检索结果-内蒙古大学图书馆

International Conference on Advanced computer Information Technologies (ACIT)

作者： Yaroslav Pyanylo Zoia Prytula Myroslav Prytula Olha Hymko Nazar Prytula Halyna Pyanylo Department of mathematical modeling of transfer processes in distributed systems National Academy of Sciences of Ukraine Pidstryhach Institute for Applied Problems of Mechanics and Mathematics Lviv Ukraine Laboratory of mathematical problems of mechanics of inhomogeneous bodies Pidstryhach Institute for Applied Problems of Mechanics and Mathematics National Academy of Sciences of Ukraine Lviv Ukraine Department of development of systems for optimal planning and forecasting of UGS operating modes Research and Design Institute of Gas Transport of PJSC “Ukrtransgaz” Lviv Ukraine Department of Automation and Computer-Integrated Technologies Lviv Polytechnic National University Lviv Ukraine

Problems of research of underground gas storage (UGS) wells are given. The analysis of the results of well research is carried out and the constant variability of filtration resistance coefficients of bottomhole zones of wells is substantiated. Studies of the influence of bottomhole pressures of wells on the calculated pressure at gas gathering stations (GGS) of underground storage facilities have been carried out. It was found that the calculated filtration resistance coefficients do not allow to calculate the pressures at the gas gathering stations of the underground storage plant with sufficient accuracy. The magnitude of the discrepancy between the measured and calculated pressures on the GGS varies depending on the flow rate and operating time of wells. It is established that the calculation of depression (repression) of pressure in the bottomhole zones of wells in non-stationary conditions of their operation gives underestimated results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GSLB: the graph structure learning benchmark 23

GSLB: the graph structure learning benchmark

引用

Proceedings of the 37th International Conference on Neural Information Processing systems

作者： Zhixun Li Liang Wang Xin Sun Yifan Luo Yanqiao Zhu Dingshuo Chen Yingtao Luo Xiangxin Zhou Qiang Liu Shu Wu Jeffrey Xu Yu Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Center for Research on Intelligent Perception and Computing State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences and School of Artificial Intelligence University of Chinese Academy of Sciences and Department of Automation University of Science and Technology of China Department of Automation University of Science and Technology of China School of Cyberspace Security Beijing University of Posts and Telecommunications Department of Computer Science University of California Los Angeles Center for Research on Intelligent Perception and Computing State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences and School of Artificial Intelligence University of Chinese Academy of Sciences Heinz College of Information Systems and Public Policy Machine Learning Department School of Computer Science Carnegie Mellon University

Graph Structure Learning (GSL) has recently garnered considerable attention due to its ability to optimize both the parameters of Graph Neural Networks (GNNs) and the computation graph structure simultaneously. Despite the proliferation of GSL methods developed in recent years, there is no standard experimental setting or fair comparison for performance evaluation, which creates a great obstacle to understanding the progress in this field. To fill this gap, we systematically analyze the performance of GSL in different scenarios and develop a comprehensive Graph Structure Learning Benchmark (GSLB) curated from 20 diverse graph datasets and 16 distinct GSL algorithms. Specifically, GSLB systematically investigates the characteristics of GSL in terms of three dimensions: effectiveness, robustness, and complexity. We comprehensively evaluate state-of-the-art GSL algorithms in node- and graph-level tasks, and analyze their performance in robust learning and model complexity. Further, to facilitate reproducible research, we have developed an easy-to-use library for training, evaluating, and visualizing different GSL methods. Empirical results of our extensive experiments demonstrate the ability of GSL and reveal its potential benefits on various downstream tasks, offering insights and opportunities for future research. The code of GSLB is available at: https://***/GSL-Benchmark/GSLB.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection Based on Principle of Justifiable Granularity and Probability Density Estimation

Anomaly Detection Based on Principle of Justifiable Granular...

引用

Chinese automation Congress (CAC)

作者： Sheng Du Xian Ma Xiang Li Min Wu Weihua Cao Witold Pedrycz School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China Department of Electrical and Computer Engineering University of Alberta Edmonton AB Canada Systems Research Institute Polish Academy of Sciences Warsaw Poland Department of Computer Engineering Faculty of Engineering and Natural Sciences Istinye University Sariyer/Istanbul Turkiye

Anomaly detection is essential to ensure the safety of industrial processes. This paper presents an anomaly detection approach based on the probability density estimation and principle of justifiable granularity. First, time series data are transformed into a two-dimensional information granule by the principle of justifiable granularity. Then, the test statistic is constructed, and the probability density and cumulative distribution functions of the test statistic are calculated. Next, the confidence level determines the test threshold. Finally, the time series data of a key parameter in the sintering process is used as a case study. The experimental result demonstrates that the proposed approach can detect abnormal time series data effectively, providing an accurate and effective solution for detecting time series anomalies in industrial processes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Maximum Power Point Tracking for PV systems: A Comparison of Perturb & Observe and Fuzzy Logic Control

Maximum Power Point Tracking for PV Systems: A Comparison of...

