检索结果-内蒙古大学图书馆

A Convergence Analysis of a Structure-Preserving Gradient Flow Method for the All-Electron Kohn-Sham Model

Numerical Mathematics(Theory,Methods and Applications) 2023年第3期16卷 597-621页

作者： Yedan Shen Ting Wang Jie Zhou Guanghui Hu School of Mathematics and Information Science Guangzhou UniversityGuangzhouChina Faculty of Science and Technology University of MacaoMacao SARChina Hunan Key Laboratory for Computation and Simulation in Science and Engineering Xiangtan UniversityXiangtanChina School of Mathematical Computational Sciences Xiangtan UniversityXiangtanChina Zhuhai UM Science&Technology Research Institute ZhuhaiChina Guangdong-Hong Kong-Macao Joint Laboratory for Data-Driven Fluid Mechanics and Engineering Applications University of MacaoMacao SARChina

In[Dai et al.,***.18(4)(2020)],a structure-preserving gradient flow method was proposed for the ground state calculation in Kohn-Sham density functional theory,based on which a linearized method was developed in[Hu et al.,EAJAM.13(2)(2023)]for further improving the numerical *** this paper,a complete convergence analysis is delivered for such a linearized method for the all-electron Kohn-Sham ***,the convergence,the asymptotic stability,as well as the structure-preserving property of the linearized numerical scheme in the method is discussed following previous works,while spatially,the convergence of the h-adaptive mesh method is demonstrated following[Chen et al.,***.12(2014)],with a key study on the boundedness of the Kohn-Sham potential for the all-electron Kohn-Sham *** examples confirm the theoretical results very well.

关键词： Kohn-Sham density functional theory gradient flow model structure-preserving linear scheme convergence analysis

来源：评论

学校读者我要写书评

暂无评论

A method for automatic detection and characterization of plasma bubbles using GPS and BDS data

引用

Chinese Journal of Aeronautics 2021年第5期34卷 195-204页

作者： Qiang LI Yanbo ZHU Zhipeng WANG Kun FANG National Key Laboratory of CNS/ATM School of Electronics and Information EngineeringBeihang UniversityBeijing 100191China Aviation Data Communication Corporation Beijing100191China

Detecting and characterizing Total Electron Content(TEC)depletion is important for studying the ionospheric threat due to the Equatorial Plasma Bubble(EPB)when applying the Ground-Based Augmentation System(GBAS)at low *** paper develops a robust method to automatically identify TEC depletion and derive its *** rolling barrel algorithm is used to automatically identify the TEC depletion candidate and its ***,the depletion candidates are screened by several improved techniques to distinguish actual depletions from other phenomena such as Traveling Ionospheric Disturbance(TID)or abnormal ***,based on the depletion signals from three triangular receivers,the method derives EPB parameters such as velocity,width and *** time lag and front velocity are calculated based on crosscorrelation using TEC depletions and the geometrical distribution of three triangular *** width and gradient of slope are then determined by using TEC depletion from a single *** comparison,both the station-pair method and proposed method depend on the assumption that the EPB morphology is frozen during the short time when the plasma bubble moves between the ***,our method relaxes the restriction that the baseline length should be shorter than the width of slope required by the *** relaxation is favorable for studying small-scale slope of depletions using stations of a longer *** addition,the accuracy of the width and gradient is free of impact from hardware biases and small-scale disturbance,as it is based only on the relative TEC *** method is demonstrated by processing Global Positioning System(GPS)and Bei Dou Navigation Satellite System(BDS)data on 15 August,2018,in a solar minimum cycle.

关键词： Depletion drift Ground-Based Augmentation System(GBAS) Ionosphere gradient Plasma bubble TEC depletion

来源：评论

学校读者我要写书评

暂无评论

Each Fake News is Fake in its Own Way: An Attribution Multi-Granularity Benchmark for Multimodal Fake News Detection

arXiv

引用

arXiv 2024年

作者： Guo, Hao Ma, Zihan Zeng, Zhi Luo, Minnan Zeng, Weixin Tang, Jiuyang Zhao, Xiang Laboratory for Big Data and Decision Nation University of Defence Technology China School of Computer Science and Technology Xi’an Jiaotong University China Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi’an Jiaotong University China Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University China

