检索结果-内蒙古大学图书馆

Dissecting and Mitigating Semantic Discrepancy in Stable Diffusion for Image-to-Image Translation

IEEE-CAA JOURNAL OF AUTOMATICA SINICA 2025年第4期12卷 705-718页

作者： Yuan, Yifan Yang, Guanqun Wang, James Z. Zhang, Hui Shan, Hongming Wang, Fei-Yue Zhang, Junping Fudan Univ Sch Comp Sci Shanghai Key Lab Intelligent Informat Proc Shanghai 200433 Peoples R China Fuxi Team NetEase Corp Hangzhou Peoples R China Penn State Univ Coll Informat Sci & Technol University Pk PA 16802 USA Beijing Jiaotong Univ Sch Comp & Informat Technol Beijing 100098 Peoples R China Fudan Univ Inst Sci & Technol Brain inspired Intelligence Shanghai 200433 Peoples R China Fudan Univ MOE Frontiers Ctr Brain Sci Shanghai 200433 Peoples R China Shanghai Ctr Brain Sci & Brain inspired Technol Shanghai 200031 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Macau Univ Sci & Technol Inst Syst Engn Macau Peoples R China Qingdao Acad Intelligent Ind Qingdao 266109 Peoples R China

Finding suitable initial noise that retains the original image's information is crucial for image-to-image (I2I) translation using text-to-image (T2I) diffusion models. A common approach is to add random noise directly to the original image, as in SDEdit. However, we have observed that this can result in "semantic discrepancy" issues, wherein T2I diffusion models mis-interpret the semantic relationships and generate content not present in the original image. We identify that the noise introduced by SDEdit disrupts the semantic integrity of the image, leading to unintended associations between unrelated regions after U-Net upsampling. Building on the widely-used latent diffusion model, Stable Diffusion, we propose a training-free, plug-and-play method to alleviate semantic discrepancy and enhance the fidelity of the translated image. By leveraging the deterministic nature of denoising diffusion implicit models (DDIMs) inversion, we correct the erroneous features and correlations from the original generative process with accurate ones from DDIM inversion. This approach alleviates semantic discrepancy and surpasses recent DDIM-inversion-based methods such as PnP with fewer priors, achieving a speedup of 11.2 times in experiments conducted on COCO, ImageNet, and ImageNet-R datasets across multiple I2I translation tasks.

关键词： Translation Correlation Codes Image edge detection Semantics Noise Noise reduction Text to image Diffusion models Erosion DDIM inversion diffusion model image-to-image translation semantic discrepancy stable diffusion

来源：评论

学校读者我要写书评

暂无评论

Correlation analysis and text classification of chemical accident cases based on word embedding

引用

PROCESS SAFETY AND ENVIRONMENTAL PROTECTION 2022年第0期158卷 698-710页

作者： Jing, Sifeng Liu, Xiwei Gong, Xiaoyan Tang, Ying Xiong, Gang Liu, Sheng Xiang, Shuguang Bi, Rongshan Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Qingdao Univ Sci & Technol Coll Chem Engn Qingdao 266042 Peoples R China Qingdao Acad Intelligent Ind Inst Smart Educ Syst Qingdao 266044 Peoples R China Rowan Univ Dept Elect & Comp Engn Glassboro NJ 08028 USA

