检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Xu, Biao Rang, Gejie Li, Wenji Gong, Dunwei Fan, Zhun Yang, Shengxiang He, Jie College of Engineering Shantou University Shantou515063 China College of Automation and Electronic Engineering Qingdao University of Science and Technology Qingdao266100 China Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou University Wuzhou543002 China Shenzhen institute for Advanced Study UESTC Shenzhen518110 China School of Computer Science and Informatics De Montfort University LeicesterLE1 9BH United Kingdom Minjiang University China

Dynamic multiobjective optimization problems (DMOPs) present significant challenges to conventional evolutionary optimization methods because of the continuous changes in their Pareto-optimal sets (PSs) and fronts (PFs). Prediction-driven approaches have demonstrated potential in rapidly adapting to these changes. However, many existing methods depend on linear models to forecast the evolving PSs, which may be restrictive. To counteract this limitation, this research presents a novel dynamic multiobjective evolutionary optimization algorithm that incorporates predictions from long short-term memory (LSTM) networks. Initially, in our methodology, the PS for each problem is segmented into multiple clusters, and the centroid of each cluster is identified. These cluster centroids, representing the PSs across various environmental conditions, are then transformed into a series of time series data. The LSTM network models are subsequently trained on this time series data as input samples. Utilizing these refined models, the centroids of the evolving PSs are predicted with improved precision. Moreover, to enhance the performance of the algorithm, an innovative population-generation strategy is also introduced that guarantees a well-converged and diverse starting population. Our proposed algorithm undergoes rigorous testing using benchmark functions, and the outcomes validate its proficiency in tackling DMOPs, showing superior performance compared to existing state-of-the-art algorithms. © 2024, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

PUGAN: Physical Model-Guided Underwater Image Enhancement Using GAN with Dual-Discriminators

arXiv

引用

arXiv 2023年

作者： Cong, Runmin Yang, Wenyu Zhang, Wei Li, Chongyi Guo, Chun-Le Huang, Qingming Kwong, Sam Institute of Information Science Beijing Jiaotong University Beijing100044 China School of Control Science and Engineering Shandong University Jinan250061 China Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan250061 China Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing100044 China College of Computer Science Nankai University Tianjin300350 China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Peng Cheng Laboratory Shenzhen518055 China Department of Computer Science City University of Hong Kong Hong Kong City University of Hong Kong Shenzhen Research Institute Shenzhen51800 China

Due to the light absorption and scattering induced by the water medium, underwater images usually suffer from some degradation problems, such as low contrast, color distortion, and blurring details, which aggravate the difficulty of downstream underwater understanding tasks. Therefore, how to obtain clear and visually pleasant images has become a common concern of people, and the task of underwater image enhancement (UIE) has also emerged as the times require. Among existing UIE methods, Generative Adversarial Networks (GANs) based methods perform well in visual aesthetics, while the physical model-based methods have better scene adaptability. Inheriting the advantages of the above two types of models, we propose a physical model-guided GAN model for UIE in this paper, referred to as PUGAN. The entire network is under the GAN architecture. On the one hand, we design a Parameters Estimation subnetwork (Par-subnet) to learn the parameters for physical model inversion, and use the generated color enhancement image as auxiliary information for the Two-Stream Interaction Enhancement subnetwork (TSIE-subnet). Meanwhile, we design a Degradation Quantization (DQ) module in TSIE-subnet to quantize scene degradation, thereby achieving reinforcing enhancement of key regions. On the other hand, we design the Dual-Discriminators for the style-content adversarial constraint, promoting the authenticity and visual aesthetics of the results. Extensive experiments on three benchmark datasets demonstrate that our PUGAN outperforms state-of-the-art methods in both qualitative and quantitative metrics. The code and results can be found from the link of https://***/proj_***. © 2023, CC BY-NC-SA.

关键词： Discriminators

来源：评论

学校读者我要写书评

暂无评论

AADL and Modelica model combination and model conversion based on CPS 4

AADL and Modelica model combination and model conversion bas...