Social platforms, while facilitating access to information, have also become saturated with a plethora of fake news, resulting in negative consequences. Automatic multimodal fake news detection is a worthwhile pursuit. Existing multimodal fake news datasets only provide binary labels of real or fake. However, real news is alike, while each fake news is fake in its own way. These datasets fail to reflect the mixed nature of various types of multimodal fake news. To bridge the gap, we construct an attributing multi-granularity multimodal fake news detection dataset AMG, revealing the inherent fake pattern. Furthermore, we propose a multi-granularity clue alignment model MGCA to achieve multimodal fake news detection and attribution. Experimental results demonstrate that AMG is a challenging dataset, and its attribution setting opens up new avenues for future research. © 2024, CC BY-NC-ND.

关键词： Fake detection

来源：评论

学校读者我要写书评

暂无评论

Optimization Configuration of Energy Storage System Considering the Cost of Retired Power Battery Life 18th

Optimization Configuration of Energy Storage System Consider...

引用

18th Annual Conference of China Electrotechnical Society, ACCES 2023

作者： Jiang, Yuan Ma, Suliang Zhang, Qian Chen, Wenzhen Li, Qing Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing100083 China Energy Storage Technology Engineering Research Center North China University of Technology Beijing100144 China International Student Center University of Science and Technology Beijing Beijing100083 China

ISBN: (纸本)9789819710713

For discovering a solution to the configuration issue of retired power battery applied to the energy storage system, a double hierarchy decision model with technical and economic layer is introduced in this paper. Due to the high uncertainty of wind speed, the output of the thermal power plant will vary with the fluctuation of wind power, aggravating the fatigue and wear of the unit equipment, and affecting the steadiness of the system. The time-power sequence of the energy storage system is acquired by particle swarm optimization, and the power and capacity are configured according to the possibility density role curve of the energy storage output curve. The simulation of the IEEE-30-node model shows that the optimal energy storage configuration strategy put forward herein can control the power fluctuation and strengthen the stability of the wind-fire complementary system, and has good practicability. © Beijing Paike Culture Commu. Co., Ltd. 2024.

关键词： Energy storage

来源：评论

学校读者我要写书评

暂无评论

High Order Conditional Random Field Based Cervical Cancer Histopathological Image Classification

High Order Conditional Random Field Based Cervical Cancer Hi...

引用

International Conference on Image, Vision and Intelligent Systems, ICIVIS 2023

作者： Zhou, Shangqi Li, Xintong Fu, Yanyu Ouyang, Xinyu Yang, Jinzhu Grzegorzek, Marcin Li, Chen Microscopic Image and Medical Image Analysis Group College of Medicine and Biological Information Engineering Northeastern University Shenyang China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang China Institute of Medical Informatics University of Luebeck Luebeck Germany Department of Knowledge Engineering University of Economics in Katowice Katowice Poland

ISBN: (纸本)9789819708543

Cervical cancer ranks as the fourth most frequently diagnosed cancer. This disease has an extended precancerous stage and can be completely cured and prevented through early detection. Currently, the analysis of histopathological images of cervical cancer relies on manual assessment by pathologists, a subjective and time-consuming process. Moreover, there is limited research on differentiating the severity of cervical cancer in histopathological images. To address these challenges, this study proposes a classification algorithm based on high-order conditional random field for cervical cancer histopathologic images. The algorithm effectively categorizes images into high differentiation, medium differentiation, and low differentiation stages. Three deep learning models, namely VGG-16, Inception-V3, and ResNet-50, are utilized for pre-classification at the image block level. For image-level classification, the Visual Transformer model is employed. Finally, the block-level and image-level classification components are integrated using the conditional random field model, resulting in the high-order conditional random field model. Following training and testing using the dataset, the model achieves an overall accuracy of 75.4%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Development and validation of a nomogram prediction model for overall survival in patients with rectal cancer

引用

World Journal of Gastrointestinal Oncology 2025年第2期17卷 93-104页

作者： Ling Liang Xiao-Sheng Li Ze-Jun Huang Zu-Hai Hu Qian-Jie Xu Yu-Liang Yuan Wei Zhang Hai-Ke Lei Chongqing Key Laboratory of Translational Research for Cancer Metastasis and Individualized Treatment Chongqing University Cancer HospitalChongqing 400030China Chongqing Cancer Multiomics Big Data Application Engineering Research Center Chongqing University Cancer HospitalChongqing 400030China Department of Health Statistics School of Public HealthChongqing Medical UniversityChongqing 400016China