Accident precursors can provide valuable clues for risk assessment and risk warning. Trends such as the main characteristics, common causes, and high-frequency types of chemical accidents can provide references for formulating safety-management strategies. However, such information is usually documented in unstructured or semistructured free text related to chemical accident cases, and it can be costly to manually extract the information. Recently, text-mining methods based on deep learning have been shown to be very effective. This study, therefore, developed a text-mining method for chemical accident cases based on word embedding and deep learning. First, the word2vec model was used to obtain word vectors from a text corpus of chemical accident cases. Then, a bidirectional long short-term memory (LSTM) model with an attention mechanism was constructed to classify the types and causes of Chinese chemical accident cases. The case studies revealed the following results: 1) Common trends in chemical accidents (e.g., characteristics, causes, high-frequency types) could be obtained through correlation analysis based on word embedding;2) The developed text-classification model could classify different types of accidents as fires, explosions, poisoning, and others, and the average p (73.1%) and r (72.5%) of the model achieved ideal performance for Chinese text classification;3) The developed text-classification model could classify the causes of accidents as personal unsafe act, personal habitual behavior, unsafe conditions of equipment or materials and vulnerabilities management strategy;p and r were 63.6% for the causes of vulnerabilities management strategy, and the average p and r are both 60.7%;4) the accident precursors of explosion, fire, and poisoning were obtained through correlation analyses of each high-frequency type of chemical accident case based on text classification;5) the text-mining method can provide site managers with an efficient tool for extracting

关键词： Text mining Correlation analysis Text classification Word embedding Deep learning Chemical accident cases

来源：评论

学校读者我要写书评

暂无评论

An Edge Computing Architecture Based on Unikernel

An Edge Computing Architecture Based on Unikernel

引用

2022 Australian and New Zealand control Conference

作者： Chen, Shichao Xu, Ruijie Sun, Wenqiao Chinese Acad Sci State Key Lab Management & Control Complex Syst I Ctr Natl Railway Intelligent Transportat Syst Eng China Acad Railway Sci Corp Ltd Beijing Peoples R China Chinese Acad Sci Beijing Univ Chem Technol State Key Lab Management & Control Complex Syst I Coll Informat Sci & Technol Beijing Peoples R China China Acad Railway Sci Corp Ltd Transportat & Econ Res Inst Beijing Peoples R China China Acad Railway Sci Corp Ltd Ctr Natl Railway Intelligent Transportat Syst Eng Beijing Peoples R China

ISBN: (数字)9781665498876

ISBN: (纸本)9781665498876

In the era of big data, more and more applications of smart devices are computing-intensive, thus raising the strong demand for task offloading to cloud data centers. However, it gives rise to network delay and privacy data leak issues. Edge computing can effectively solve latency, bandwidth occupation and data privacy problems, but the deployment of applications are also limited by hardware architectures and resources, i.e., computing and storage resources. Therefore, the combination of virtualization technology and edge computing become important in order to realize the rapid deployment of intelligent application in an edge server or an edge node by virtualization technology. The traditional virtual machine (VM) is no longer suitable for resource-constrained devices. Container technique including Docker can effectively solve these problems, but it also depends on an operating system. Unikernel is the state-of-art virtualization technology. In this paper, we combine Unikernel with edge computing to explore its application in an edge computing system. An application architecture of edge computing based on Unikernel is proposed. It is suitable for application in edge computing.

关键词： unikernel docker virtualization technology edge computing

来源：评论

学校读者我要写书评

暂无评论

Consensus control of Leader-Following Multi-Agent systems in Directed Topology With Heterogeneous Disturbances

引用

IEEE/CAA Journal of Automatica Sinica 2021年第2期8卷 423-431页

作者： Qinglai Wei Xin Wang Xiangnan Zhong Naiqi Wu the State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190 the School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049and also with Qingdao Academy of Intelligent IndustriesQingdao 266109China the Department of Computer and Electrical Engineering and Computer Science Florida Atlantic UniversityBoca Raton FL33431 USA the Institute of Systems Engineering and Collaborative Laboratory for Intelligent Science and SystemsMacao University of Science and TechnologyMacao 999078China

This paper investigates the consensus problem for linear multi-agent systems with the heterogeneous disturbances generated by the Brown *** main contribution is that a control scheme is designed to achieve the dynamic consensus for the multi-agent systems in directed topology interfered by stochastic *** traditional ways,the coupling weights depending on the communication structure are static.A new distributed controller is designed based on Riccati inequalities,while updating the coupling weights associated with the gain matrix by state errors between adjacent *** introducing time-varying coupling weights into this novel control law,the state errors between leader and followers asymptotically converge to the minimum value utilizing the local *** the Lyapunov directed method and It?formula,the stability of the closed-loop system with the proposed control law is *** simulation results conducted by the new and traditional schemes are presented to demonstrate the effectiveness and advantage of the developed control method.