引用

4th International Conference on Electronic Information technology and Computer Engineering, EITCE 2020

作者： Zhu, Yifeng Cao, Zining Wang, Fujun Lu, Weiwei College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China College of Computer Science and Technology Collaborative Innovation Center of Novel Software Technology and Industrialization Miit Key Laboratory of Pattern Analysis and Machine Intelligence Luoyang China Science and Technology on Electro-optic Control Laboratory Luoyang China

ISBN: (纸本)9781450387811

Cyber-Physical System (CPS), which realizes the close integration of physical resources and information resources, is a distributed and asynchronous dynamic hybrid system running in different time and space. In this paper, we use AADL to model information system and use Modelica to model physical system. However, they are all semi-formal models such that we cannot do future work about formal verification. To overcome this defect, we convert them to formal models like automaton through conversion algorithms and rules. Due to the fact of probabilistic events and resource consumption in CPS, this paper adopts the weighted probabilistic hybrid automaton as formal model, and adds the properties of probability and weight to the behavior annex of AADL. Then we conduct the rule and algorithm of the model conversion. In order to ensure consistency of further work about model checking, the paper prove the equivalence of the two models by bisimulation. Finally, the capability of modeling of the extended modeling language of AADL and the significance of conversion to automaton is illustrated by the aircraft system. © 2020 ACM.

关键词： Cyber Physical System

来源：评论

学校读者我要写书评

暂无评论

Traffic Flow Prediction via Weighted Combination of ARIMA and WASDNN Models

Traffic Flow Prediction via Weighted Combination of ARIMA an...

引用

第33届中国控制与决策会议

作者： Xiao Liu Yunong Zhang Min Yang Zhongxian Xue Chengxu Ye School of Electronics and Information Technology Sun Yat-sen University Guangdong Key Laboratory of Modern Control Technology Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education School of Data and Computer Science Sun Yat-sen University School of Computer Science Qinghai Normal University

The modeling and prediction of traffic flow are important in transportation study and traffic network *** from individual models,a hybrid model which is a combination of autoregressive integrated moving average(ARIMA) and weights and structure determination neural network(WASDNN) models,is proposed for modeling and prediction of traffic *** with individual models like ARIMA and WASDNN,the proposed ARIMAWASDNN model has better performance in modeling and prediction of traffic flow of Shenzhen city as an *** addition,prediction results of different activation functions of hidden layer neurons are *** is more,the proposed ARIMA-WASDNN model also performs better than the popular long short-term memory(LSTM) model in predicting traffic flow of Shenzhen *** effectiveness and superiority of ARIMA-WASDNN model are substantiated by results of numerical experiments.

关键词： Time series traffic flow prediction autoregressive integrated moving average(ARIMA) model weights and structure determination(WASD) algorithm

来源：评论

学校读者我要写书评

暂无评论

Prediction of PM2.5 Concentration on the Basis of Multi Temporal Spatial Scale Fusion

SSRN

引用

SSRN 2023年

作者： Gong, He Guo, Jie Luo, Tianye Mu, Ye Hu, Tianli Guo, Ying Li, Shijun Li, Xue Bao, Yu Sun, Yu College of Information Technology Jilin Agricultural University Changchun130118 China Jilin Province Agricultural Internet of Things Technology Collaborative Innovation Center Changchun130118 China Jilin Province Intelligent Environmental Engineering Research Center Changchun130118 China Jilin Provincial Engineering Research Center of Information Technology and Intelligent Agriculture Changchun130118 China College of Information Technology Wuzhou University Wuzhou543003 China Guangxi Key Laboratory of Machine Vision and Inteligent Control Wuzhou543003 China School of Life Sciences Changchun Normal University Changchun130032 China

Air pollution can be predicted by deep learning. Current deep learning-based prediction models only consider the nonlinear relationship between PM2.5 concentration and explanatory variables or the time correlation of air quality monitoring station data. Spatial correlation is not well incorporated into the PM2.5 prediction model. Long-term prediction is challenging because air pollution concentrations in the past and the future are frequently different. A convolutional long short term memory (LSTM) network-based multi feature extraction neural network model is suggested for forecasting air pollution. In order to extract time characteristics at different scales, a multi-branch network structure is constructed. We create the 3D-SA-LSTM by fusing 3D convolution and self-attention to extract spatio-temporal features. By fusing features from various scales, fusion prediction can predict the spatio-temporal distribution of PM2.5. We made comparisons. Because the root mean square error (RMSE) is reduced by 5.99, 6.07, and 6.01, respectively, when predicting PM2.5 concentrations for the following day, three days, and seven days, the experimental results demonstrate that the proposed method has strong spatio-temporal feature modeling capability and is suitable for regional PM2.5 prediction. © 2023, The Authors. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

B2e-Cdg: Artifact Removal for Enhanced Optical Coherence Tomography Angiography Using Conditional Guidance Diffusion