引用

International Conference on ENERGY and ENVIRONMENT (CIEM)

作者： Fadila Tahiri Abdelkader Harrouz Virgil Dumbrava Patrice Wira M.Amine Hartani Technology and Sciences Department LDDI Laboratory Adrar Algeria Department of Hydrocarbon and Renewable Energy LDDI Laboratory Adrar Algeria Department of Electric Power Systems Polytechnic University of Bucharest Buchrest Roumanie Institute for Research in Computer Science Mathematics Automation and Signal Mulhouse France

The purpose of this research paper is to explore different approaches to maximize power point tracking (MPPT) in photovoltaic (PV) systems. In this work, we evaluate and compare incremental conductance (InC) and fuzzy logic control techniques. To extract the highest amount of power, a DC/DC boost converter is employed between the PV system and the load. Traditional MPPT techniques like InC have demonstrated limitations in effectively identifying and precisely tracking the highest peak, leading to significant power losses, Therefore, a proposed approach called fuzzy logic control is recommended, which provides several advantages including robustness against parameter variations, minimal distortion in current output, and superior reference tracking. Simulation results conducted in MATLAB confirm that the suggested control method effectively reduces steady-state fluctuations and achieves improved tracking of the maximum power point with reduced power losses compared to InC control.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Constrained Probabilistic Pareto Dominance for Expensive Constrained Multiobjective Optimization Problems

引用

IEEE Transactions on Evolutionary Computation 2024年 1-1页

作者： Zhang, Zhiyao Wang, Yong Sun, Guangyong Pang, Tong Tang, Ke School of Automation Central South University Changsha China State Key Laboratory of Advanced Design and Manufacturing Technology for Vehicle Hunan University Changsha China Guangdong Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering and the Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China

This paper proposes a new parameterless constraint-handling technique, named constrained probabilistic Pareto dominance (CPPD), for expensive constrained multiobjective optimization problems (CMOPs). In CPPD, when comparing two solutions, in terms of each original objective, we design a new objective for each solution, which is the negative product of two probabilities calculated based on the predicted fitness mean values and the uncertainty information provided by Kriging models: 1) the probability that this solution satisfies all constraints, denoted as PoF, and 2) the probability that this solution is better than the other on the original objective, denoted as PoB. It is evident that for each solution, PoF and PoB indicate its feasibility and its optimality on the corresponding original objective, respectively. Then, Pareto dominance based on new objectives is executed. As a result, both competitive feasible solutions and promising infeasible solutions with good diversity can be preserved by CPPD. These two kinds of solutions can help the population to exploit the located feasible parts and to explore new feasible parts, respectively. Further, based on CPPD, we develop a Pareto-based Kriging-assisted constrained multiobjective evolutionary algorithm (called PEA) to deal with expensive CMOPs with two or three objectives. Finally, PEA is generalized to solve expensive constrained many-objective optimization problems, named PEA+. The effectiveness of CPPD, PEA, and PEA+ is verified by comprehensive experiments. IEEE

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Generalized Simultaneous Perturbation-based Gradient Search with Reduced Estimator Bias

arXiv

引用

arXiv 2022年

作者： Pachal, Soumen Bhatnagar, Shalabh Prashanth, L.A. Department of Computer Science and Engineering Indian Institute of Technology Madras TCS Research Chennai India Department of Computer Science and Automation the Robert Bosch Centre for Cyber Physical Systems Indian Institute of Science Bangalore India Department of Computer Science and Engineering Indian Institute of Technology Madras Chennai India

We present in this paper a family of generalized simultaneous perturbation-based gradient search (GSPGS) estimators that use noisy function measurements. The number of function measurements required by each estimator is guided by the desired level of accuracy. We first present in detail unbalanced generalized simultaneous perturbation stochastic approximation (GSPSA) estimators and later present the balanced versions (B-GSPSA) of these. We extend this idea further and present the generalized smoothed functional (GSF) and generalized random directions stochastic approximation (GRDSA) estimators, respectively, as well as their balanced variants. We show that estimators within any specified class requiring more number of function measurements result in lower estimator bias. We present a detailed analysis of both the asymptotic and non-asymptotic convergence of the resulting stochastic approximation schemes. We further present a series of experimental results with the various GSPGS estimators on the Rastrigin and quadratic function objectives. Our experiments are seen to validate our theoretical findings. Copyright © 2022, 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