关键词： Consensus control directed topology external disturbance multi-agent(MA)systems

来源：评论

学校读者我要写书评

暂无评论

Bridging the Micro and Macro: Calibration of Agent-Based Model Using Mean-Field Dynamics

引用

IEEE TRANSACTIONS ON CYBERNETICS 2022年第11期52卷 11397-11406页

作者： Ye, Peijun Chen, Yuanyuan Zhu, Fenghua Lv, Yisheng Lu, Wanze Wang, Fei-Yue Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Beijing Univ Technol Sch Artificial Intelligence & Automat Beijing 100124 Peoples R China Qingdao Acad Intelligent Ind Parallel Intelligence Res Ctr Qingdao 266109 Peoples R China Macau Univ Sci & Technol Inst Syst Engn Macau Peoples R China

Calibration of agent-based models (ABM) is an essential stage when they are applied to reproduce the actual behaviors of distributed systems. Unlike traditional methods that suffer from the repeated trial and error and slow convergence of iteration, this article proposes a new ABM calibration approach by establishing a link between agent microbehavioral parameters and systemic macro-observations. With the assumption that the agent behavior can be formulated as a high-order Markovian process, the new approach starts with a search for an optimal transfer probability through a macrostate transfer equation. Then, each agent's microparameter values are computed using mean-field approximation, where his complex dependencies with others are approximated by an expected aggregate state. To compress the agent state space, principal component analysis is also introduced to avoid high dimensions of the macrostate transfer equation. The proposed method is validated in two scenarios: 1) population evolution and 2) urban travel demand analysis. Experimental results demonstrate that compared with the machine-learning surrogate and evolutionary optimization, our method can achieve higher accuracies with much lower computational complexities.

关键词： Calibration Computational modeling Mathematical model Machine learning Aggregates Optimization Bayes methods Agent-based model (ABM) calibration Markovian process

来源：评论

学校读者我要写书评

暂无评论

ESTNet: Embedded Spatial-Temporal Network for Modeling Traffic Flow Dynamics

引用

IEEE TRANSACTIONS ON intelligent TRANSPORTATION systems 2022年第10期23卷 19201-19212页

作者： Luo, Guiyang Zhang, Hui Yuan, Quan Li, Jinglin Wang, Fei-Yue Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100088 Peoples R China Beijing Jiaotong Univ Sch Comp & Informat Technol Beijing 100044 Peoples R China Chinese Acad Sci State Key Lab Management & Control Complex Syst Inst Automat Beijing 100190 Peoples R China Beijing Univ Posts & Telecommun Sci & Technol Commun Networks Lab Beijing 100088 Peoples R China State Key Lab Networking & Switching Technol Shijiahznang 050081 Hebei Peoples R China Qingdao Acad Intelligent Ind Innovat Ctr Parallel Vis Qingdao 266000 Peoples R China Macau Univ Sci & Technol Inst Syst Engn Taipa Macao Peoples R China

Accurate spatial-temporal prediction is a fundamental building block of many real-world applications such as traffic scheduling and management, environment policy making, and public safety. This problem is still challenging due to nonlinear, complicated, and dynamic spatial-temporal dependencies. To address these challenges, we propose a novel embedded spatial-temporal network (ESTNet), which extracts efficient features to model the dynamic correlations and then exploits three-dimension convolution to synchronously model the spatial-temporal dependencies. Specifically, we propose multi-range graph convolution networks for extracting multi-scale static features from the fine-grained road network. Meanwhile, dynamic features are extracted from real-time traffic using a gated recurrent unit network. These features can be applied to identify the dynamic and flexible correlations among sensors and make it possible to exploit a three-dimension convolution unit (3DCon) to simultaneously model the spatial-temporal dependencies. Furthermore, we propose a residual network by stacking multiple 3DCon to capture the nonlinear and complicated dependencies. The effectiveness and superiority of ESTNet are verified on two real-world datasets, and experiments show ESTNet outperforms the state-of-the-art with a significant margin. The code and models will be publicly available.