BACKGROUND Rectal cancer is prevalent and associated with substantial morbidity and *** To develop a nomogram prediction model for overall survival(OS)in patients with rectal cancer by leveraging a comprehensive analysis of demographic,clinicopathological,haematological,and follow-up data to identify independent prognostic *** We conducted a prospective cohort study in China involving rectal cancer patients and applied Cox regression and least absolute shrinkage and selection operator regression to assess the significance of various variables as independent prognostic factors for *** identified factors were integrated into a nomogram model,which was evaluated for predictive accuracy via the C-index,area under the curve(AUC),calibration curve,and decision curve analysis(DCA).RESULTS Multivariate analysis revealed independent predictors of OS,including the Karnofsky performance status,age,sex,TNM stage,chemotherapy,surgery,targeted therapy,β2-microglobulin,lactate dehydrogenase,and the neutrophil-to-lymphocyte *** nomogram demonstrated a C-index of 0.80 for the training and validation cohorts,with AUC values indicating high predictive accuracy for 1-year,3-year,and 5-year *** calibration curves confirmed the model's excellent agreement with the observed survival rates,and DCA revealed the superior clinical utility of the nomogram over the TNM staging *** In this study,a novel prognostic model that accurately predicts the OS of rectal cancer patients was *** model exhibited excellent discriminatory and calibration capabilities,thus offering a reliable tool for health care professionals to estimate patient survival.

关键词： Rectal cancer Overall survival Nomogram Prognosis

来源：评论

学校读者我要写书评

暂无评论

Multiple Machine Learning Fusion Based Analysis of Fat Composition in CT Images

Multiple Machine Learning Fusion Based Analysis of Fat Compo...

引用

International Conference on Image, Vision and Intelligent Systems, ICIVIS 2023

作者： Fu, Yanyu Quanyu, E. Zhou, Shangqi Ouyang, Xinyu Yang, Jinzhu Grzegorzek, Marcin Li, Chen Microscopic Image and Medical Image Analysis Group College of Medicine and Biological Information Engineering Northeastern University Shenyang China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang China Institute of Medical Informatics University of Luebeck Luebeck Germany Department of Knowledge Engineering University of Economics in Katowice Katowice Poland

ISBN: (纸本)9789819708543

Intra-abdominal fat is a crucial factor in determining metabolic syndrome and insulin resistance. Therefore, high levels of intra-abdominal fat are always accompanied by a series of diseases such as diabetes, ischemia, hypertension, and dyslipidemia. Although methods such as the ultrasonic method and electrical impedance method have been widely used to calculate body fat tissue in recent years, these methods only provide qualitative analysis of the overall degree of obesity. However, for quantitative analysis of abdominal fat and adipose tissue distribution in the human body, the computed tomography (CT) fat segmentation method is necessary. This paper focuses on machine learning, image segmentation, and multi-feature fusion of mean clustering as its main technical directions. In terms of application, it aims to perform a quantitative analysis of the distribution and proportion of intra-abdominal fat in the abdominal cavity of the human body. The study concluded that the quantitative analysis of fat after the fusion method is more accurate, with a subcutaneous fat accuracy rate of 84.26% and a visceral fat accuracy rate of 70.20%. It can effectively, conveniently, and objectively analyze the degree of obesity in the human body. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

data-Driven Active Power Dispatch for Wind Farms 13

Data-Driven Active Power Dispatch for Wind Farms

引用

13th IEEE data Driven Control and Learning Systems Conference, DDCLS 2024

作者： Jiao, Xuguo Zhang, Daoyuan Wang, Xin Ma, Zhaoxing Zhang, Zhenyong Liu, Wenfeng School of Information and Control Engineering Qingdao University of Technology Qingdao266520 China College of Control Science and Engineering Zhejiang University State Key Laboratory of Industrial Control Technology Hangzhou310027 China Ministry of Education Shandong Computer Science Center Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Jinan250014 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan250014 China College of Computer Science and Technology Guizhou University State Key Laboratory of Public Big Data Guiyang550025 China School of Civil Engineering Qingdao University of Technology Qingdao266520 China

