an autoencoder with powerful unsupervised feature extraction,we propose a new deep learning(DL)model for BDS signal recognition that places a long short-term memory(LSTM)module in series with a convolutional sparse autoencoder to create a new autoencoder ***,we propose to capture the temporal correlations in long-duration BeiDou satellite time-series signals by using the LSTM module to mine the temporal change patterns in the time ***,we develop a convolutional sparse autoencoder method that learns a compressed representation of the input data,which then enables downscaled and unsupervised feature extraction from long-duration BeiDou satellite series ***,we add an l_(1/2) regularizer to the objective function of our DL model to remove redundant neurons from the neural network while ensuring recognition *** tested our proposed approach on a real urban canyon dataset,and the results demonstrated that our algorithm could achieve better classification performance than two ML-based methods(e.g.,11%better than a support vector machine)and two existing DL-based methods(e.g.,7.26%better than convolutional neural networks).

关键词： convolutional sparse autoencoder BeiDou Navigation Satellite system(BDS) long short-term memory(LSTM) multipath classification

来源：评论

学校读者我要写书评

暂无评论

Distributionally Robust control Synthesis for Stochastic systems with Safety and Reach-Avoid Specifications

arXiv

引用

arXiv 2025年

作者： Chen, Yu Li, Yuda Li, Shaoyuan Yin, Xiang Department of Automation Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China

We investigate the problem of synthesizing distributionally robust control policies for stochastic systems under safety and reach-avoid specifications. Using a game-theoretical framework, we consider the setting where the probability distribution of the disturbance at each time step is selected from an ambiguity set defined by the Wasserstein distance. The goal is to synthesize a distributionally robust control policy that ensures the satisfaction probability exceeds a specified threshold under any distribution within the ambiguity set. First, for both safety and reach-avoid specifications, we establish the existence of optimal policies by leveraging the dynamic programming principles. Then we demonstrate how the associated optimization problem can be efficiently solved using the dual representation of Wasserstein distributionally robust optimization. Furthermore, for safety specifications in particular, we introduce a novel concept of distributionally robust control barrier certificates and show how these enable the efficient synthesis of controllers through sum-of-squares programming techniques. Finally, our experimental results reveal that incorporating distributional robustness during the synthesis phase significantly improves the satisfaction probability during online execution, even with limited statistical knowledge of the disturbance distribution. Copyright © 2025, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Discovering the nuclear localization signal universe through a deep learning model with interpretable attention units

Patterns

引用

Patterns 2025年

作者： Li, Yi-Fan Pan, Xiaoyong Shen, Hong-Bin Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University and Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China

We describe NLSExplorer, an interpretable approach for nuclear localization signal (NLS) prediction. By utilizing the extracted information on nuclear-specific sites from the protein language model to assist in NLS detection, NLSExplorer achieves superior performance with greater than 10% improvement in the F1 score compared with existing methods on benchmark datasets and highlights other nuclear transport segments. We applied NLSExplorer to the nucleus-localized proteins in the Swiss-Prot database to extract valuable segments. A comprehensive analysis of these segments revealed a potential NLS landscape and uncovered features of nuclear transport segments across 416 species. This study introduces a powerful tool for exploring the NLS universe and provides a versatile network that can efficiently detect characteristic domains and motifs. © 2025 The Author(s)

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Optimizing Fixed-Time Generalized Nash Equilibrium Seeking in Multi-Unmanned Aerial Vehicle Games

引用

IEEE Transactions on Aerospace and Electronic systems 2025年

作者： Hua, Menghu Yao, Xiang-Yu Liu, Wen-Jin Geng, Mei-Jie Lv, Maolong China University of Geosciences School of Mechanical Engineering and Electronic Information Wuhan430074 China Ministry of Education Key Laboratory of System Control and Information Processing Shanghai 200240 China Air Force Engineering University College of Air Traffic Control and Navigation Xi'an710038 China

This study addresses a fixed-time generalized noncooperative game involving multiple unmanned aerial vehicles (UAVs) that encounter challenges such as discontinuous communication and external disturbances. Each UAV, motivated by selfinterest, seeks to optimize its performance function by adjusting its actions within shared equality and inequality constraints. To facilitate this, a fixed-time generalized Nash equilibrium (GNE) seeking algorithm is proposed for games with shared equality constraints, incorporating an internal dynamic system to ensure compliance with these constraints. By employing penalty methods, an auxiliary performance function is developed to manage games with mixed constraints. Furthermore, an error decomposition method and a fixed-time observer are introduced to address the issues of discontinuous communication and external disturbances. The study establishes sufficient conditions for the convergence of the fixed-time GNE seeking algorithm and provides an explicit upper bound on the settling time based on Lyapunov stability theory. The effectiveness of the proposed algorithms is demonstrated through various simulation examples. © 1965-2011 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

Target extraction based on hybrid domain features of array GM-APD lidar 10

Target extraction based on hybrid domain features of array G...