关键词： Roads Correlation Feature extraction Sensors Deep learning Convolution Sensor phenomena and characterization Traffic forecasting graph convolutional network spatial-temporal networks

来源：评论

学校读者我要写书评

暂无评论

An IVC-Based Nuclear Emergency Parallel Evacuation System

引用

IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL systems 2021年第4期8卷 844-855页

作者： Tan, Ke Yang, Linyao Liu, Xin Xu, Yancai Lin, Jiazhen Wang, Xiao Wang, Fei-Yue State Key Lab Nucl Power Safety Monitoring Techno Shenzhen 518108 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Qingdao Acad Intelligent Ind Qingdao 266000 Peoples R China

Nuclear emergency evacuation is challenging and dangerous, with time constraints, resource limitations, and radiation exposure risks. The development of the Internet of Things (IoT) and artificial intelligence enables us to build an intelligent evacuation system to help mitigate this problem a great deal. In this article, we design the nuclear emergency parallel evacuation system based on the artificial systems (A), computational experiments (C), and parallel execution (P) approach and intelligent vehicle collaborative systems (IVCs). In this system, the evacuation risks of different regions under various possible scenarios are simulated and evaluated in the artificial systems. With data adversarially generated from the artificial systems and collected from sensors all over the area, an optimization model is proposed to find the optimal evacuation plans for emergent evacuation scenarios in the computational experiments. Eventually, the most suitable running strategy of autonomous buses will be selected and carried out based on the parallel execution in accordance with the real scene. A case study is conducted, and results indicate that the system can serve as an efficient tool for future nuclear emergency evacuation planning.

关键词： Computational modeling Planning Optimization Roads Mathematical model Collaboration Power generation ACP intelligent vehicle collaborative system nuclear evacuation optimization parallel intelligence

来源：评论

学校读者我要写书评

暂无评论

Machine-learning-based monitoring and optimization of processing parameters in 3D printing

引用

INTERNATIONAL JOURNAL OF COMPUTER INTEGRATED MANUFACTURING 2023年第9期36卷 1362-1378页

作者： Tamir, Tariku Sinshaw Xiong, Gang Fang, Qihang Yang, Yong Shen, Zhen Zhou, MengChu Jiang, Jingchao Chinese Acad Sci State Key Lab Management & Control Complex Syst Beijing Engn Res Ctr Intelligent Syst & Technol Inst Automat Beijing Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing Peoples R China Chinese Acad Sci Guangdong Engn Res Ctr 3D Printing & Intelligent Cloud Comp Ctr Dongguan Peoples R China Chinese Acad Sci Shanghai Inst Ceram State Key Lab High Performance Ceram & Superfine Shanghai Peoples R China New Jersey Inst Technol Helen & John C Hartmann Dept Elect & Comp Engn Newark NJ 07102 USA Macau Univ Sci & Technol Macao Inst Syst Engn Macau 999078 Peoples R China Macau Univ Sci & Technol Collaborat Lab Intelligent Sci & Syst Macau 999078 Peoples R China Chinese Univ Hong Kong Dept Mech & Automat Engn Shatin Hong Kong Peoples R China

Additive manufacturing (AM), commonly known as 3D printing, is a rapidly growing technology. Guaranteeing the quality and mechanical strength of printed parts is an active research area. Most of the existing methods adopt open-loop-like Machine Learning (ML) algorithms that can be used only for predicting properties of printed parts without any quality assuring mechanism. Some closed-loop approaches, on the other hand, consider a single adjustable processing parameter to monitor the properties of a printed part. This work proposes both open-loop and closed-loop ML models and integrates them to monitor the effects of processing parameters on the quality of printed parts. By using experimental 3D printing data, an open-loop classification model formulates the relationship between processing parameters and printed part properties. Then, a closed-loop control algorithm that combines open-loop ML models and a fuzzy inference system is constructed to generate optimized processing parameters for better printed part properties. The proposed system realizes the application of a closed-loop control system to AM.