Contrastive Conditional Adversarial Autoencoder with Class-specific Forces for Imbalanced Open-set Fault Detection

引用

IEEE Transactions on automation Science and Engineering 2025年 22卷 15757-15767页

作者： Zuo, Zhonglin Meng, Tao Li, Zheng Zhang, Hao Liu, Tong Chen, Zhansheng Pang, Zhibo Zhejiang University College of Control Science and Engineering Hangzhou310027 China Zhejiang University School of Aeronautics and Astronautics Hangzhou310027 China Hainan Institute of Zhejiang University Sanya572025 China Chongqing University School of Automation Chongqing400044 China University of Sheffield Department of Computer Science SheffieldS1 4DP United Kingdom Shanghai Aerospace Space Technology Co. Ltd Shanghai201109 China ABB Corporate Research Sweden Department of Automation Technology Vasteras Sweden KTH Royal Institute of Technology Department of Intelligent Systems Stockholm Sweden

In real-world industrial scenarios, fault detection faces the widely recognized challenge of data imbalance, which not only refers to the scarcity of fault data but also includes the imbalance in healthy data. This article is concerned with imbalanced open-set fault detection (IOSFD), a practical yet challenging scenario in industrial applications where multiple healthy operating conditions and multiple fault types are imbalanced. In this article, we propose a new contrastive conditional adversarial autoencoder for IOSFD. It constructs an end-to-end unified model based on multi-class known healthy and faulty data to address the reliance of traditional methods on fault samples, while optimizing with class-specific weighted forces to ensure equal attention to imbalanced known classes. Input and feature reconstruction conditioned on operating modes are utilized to learn a compact decision plane and achieve both unknown fault detection and known data classification. Significantly, we formulate the optimization objective of conditional reconstruction based on contrastive learning and introduce adversarial training to further enhance the model’s performance. The effectiveness of the proposed method is validated through real-world pipeline leak detection and Tennessee-Eastman multi-fault detection. © 2004-2012 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

ViKL: A Mammography Interpretation Framework via Multimodal Aggregation of Visual-knowledge-linguistic Features

arXiv

引用

arXiv 2024年

作者： Wei, Xin Tao, Yaling Du, Changde Zhao, Gangming Yu, Yizhou Li, Jinpeng The Ningbo Institute of Life and Health Industry UCAS Ningbo315000 China School of Automation Science and Engineering South China University of Technology Guangdong Guangzhou510641 China The Research Center for Brain-Inspired Intelligence State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China The Department of Computer Science University of Hong Kong Pokfulam Hong Kong

Mammography is the primary imaging tool for breast cancer diagnosis. Despite significant strides in applying deep learning to interpret mammography images, efforts that focus predominantly on visual features often struggle with generalization across datasets. We hypothesize that integrating additional modalities in the radiology practice, notably the linguistic features of reports and manifestation features embodying radiological insights, offers a more powerful, interpretable and generalizable representation. In this paper, we announce MVKL, the first multimodal mammography dataset encompassing multi-view images, detailed manifestations and reports. Based on this dataset, we focus on the challanging task of unsupervised pretraining and propose ViKL, a innovative framework that synergizes Visual, Knowledge, and Linguistic features. This framework relies solely on pairing information without the necessity for pathology labels, which are often challanging to acquire. ViKL employs a triple contrastive learning approach to merge linguistic and knowledge-based insights with visual data, enabling both inter-modality and intra-modality feature enhancement. Our research yields significant findings: 1) Integrating reports and manifestations with unsupervised visual pretraining, ViKL substantially enhances the pathological classification and fosters multimodal interactions. 2) Manifestations can introduce a novel hard negative sample selection mechanism. 3) The multimodal features demonstrate transferability across different datasets. 4) The multimodal pretraining approach curbs miscalibrations and crafts a high-quality representation space. The MVKL dataset and ViKL code are publicly available at https://***/wxwxwwxxx/ViKL to support a broad spectrum of future research. Copyright © 2024, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Data-Filtered Prediction with Decomposition and Amplitude-Aware Permutation Entropy for Workload and Resource Utilization in Cloud Data Centers