引用

10th Symposium on Novel Optoelectronic Detection Technology and Applications

作者： Zhang, Xin Li, Sining Sun, Jianfeng Jiang, Peng Jin, Haowei National Key Laboratory of Laser Spatial Information Institute of Opto-Electronic Harbin Institute of Technology Heilongjiang Harbin150001 China Zhengzhou Research Institute of Harbin Institute of Technology Henan Zhengzhou450000 China National Key Laboratory of Complex System Control and Intelligent Agent Cooperation Beijing100074 China

ISBN: (数字)9781510688155

ISBN: (纸本)9781510688148

This study proposes a target extraction algorithm for array GM-APD lidar based on hybrid domain features, designed to address the challenges of accurately extracting target region based on the image in complex scenes and high noise interference. We extracted the temporal features of the echo signals and transformed the echo signals into the image domain to enhance the information content and further extract image features. By integrating multi-view K-means clustering and AdaBoost classification methods, we introduced a dynamic weight adjustment mechanism and a region adjustment method based on a correlation coefficient to achieve pixel-type discrimination and target region extraction. Experimental results demonstrate that the proposed method exhibits good robustness and adaptability in complex detection environments. Under conditions of different occlusion, different signal-to-noise ratios, and different target reflectivity, the proposed algorithm significantly outperforms traditional region-growing segmentation methods in terms of accuracy of target region extraction. © 2025 SPIE.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Resilient Distributed Quadrotor UAVs Game: Addressing FDI and Physical Attacks

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Geng, Mei-Jie Ding, Hua-Feng Yao, Xiang-Yu Lv, Maolong China University of Geosciences School of Mechanical Engineering and Electronic Information Wuhan430074 China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai200240 China Air Force Engineering University College of Air Traffic Control and Navigation Xi'an710038 China

Distributed quadrotor unmanned aerial vehicles (UAVs) are increasingly deployed in critical applications, including reconnaissance, disaster response, and transportation, where system resilience is paramount. However, their complex dynamics and reliance on cyber-physical systems make them highly vulnerable to adversities such as uncertain dynamics, time-varying input disturbances, false data injection (FDI), and physical attacks. This paper proposes a hierarchical framework consisting of a game layer and an execution layer to enhance the resilience of a noncooperative game involving distributed UAVs. In the game layer, a novel FDI observer mitigates communication and computational FDI attacks, facilitating convergence to infinitesimal ranges around the Nash equilibrium (NE) point. The execution layer addresses uncertain dynamics and physical attacks, ensuring that UAVs can track a narrow neighborhood of the NE even in the presence of actuator failures. Extensive simulations validate the algorithm's effectiveness and robustness against mixed attack scenarios, underscoring its potential for real-world UAV applications. © 1967-2012 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

Transfer learning with a spatiotemporal graph convolution network for city flowprediction

引用

Frontiers of information Technology & Electronic Engineering 2025年第1期26卷 79-92页

作者： Binkun LIU Yu KANG Yang CAO Yunbo ZHAO Zhenyi XU Department of Automation University of Science and Technology of ChinaHefei 230026China Key Laboratory of System Control and Information Processing Ministry of EducationShanghai 200240China Institute of Artificial Intelligence Hefei Comprehensive National Science CenterHefei 230088China Institute of Advanced Technology University of Science and Technology of ChinaHefei 230088China

Recently,deep learning based city flow prediction has been extensively used in the establishment of *** methods are data-hungry,making them unscalable to areas lacking *** transfer learningcan use data-rich source domains to assist target domain cities in city flow prediction,the performance of existingmethods cannot meet the needs of actual use,because the long-distance road network connectivity is *** this problem,we propose a transfer learning method based on spatiotemporal graph convolution,in which weconstruct a co-occurrence space between the source and target domains,and then align the mapping of the sourceand target domains’data in this space,to achieve the transfer learning of the source city flow prediction modelon the target ***,a dynamic spatiotemporal graph convolution module along with a temporalencoder is devised to simultaneously capture the concurrent spatiotemporal features,which implies the inherentrelationship among the road network structures,human travel habits,and city bike ***,these concurrentfeatures are leveraged as cross-city invariant representations and nonlinearly spanned to a co-occurrence *** domain features are thereby aligned with the source domain features in the co-occurrence space by using aMahalanobis distance loss,to achieve cross-city bike flow *** proposed method is evaluated on the publicbike flow datasets in Chicago,New York,and Washington in 2015,and significantly outperforms state-of-the-arttechniques.