ISBN: (纸本)9798350361674

Active power dispatch of wind farms plays an important role in power grid scheduling. In this paper, a data-driven active power dispatch strategy for wind farms is proposed, which uses the key point of minimizing the standard deviation of wind turbines' output power series to reduce their fluctuations. First, to build the optimization problem, the historical active power output data of each wind turbine is collected from the Supervisory Control And data Acquisition (SCADA) system. Then, the objective function is developed based on the idea of minimizing the standard deviation of the output power time series. Meanwhile, considering the constraints of wind turbines' output power and active power balance of the grid, the feasible domain of the cost function is constructed. Further, to solve the proposed nonlinear optimization problem with equality and inequality constraints, the trust region interior point method (TRIPM) is employed to explore optimal solution within the feasible domain. Finally, actual data collected from wind farms is used to test effectiveness of the designed approach and experimental results show that our method can achieve better output power smoothing performance than conventional Proportional Dispatch (PD) method. © 2024 IEEE.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Mutual information oriented deep skill chaining for multi‐agent reinforcement learning

引用

CAAI Transactions on Intelligence Technology 2024年第4期9卷 1014-1030页

作者： Zaipeng Xie Cheng Ji Chentai Qiao WenZhan Song Zewen Li Yufeng Zhang Yujing Zhang Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai UniversityNanjingChina College of Computer and Information Hohai UniversityNanjingChina Center for Cyber‐Physical Systems University of GeorgiaAthensGeorgiaUSA Information Networking Institute Carnegie Mellon UniversityPittsburghPennsylvaniaUSA Department of Electrical and Systems Engineering University of PennsylvaniaPhiladelphiaPennsylvaniaUSA

Multi‐agent reinforcement learning relies on reward signals to guide the policy networks of individual ***,in high‐dimensional continuous spaces,the non‐stationary environment can provide outdated experiences that hinder convergence,resulting in ineffective training performance for multi‐agent *** tackle this issue,a novel reinforcement learning scheme,Mutual Information Oriented Deep Skill Chaining(MioDSC),is proposed that generates an optimised cooperative policy by incorporating intrinsic rewards based on mutual information to improve exploration *** rewards encourage agents to diversify their learning process by engaging in actions that increase the mutual information between their actions and the environment *** addition,MioDSC can generate cooperative policies using the options framework,allowing agents to learn and reuse complex action sequences and accelerating the convergence speed of multi‐agent *** was evaluated in the multi‐agent particle environment and the StarCraft multi‐agent challenge at varying difficulty *** experimental results demonstrate that MioDSC outperforms state‐of‐the‐art methods and is robust across various multi‐agent system tasks with high stability.

关键词： artificial intelligence techniques decision making intelligent multi‐agent systems

来源：评论

学校读者我要写书评

暂无评论

In-context decision transformer: reinforcement learning via hierarchical chain-of-thought 24

In-context decision transformer: reinforcement learning via ...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Sili Huang Jifeng Hu Hechang Chen Lichao Sun Bo Yang School of Artificial Intelligence and Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China School of Artificial Intelligence Jilin University China Lehigh University Bethlehem Pennsylvania Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China

In-context learning is a promising approach for offline reinforcement learning (RL) to handle online tasks, which can be achieved by providing task prompts. Recent works demonstrated that in-context RL could emerge with self-improvement in a trial-and-error manner when treating RL tasks as an across-episodic sequential prediction problem. Despite the self-improvement not requiring gradient updates, current works still suffer from high computational costs when the across-episodic sequence increases with task horizons. To this end, we propose an In-context Decision Transformer (IDT) to achieve self-improvement in a high-level trial-and-error manner. Specifically, IDT is inspired by the efficient hierarchical structure of human decision-making and thus reconstructs the sequence to consist of high-level decisions instead of low-level actions that interact with environments. As one high-level decision can guide multi-step low-level actions, IDT naturally avoids excessively long sequences and solves online tasks more efficiently. Experimental results show that IDT achieves state-of-the-art in long-horizon tasks over current in-context RL methods. In particular, the online evaluation time of our IDT is 36× times faster than baselines in the D4RL benchmark and 27× times faster in the Grid World benchmark.

关键词：

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：