检索结果-内蒙古大学图书馆

2023 International Conference on Frontiers of Robotics and Software engineering, FRSE 2023

作者： Guo, Sitong Zhang, Yu Zhejiang University Key Laboratory of Collaborative Sensing and Autonomous Unmanned Systems of Zhejiang Province State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Hangzhou China

ISBN: (纸本)9798350301113

Animals can navigate robustly through large unknown environments, utilizing inaccurate sensor and egomotion cues. Inspired by the mechanism of the human visual system, this paper presents a biological simultaneous localization and mapping (SLAM) system based on a monocular vision sensor to perform navigation tasks in complex environments. Specifically, our contributions are two folds: an improved monocular visual odometry with a scale recovery algorithm to calibrate the estimated robot pose, and a bionic vision model based on image enhancement algorithm and feature extraction approach to detect closed-loop. Experiments on public datasets demonstrate that our proposed method performs competitively in illumination-varying scenarios indoors and outdoors, which achieve a trade-off to maintain performances in terms of accuracy, execution time, and robustness. © 2023 IEEE.

关键词： Vision

来源：评论

学校读者我要写书评

暂无评论

Image Enhancement via Associated Perturbation Removal and Texture Reconstruction Learning

引用

IEEE/CAA Journal of Automatica Sinica 2024年第11期11卷 2253-2269页

作者： Kui Jiang Ruoxi Wang Yi Xiao Junjun Jiang Xin Xu Tao Lu IEEE the School of Computer Science and Technology Harbin Institute of Technology Zhengzhou Research Institute Harbin Institute of Technology the School of Artificial Intelligence Jianghan University the School of Geodesy and Geomatics Wuhan University the Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan University of Science and Technology the School of Computer Science and Engineering and also with the Hubei Province Key Laboratory of Intelligent Robot Wuhan Institute of Technology

Degradation under challenging conditions such as rain, haze, and low light not only diminishes content visibility, but also results in additional degradation side effects, including detail occlusion and color distortion. However, current technologies have barely explored the correlation between perturbation removal and background restoration, consequently struggling to generate high-naturalness content in challenging scenarios. In this paper, we rethink the image enhancement task from the perspective of joint optimization: Perturbation removal and texture reconstruction. To this end, we advise an efficient yet effective image enhancement model, termed the perturbation-guided texture reconstruction network(PerTeRNet). It contains two subnetworks designed for the perturbation elimination and texture reconstruction tasks, respectively. To facilitate texture recovery,we develop a novel perturbation-guided texture enhancement module(PerTEM) to connect these two tasks, where informative background features are extracted from the input with the guidance of predicted perturbation priors. To alleviate the learning burden and computational cost, we suggest performing perturbation removal in a sub-space and exploiting super-resolution to infer high-frequency background details. Our PerTeRNet has demonstrated significant superiority over typical methods in both quantitative and qualitative measures, as evidenced by extensive experimental results on popular image enhancement and joint detection tasks. The source code is available at https://***/kuijiang94/PerTeRNet.

关键词： Association learning attention mechanism image enhancement perturbation modeling

来源：评论

学校读者我要写书评

暂无评论

Residual Tensor Train: A Quantum-Inspired Approach for Learning Multiple Multilinear Correlations

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第5期4卷 1101-1113页

作者： Chen, Yiwei Pan, Yu Dong, Daoyi Zhejiang University Institute of Cyber-Systems and Control College of Control Science and Engineering Hangzhou310027 China Zhejiang University State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control College of Control Science and Engineering Hangzhou310027 China University of New South Wales School of Engineering and Information Technology CanberraACT2600 Australia

States of quantum many-body systems are defined in a high-dimensional Hilbert space, where rich and complex interactions among subsystems can be modeled. In machine learning, complex multiple multilinear correlations may also exist within input features. In this article, we present a quantum-inspired multilinear model, named residual tensor train (ResTT), to capture the multiple multilinear correlations of features, from low to high orders, within a single model. ResTT is able to build a robust decision boundary in a high-dimensional space for solving fitting and classification tasks. In particular, we prove that the fully connected layer and the Volterra series can be taken as special cases of ResTT. Furthermore, we derive the rule for weight initialization that stabilizes the training of ResTT based on a mean-field analysis. We prove that such a rule is much more relaxed than that of tensor train (TT), which means that ResTT can easily address the vanishing and exploding gradient problem that exists in the existing TT models. Numerical experiments demonstrate that ResTT outperforms the state-of-the-art tensor network and benchmark deep learning models on MNIST and Fashion-MNIST datasets. Moreover, ResTT achieves better performance than other statistical methods on two practical examples with limited data, which are known to have complex feature interactions. © 2020 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Optimal control of Constrained Trajectory Optimization Problem of UAV with Limited Sensing

Optimal Control of Constrained Trajectory Optimization Probl...