关键词： Transfer learning City flow prediction Spatiotemporal graph convolution

来源：评论

学校读者我要写书评

暂无评论

Learning-based 3D Reconstruction in Autonomous Driving: A Comprehensive Survey

arXiv

引用

arXiv 2025年

作者： Liao, Liewen Yan, Weihao Yang, Ming Zhang, Songan Global Institute of Future Technology Shanghai Jiao Tong University Key Labeoratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China Department of Automation Shanghai Jiao Tong University Key Labeoratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China

Learning-based 3D reconstruction has emerged as a transformative technique in autonomous driving, enabling precise modeling of both dynamic and static environments through advanced neural representations. Despite data augmentation, 3D reconstruction inspires pioneering solution for vital tasks in the field of autonomous driving, such as scene understanding and closed-loop simulation. We investigates the details of 3D reconstruction and conducts a multi-perspective, in-depth analysis of recent advancements. Specifically, we first provide a systematic introduction of preliminaries, including data modalities, benchmarks and technical preliminaries of learning-based 3D reconstruction, facilitating instant identification of suitable methods according to sensor suites. Then, we systematically review learning-based 3D reconstruction methods in autonomous driving, categorizing approaches by subtasks and conducting multi-dimensional analysis and summary to establish a comprehensive technical reference. The development trends and existing challenges are summarized in the context of learning-based 3D reconstruction in autonomous driving. We hope that our review will inspire future researches. Copyright © 2025, The Authors. All rights reserved.

关键词： 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

An online self-organizing radial basis function neural network based on Gaussian Membership

引用

Applied Intelligence 2025年第6期55卷 1-17页

作者： Jia, Lijie Li, Wenjing Qiao, Junfei Zhang, Xinliang School of Electrical Engineering and Automation Henan International Joint Laboratory of Direct Drive and Control of Intelligent Equipment Henan Polytechnic University Jiaozuo454003 China Faculty of Information Technology Beijing University of Technology No. 100 Pingleyuan Chaoyang District Beijing100124 China Beijing Key Laboratory of Computational Intelligence and Intelligent System No. 100 Pingleyuan Chaoyang District Beijing100124 China

Radial basis function neural network (RBFNN) is one of the most popular neural networks, and an appropriate selection of its structure and learning algorithms is crucial for its performance. Aiming to alleviate the sensitivity of the RBFNN to its parameters and improve the overall performance of the network, this study proposes a Gaussian Membership-based online self-organizing RBF neural network (GM-OSRBFNN). First, the Gaussian Membership is introduced to enhance network insensitivity to network parameters and used as a similarity metric to indicate the similarity between the sample to a hidden neuron and that between hidden neurons. Second, the similarity metric is used to design the neuron addition and merging rules to achieve a self-organizing network structure, and error constraints are introduced to the neuron addition rule;also, the noisy neuron deletion rule is defined to make the network structure more compact. In addition, an online fixed mini-batch gradient algorithm is used for online learning of network parameters, which can guarantee fast and stable convergence of the network. Finally, the proposed GM-OSRBFNN is tested on common nonlinear system modeling problems to verify its effectiveness. The experimental results show that compared to the existing models, the GM-OSRBFNN can achieve competitive prediction performance with a more compact network structure, faster convergence speed, and, more importantly, better insensitivity to network parameters. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Radial basis function networks

来源：评论

学校读者我要写书评

暂无评论

Incipient fault diagnosis method for silicon single crystal growth assisted by deep learning

引用

CrystEngComm 2025年第21期27卷 3480-3491页

作者： Liu, Yu-Yu Liu, Ding Ren, Jun Chao Wu, Shi Hai School of Automation and Information Engineering Xi'an University of Technology Xi'an710048 China Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an China

In this study, an accurate diagnostic classification algorithm based on a deep belief network and entropy value (C-DBN-E) incorporating signal decomposition, entropy theory and deep belief network (DBN) network is proposed to address the problem of tiny faults that may occur during the growth of silicon single crystals (SSC). The study is divided into three stages: feature selection, fault feature extraction and fault pattern classification. In the feature selection stage, the recursive feature elimination (RFE) method based on support vector machine (SVM) is employed to rank features according to their importance and eliminate redundant features. In the subsequent feature extraction stage, the adaptive decomposition theory is introduced to select components that contain a greater number of fault features for signal reconstruction. The deep features of the reconstructed signal are then mined in depth using a DBN and supplemented with energy entropy and multi-scale arrangement entropy as supplementary features to further refine the capture of tiny fault information. Finally, all the features are integrated and inputted into the SVM classifier to enable accurate classification of micro-fault modes in SSC growth. The effectiveness of the method in distinguishing micro-faults in the SSC growth process is verified by simulation results. This study is of great significance in solving the problem of fault diagnosis in the SSC growth system, which is expected to contribute to the improvement of work performance and the reduction of accident risk and economic loss. © 2025 The Royal Society of Chemistry.

关键词： Image reconstruction

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：