关键词： Additive manufacturing closed-loop 3D printing digital manufacturing machine learning processing parameters

来源：评论

学校读者我要写书评

暂无评论

Homophily Learning-Based Federated Intelligence: A Case Study on Industrial IoT Equipment Failure Prediction

引用

IEEE INTERNET OF THINGS JOURNAL 2023年第8期10卷 7356-7365页

作者： Zeng, Xingjie Yu, Zepei Zhang, Weishan Wang, Xiao Lu, Qinghua Wang, Tao Gu, Mu Tian, Yonglin Wang, Fei-Yue China Univ Petr East China Coll Comp Sci & Technol Qingdao 266580 Peoples R China Anhui Univ Sch Artificial Intelligence Hefei 266114 Peoples R China Qingdao Acad Intelligent Ind Qingdao 230031 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100080 Peoples R China CSIRO Data61 Sydney NSW 2070 Australia Beijing Aerosp Smart Mfg Technol Dev Co Ltd Beijing 100854 Peoples R China

Federated learning is an emerging distributed machine learning paradigm that can break through data silos and make use of data from different clients in a secure way. However, for deep neural networks in federated learning, the models on clients may learn the same pattern with different weight distributions despite the same data distribution of local data sets, which limits the performance of neural networks after weight fusions. Therefore, in this article, we propose a homophily learning-based federated intelligence (HLFI) approach, where hierarchical federated learning strategy and dynamic elimination learning strategy are designed to alleviate the problem. The experiments on equipment failure prediction show that the proposed approach can improve the failure prediction F1-score up to 9.32%. Our approach also has good generalization capabilities and can be applied in other federated learning methods to improve the model performance.

关键词： Failure prediction federated learning machine learning model generalization neural networks

来源：评论

学校读者我要写书评

暂无评论

Parallel control for Optimal Tracking via Adaptive Dynamic Programming

引用

IEEE/CAA Journal of Automatica Sinica 2020年第6期7卷 1662-1674页

作者： Jingwei Lu Qinglai Wei Fei-Yue Wang School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049 The State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China IEEE State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190 Institute of Systems Engineering Macao University of Science and TechnologyMacao 999078 Qingdao Academy of Intelligent Industries Qingdao 266109China

This paper studies the problem of optimal parallel tracking control for continuous-time general nonlinear *** existing optimal state feedback control,the control input of the optimal parallel control is introduced into the feedback ***,due to the introduction of control input into the feedback system,the optimal state feedback control methods can not be applied *** address this problem,an augmented system and an augmented performance index function are proposed ***,the general nonlinear system is transformed into an affine nonlinear *** difference between the optimal parallel control and the optimal state feedback control is analyzed *** is proven that the optimal parallel control with the augmented performance index function can be seen as the suboptimal state feedback control with the traditional performance index ***,an adaptive dynamic programming(ADP)technique is utilized to implement the optimal parallel tracking control using a critic neural network(NN)to approximate the value function *** stability analysis of the closed-loop system is performed using the Lyapunov theory,and the tracking error and NN weights errors are uniformly ultimately bounded(UUB).Also,the optimal parallel controller guarantees the continuity of the control input under the circumstance that there are finite jump discontinuities in the reference ***,the effectiveness of the developed optimal parallel control method is verified in two cases.

关键词： Adaptive dynamic programming(ADP) nonlinear optimal control parallel controller parallel control theory parallel system tracking control neural network(NN)

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：