SSRN

引用

SSRN 2024年

作者： Xu, Jing Fu, Suzhong Xing, Jiwei Xue, Linyan Wang, Cheng Tuchin, Valery V. Zhao, Qingliang State Key Laboratory of Molecular Vaccinology and Molecular Diagnostics Organ Transplantation Institute China Institute of Artificial Intelligence Xiamen University Xiamen361102 China State Key Laboratory of Vaccines for Infectious Diseases Xiang An Biomedicine Laboratory School of Public Health Xiamen University Xiamen361102 China Shenzhen518172 China College of Quality and Technical Supervision Hebei University Baoding071002 China School of Informatics Computer Science and Technology Department Xiamen University Xiamen361005 China Institute of Physics and Science Medical Center Saratov State University Saratov410012 Russia Laboratory of Laser Molecular Imaging and Machine Learning Tomsk State University Tomsk634050 Russia Institute of Precision Mechanics and Control FRS "Saratov Scientific Centre of the RAS" Saratov410028 Russia China

Optical Coherence Tomography Angiography (OCTA) is a revolutionary technology widely used to diagnose and manage fundus, skin and cardiovascular diseases. However, unavoidable movements, such as breathing, cause motion artifacts in images, which can significantly degrade image quality, obscure critical vascular details, and reduce the diagnostic reliability of the modality. Although recent advances in learning-based image inpainting methods for OCTA enface images have made notable progress in artifact removal, these methods still require the collection of large amounts of accurately labeled data and the generation of pseudo stripes to create paired training sets. Furthermore, the abundant structural information and flow intensity signals present in OCTA B-scans are nonnegligible. Hence we proposed B-scans to Enface Conditional Diffusion Guidance (B2E-CDG) for translation from signal-void B-scans to available B-scans. We introduce the normal B-scans in a connection manner and the specified reference B-scans in a gradient-based manner as style feature guidance into the diffusion model. Conditional guidance facilitates a more controllable and precise generation process for B-scans flow signal recovery. The requirement for labeled image collection and pseudo stripes is obviated, as the repetitive scanning nature of OCTA naturally results in paired datasets comprising signal-void and normal B-scans. The experimental results demonstrated that B2E-CDG effectively removes artifacts and restores vascular and structural information obscured by artifacts. This work shows superior vascular recovery and artifact removal capabilities in metrics and downstream tasks, enhancing the usability of OCTA in diagnostics. © 2024, The Authors. All rights reserved.

关键词： Optical coherence tomography

来源：评论

学校读者我要写书评

暂无评论

Zhang Neurodynamics for Cholesky Decomposition of Matrix Stream Using Pseudo-Inverse with Transpose of Unknown

Zhang Neurodynamics for Cholesky Decomposition of Matrix Str...

引用

第40届中国控制会议

作者： Xiu Zeng Min Yang Jinjin Guo Yihong Ling Yunong Zhang School of Computer Science and Engineering Sun Yat-sen University School of Information and Communication Engineering Guangzhou Maritime University School of Electronics and Information Technology Sun Yat-sen University Guangdong Key Laboratory of Modern Control Technology Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education

Cholesky decomposition is a well-known decomposition for positive definite matrix. On account of its significantly fundamental roles in linear algebra and matrix theory, there are a lot of researches and applications based on it. In recent years,solving time-varying problems has been a research hotspot, but Cholesky decomposition of matrix stream（i.e., continuous timevarying matrix） in a simple, direct and effective equation-solving manner remains a challenging issue. In this paper, the problem of Cholesky decomposition of matrix stream is attempted and solved. First, with the aid of Zhang neurodynamics（ZN）, the objective equation at time-derivative level, including the time derivatives of matrix variable and its transpose, is obtained. In order to handle the objective equation with transpose of unknown, Kronecker product, vectorization technique and vectorized transpose matrix are utilized for better derivation. Thus, a ZN solution model using pseudo-inverse is proposed and numerically experimented. Finally, numerical experiment results substantiate the efficacy of the pseudo-inverse type ZN solution model.

关键词： Cholesky decomposition Matrix stream Transpose of unknown Zhang neurodynamics Vectorized transpose matrix

来源：评论

学校读者我要写书评

暂无评论

AADL and Modelica model combination and model conversion based on CPS 20

AADL and Modelica model combination and model conversion bas...