引用

2024 China Automation Congress, CAC 2024

作者： Xiao, Long Liu, Miao Wu, Xialai Guo, Shaopan Shi, Benyun Ci, Wenyan College of Computer and Information Engineering College of Artificial Intelligence Nanjing Tech University Nanjing China Huzhou Key Laboratory of Intelligent Sensing and Optimal Control for Industrial Systems Huzhou University Huzhou China

ISBN: (纸本)9798350368604

Optimal control of constrained unmanned aerial vehicle (UAV) trajectory optimization problem is one of the frontiers and hotspots of UAV research. The various constraints generated by physical limitations and obstacles in the environment increase the difficulties of solving the trajectory optimization problem, especially when the limited sensing ability is taken into consideration. This paper presents the receding horizon optimization method to obtain optimal control for the UAV with limited sensing range in a complex environment with obstacles. To improve efficiency, a path constraint processing method is proposed to reduce the number of constraints in the nonlinear programming problem (NLP). The proposed main structure and detailed algorithm are also given. The numerical results demonstrate the effectiveness of the proposed method compared with the classical Gauss pseudospectral method. © 2024 IEEE.

关键词： Nonlinear programming

来源：评论

学校读者我要写书评

暂无评论

Flexible Clockwork Recurrent Neural Network for multirate industrial soft sensor

引用

JOURNAL OF PROCESS control 2022年 119卷 86-100页

作者： [Anonymous] State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou 310027 China Zhejiang University NGICS Platform Hangzhou 310027 China

Data-driven-based soft sensors play significant roles in predicting key quality and optimizing the production process. Considering the difficulty and cost of variable acquisition, these variables are generally collected at different sampling rates. However, traditional soft sensor methods assume that data are uniformly sampled, which cannot be directly applied to multirate industrial scenarios. In this paper, a Flexible Clockwork Recurrent Neural Network (FCW-RNN) is proposed for multirate industrial soft sensors. First, the multirate data are divided into different variable groups according to their sampling rates. Then, an FCW-RNN is developed to map these variable groups into a common hidden space separately. A flexible clockwork mechanism is designed to incrementally update the hidden space at each moment based on the specific variable groups that have been sampled. Considering different sampling rates, the hidden space will be updated with time until all variable groups are sampled. In this way, we integrate the information of multirate data into the uniform hidden space step by step. Finally, a prediction module is established to calculate the hard-to-measure variables based on the hidden space. The effectiveness of FCW-RNN is demonstrated in a real coal mill case. (c) 2022 Elsevier Ltd. All rights reserved.

关键词： Multirate industrial processes Soft sensor Recurrent neural network Flexible clockwork mechanism

来源：评论

学校读者我要写书评

暂无评论

Fair Incentive Allocation for Secure Data Sharing in Blockchain Systems: A Shapley Value Based Mechanism 3rd

Fair Incentive Allocation for Secure Data Sharing in Block...

引用

3rd International Conference on Autonomous Unmanned Systems, ICAUS 2023

作者： Yang, Ming Feng, Honglin Wang, Xin Jiao, Xuguo Wu, Xiaoming Qin, Shuwei Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China School of Information and Control Engineering Qingdao University of Technology Qingdao China State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou China Department of Public Security of Shandong Province Shandong Intelligent Public Security Joint Innovation Center Jinan China

ISBN: (纸本)9789819710829

In the contemporary era of information technology, the exponential surge in data has rendered colossal potential value, which would be fully unlocked through data circulation and sharing. However, when the data contains sensitive information, special attention must be paid to the data privacy and security problem for data sharing. A feasible solution is to incorporate blockchain technology into the data sharing system, and the new challenge is how to provide fair rewards for data owners to motivate them to contribute data. To address this challenge, in this paper, we first design a blockchain-based data sharing system to enhance the trust and reliability of the data shared among participants. Then we propose an incentive allocation method based on the Shapley value, which comprehensively incorporates each participant’s contribution while ensuring fairness for the allocation. Finally, multiple numerical simulations are conducted to validate the effectiveness of the proposed mechanism. © Beijing HIWING Scientific and Technological Information Institute 2024.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Minimax entropy-based co-training for fault diagnosis of blast furnace