引用

IEEE Internet of Things Journal 2025年

作者： Yuan, Haitao Hu, Qinglong Wang, Meijia Wang, Shen Bi, Jing Buyya, Rajkumar Shi, Shuyuan Yang, Jinhong Zhang, Jia Zhou, MengChu Beihang University School of Automation Science and Electrical Engineering Beijing100191 China City University of Hong Kong Department of Computer Science Hong Kong999077 Hong Kong Beijing University of Technology School of Software Engineering The Faculty of Information Technology Beijing100124 China Lab School of Computing and Information Systems MelbourneVIC3010 Australia Beihang University School of Integrated Circuit Science and Engineering Beijing China CSSC Systems Engineering Research Institute Beijing China Southern Methodist University Department of Computer Science The Lyle School of Engineering DallasTX75205 United States New Jersey Institute of Technology Department of Electrical and Computer Engineering NewarkNJ07102 United States

In recent years, cloud computing has witnessed widespread applications across numerous organizations. Predicting workload and computing resource data can facilitate proactive service operation management, leading to substantial improvements in quality of service and cost efficiency. However, these data often exhibit non-linearity, high volatility, and interdependencies across different categories, presenting challenges for accurate forecasting. Consequently, there is a critical need to develop a method that thoroughly and comprehensively analyzes all available data to forecast future trends effectively. This work proposes a novel integrated data-enhanced prediction model named SVAPI for achieving high-accuracy workload prediction in cloud computing systems. SVAPI employs the Savitzky-Golay filter, Variational mode decomposition, and the mode selection based on Amplitude-aware Permutation entropy for feature processing, whose features are subsequently utilized by Informer for multivariate joint analysis of the enhanced data, achieving high-precision prediction. Ablation and comparative experiments with advanced prediction models are conducted on the Google cluster trace and other typical datasets. Realistic data-driven results indicate that SVAPI improves the prediction accuracy by 37.7% compared to the original Informer, with each module contributing to the performance enhancement. Furthermore, compared with Autoformer, SVAPI enhances the prediction accuracy of workload, CPU, and memory by 65.6%, 66.9%, and 70.8%, respectively, demonstrating that SVAPI owns strong abilities in noise filtering, feature processing, and multivariate joint analysis for achieving higher prediction accuracy. © 2014 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Biomedical data and AI

引用

Science China Life Sciences 2025年第5期68卷 1536-1540页

作者： Hao Xu Shibo Zhou Zefeng Zhu Vincenzo Vitelli Liangyi Chen Ziwei Dai Ning Yang Luhua Lai Shengyong Yang Sergey Ovchinnikov Zhuoran Qiao Sirui Liu Chen Song Jianfeng Pei Han Wen Jianfeng Feng Yaoyao Zhang Zhengwei Xie Yang-Yu Liu Zhiyuan Li Fulai Jin Hao Li Mohammad Lotfollahi Xuegong Zhang Ge Yang Shihua Zhang Ge Gao Pulin Li Qi Liu Jing-Dong Jackie Han Peking-Tsinghua Center for Life Sciences (CLS) Academy for Advanced Interdisciplinary StudiesPeking University Center for Quantitative Biology (CQB) Academy for Advanced Interdisciplinary StudiesPeking University Peking University-Tsinghua University-National Institute of Biological Sciences Joint Graduate Program Academy for Advanced Interdisciplinary StudiesPeking University Department of Physics University of Chicago School of Life Sciences Southern University of Science and Technology Peking University Chengdu Academy for Advanced Interdisciplinary Biotechnologies College of Chemistry and Molecular Engineering Peking University Department of Biotherapy Cancer Center and State Key Laboratory of BiotherapyWest China HospitalSichuan University Department of Biology Massachusetts Institute of Technology Lambic Therapeutics Inc. Changping Laboratory Al for Science Institute Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence Fudan University Department of Obstetrics and Gynecology West China Second University HospitalSichuan University Peking University International Cancer Institute and Peking University-Yunnan Baiyao International Medical Institute and State Key Laboratory of Natural and Biomimetic Drugs Department of Molecular and Cellular PharmacologySchool of Pharmaceutical SciencesPeking University Health Science CenterPeking University Channing Division of Network Medicine Department of MedicineBrigham and Women's Hospital and Harvard Medical School Center for Artificial Intelligence and Modeling the Carl R.Woese Institute for Genomic BiologyUniversity of Illinois Urbana-Champaign Department of Genetics and Genome Sciences School of Medicine and Department of Computer and Data Sciences and Department of Population and Quantitative Health SciencesCase Western Reserve University Department of Biochemistry and Biophysics University of California Sanger Institute Department of Automation Tsinghua University State Key Laboratory of Multimodal Artificial Intelligence Systems I

The development of artificial intelligence(AI) and the mining of biomedical data complement each other. From the direct use of computer vision results to analyze medical images for disease screening, to now integrating biological knowledge into models and even accelerating the development of new AI based on biological discoveries, the boundaries of both are constantly expanding, and their connections are becoming closer.

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：