引用

Proceedings of the 2020 4th International Conference on Electronic Information technology and Computer Engineering

作者： Yifeng Zhu Zining Cao Fujun Wang Weiwei Lu College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China College of Computer Science and Technology Collaborative Innovation Center of Novel Software Technology and Industrialization MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing University of Aeronautics and Astronautics and Science and Technology on Electro-optic Control Laboratory Luoyang China Science and Technology on Electro-optic Control Laboratory Luoyang China

ISBN: (纸本)9781450387811

关键词： Cyber-Physical System model conversion weighted probabilistic hybrid automaton AADL behavior annex bisimulation

来源：评论

学校读者我要写书评

暂无评论

ZND-ZeaD Models and Theoretics Including Proofs for Takagi Factorization of Complex Time-Dependent Symmetric Matrix

ZND-ZeaD Models and Theoretics Including Proofs for Takagi F...

引用

第33届中国控制与决策会议

作者： Zhuosong Fu Min Yang Jinjin Guo Jianrong Chen Yunong Zhang School of Computer Science and Engineering Sun Yat-sen University Guangdong Key Laboratory of Modern Control Technology Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education School of Electronics and Information Technology Sun Yat-sen University School of Public Health and Management Youjiang Medical University for Nationalities

Takagi factorization(TF) is a kind of matrix factorization(also termed,decomposition) *** this paper,the problem of TF for complex time-dependent symmetric matrix(simply termed,time-dependent Takagi factorization)is presented and theoretically *** simplify the tough problem,we first consider converting it into an equivalent equation ***,a continuous-time(CT) TF(CTTF) model is presented and derived theoretically,by adopting ZND(Zhang neural dynamics,or termed,Zhang neural network) method and a dimensional reduction *** order to facilitate the implementation on digital hardware platforms,the corresponding discrete-time(DT) ZND solution models(or termed,algorithms) with different discretization precisions of the CTTF model are presented and taken into theoretical ***,we present and investigate a discrete-time TF(DTTF) model,termed eight-instant DTTF(8IDTTF) model,by using a new eight-instant Zhang et al discretization(ZeaD,also termed,Zhang time discretization,ZTD) formula to discretize the CTTF ***,two other DTTF models,termed four-instant DTTF(4IDTTF) and six-instant DTTF(6IDTTF) models,are presented respectively,on the basis of two corresponding multiinstant ZeaD ***,the effective solution step-size intervals of the three DTTF models are further presented and proved.

关键词： Time-dependent Takagi factorization Dimensional reduction Zhang neural dynamics(ZND) Kronecker product Zhang et al discretization(ZeaD) formulas

来源：评论

学校读者我要写书评

暂无评论

Dispatching and control Information Freshness-Aware Federated Learning for Simplified Power IoT

Dispatching and Control Information Freshness-Aware Federate...

引用

GLOBECOM 2022 - 2022 IEEE Global Communications Conference

作者： Zehan Jia Ziqi Yu Haijun Liao Zhao Wang Zhenyu Zhou Xiaoyan Wang Guoqing He Shahid Mumtaz Mohsen Guizani Hebei Key Laboratory of Power Internet of Things Technology North China Electric Power University Beijing Baoding Hebei China Graduate School of Science and Engineering Ibaraki University Ibaraki-ken Japan State Key Laboratory of Operation and Control of Renewable Energy & Storage Systems China Electric Power Research Institute Beijing China Instituto de Telecomunicações Aveiro Portugal Machine Learning Department Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI) UAE

ISBN: (纸本)9781665435413

Dispatching and control information freshness conducts an important impact on the training accuracy of distributed energy dispatching and control model. Poor information freshness will increase the loss function of the training model, and reduce the reliability and economy of dispatching and control. Simplified power internet of things can provide plug-and-play and multi- mode fusion communication support, but it still faces challenges of the coupling of model training and data transmission as well as the difficulty in guaranteeing dispatching and control information freshness. In this paper, a semi-distributed federated learning- based framework for dispatching and control model training decision-making is proposed, and a dispatChing and control informAtion fReshness-aware batch size Optimization aLgorithm (CAROL) is presented. CAROL leverages deep Q network and dispatching and control information freshness awareness to learn the batch size optimization strategy. CAROL can minimize model loss function while guaranteeing long-term dispatching and control information freshness constraints. Compared with existing feder- ated learning algorithms, CAROL achieves superior performance in global loss function and information freshness.

关键词： Training Computational modeling Simulation Decision making Minimization Dispatching Data models

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：