引用

Chinese Journal of Chemical engineering 2023年第7期59卷 231-239页

作者： Dali Gao Chunjie Yang Bo Yang Yu Chen Ruilong Deng The State Key Laboratory of Industrial Control Technology College of Control Science and EngineeringZhejiang UniversityHangzhou 310027China Jianwei Digital Sphere Co. LtdLianyungang 222113China Jiangsu Binxin Iron and Steel Group Co. LtdChongqing 401220China

Due to the problems of few fault samples and large data fluctuations in the blast furnace(BF)ironmaking process,some transfer learning-based fault diagnosis methods are *** vast majority of such methods perform distribution adaptation by reducing the distance between data distributions and applying a classifier to generate pseudo-labels for ***,since the training data is dominated by labeled source domain data,such classifiers tend to be weak classifiers in the target *** addition,the features generated after domain adaptation are likely to be at the decision boundary,resulting in a loss of classification ***,we propose a novel method called minimax entropy-based co-training(MMEC)that adversarially optimizes a transferable fault diagnosis model for the *** structure of MMEC includes a dual-view feature extractor,followed by two classifiers that compute the feature's cosine similarity to representative vector of each *** transfer is achieved by alternately increasing and decreasing the entropy of unlabeled target samples with the classifier and the feature extractor,*** BF fault diagnosis experiments show that our method improves accuracy by about 5%over state-of-the-art methods.

关键词： Co-training Fault diagnosis Blast furnace Minimax entropy Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Transient Angle Stability of Inverters Equipped with Robust Droop control

引用

CSEE Journal of Power and Energy Systems 2023年第2期9卷 659-670页

作者： Chen Qi keyou Wang Qing-Chang Zhong Jin Xu Guojie Li Key Laboratory of Control of Power Transmission and Conversion Ministry of EducationShanghai Jiao Tong UniversityShanghai 200240China Department of Electrical and Computer Engineering Illinois Institute of TechnologyChicagoIllinois60616USA

Transient angle stability of inverters equipped with the robust droop controller is investigated in this *** first,the conditions on the control references to guarantee the existence of a feasible post-disturbance operating point are ***,the post-disturbance equilibrium points are found and their stability properties are ***,the attraction regions of the stable equilibrium points are accurately depicted by calculating the stable and unstable manifolds of the surrounding unstable equilibrium points,which presents an explanation to system transient ***,the transient control considerations are provided to help the inverter ridethrough the disturbance and maintain its stability *** is shown that the transient angle stability is not a serious problem for droop controlled inverters with proper control settings.

关键词： Droop controlled inverter equilibrium point transient angle stability (un)stable manifold

来源：评论

学校读者我要写书评

暂无评论

Unity3D-based Virtual Click Interaction Implementation 23

Unity3D-based Virtual Click Interaction Implementation

引用

15th International Conference on computer Modeling and Simulation, ICCMS 2023

作者： Jing, Qishuai Du, Shuxin Qiu, Yi School of Engineering Huzhou University Huzhou Key Laboratory of Intelligent Sensing and Optimal Control for Industrial Systems China

ISBN: (纸本)9798400707919

In order to solve the problem of broken colliders caused by the fact that the object models for interaction are not constructed in one piece, but are built in pieces in the Unity3D macro virtual scene, this paper proposes a collider combining method, which enables the combining of colliders of objects in the scene, so that when the effective part of the object to be interacted with is clicked, the click of the object will be triggered event to display the data information. Finally, the collider combining method is applied in the virtual industrial park, and the colliders of the models to be interacted with in the virtual industrial park are successfully combined. The results show that this method can effectively interact with the target object model. © 2023 ACM.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

A Simple Framework to Generalized Zero-Shot Learning for Fault Diagnosis of industrial Processes

引用

IEEE/CAA Journal of Automatica Sinica 2023年第6期10卷 1504-1506页

作者： Jiacheng Huang Zuxin Li Zhe Zhou Huzhou Key Laboratory of Intelligent Sensing and Optimal Control for Industrial Systems School of EngineeringHuzhou UniversityHuzhou 313000China School of Intelligent Manufacturing Huzhou CollegeHuzhou 313000China

Dear Editor, This letter provides a simple framework to generalized zero-shot learning for fault diagnosis. For industrial process monitoring, supervised learning and zero-shot learning(ZSL) can only deal with seen and unseen faults, respectively. However, in the online monitoring stage of the actual industrial process, both seen and unseen faults may occur. This makes supervised learning and zero-shot learning impractical in industrial process monitoring.

关键词： see letter learning

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：