检索结果-内蒙古大学图书馆

IEEE International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT)

作者： Jiaman Ding Haibin Li Yuanyuan Wang Lianyin Jia Jinguo You Yang Yang Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming China College of Engineering and Computer Science Australian National University Canberra Australia

ISBN: (数字)9781728126166

ISBN: (纸本)9781728126173

Frequent Itemset Mining (FIM) from large-scale databases has emerged as an important problem in the data mining and knowledge discovery research community. However, FIM suffers from three important limitations with the rapidly expanding of big data in all domains. First, it assumes that all items have the same importance. Second, it ignores the fact that data collected in a real-life environment is often inaccurate. Third, it is also a data-intensive and computation-intensive process which makes the FIM algorithm very time-consuming over large datasets. To address these issues, we propose a Parallel uncertain frequent itemset mining algorithm with spark (Pufim). Pufim firstly expresses item uncertainty by considering both the probability and weight, and calculates the maximum probability weight value of 1-items. Next, a distributed Pufim-tree structure is designed inspiring by FP-Tree for reducing the times of scanning the databases. Each node of Pufim-tree stores an item and its maximum probability weight value. Finally, experiments on publicly available UCI datasets demonstrate that Pufim achieves more prominent results than other related approaches across various metrics. In addition, the empirical study also shows Pufim has a good scalability.

关键词： Itemsets Data mining Probability Database systems

来源：评论

学校读者我要写书评

暂无评论

Reviewing continual learning from the perspective of human-level intelligence

arXiv

引用

arXiv 2021年

作者： Chang, Yifan Li, Wenbo Peng, Jian Tang, Bo Kang, Yu Lei, Yinjie Gui, Yuanmiao Zhu, Qing Liu, Yu Li, Haifeng The State Key Laboratory of Fire Science Department of Automation and Institute of Advanced Technology University of Science and Technology of China Hefei China Institute of Intelligent Machines Chinese Academy of Sciences Hefei230031 China The Department of Electrical and Computer Engineering Mississippi State University United States College of Electronics and Information Engineering Sichuan University Chengdu China Faculty of Geosciences and Environmental Engineering The Southwest Jiaotong University Chengdu China Institute of Remote Sensing and Geographic Information System Peking Universit Beijing China School of Geosciences and Info-Physics Central South University South Lushan Road Changsha410083 China

Humans continual learning (CL) ability is closely related to Stability Versus Plasticity Dilemma that describes how humans achieve ongoing learning capacity and preservation for learned information. The notion of CL has always been present in artificial intelligence (AI) since its births. This paper proposes a comprehensive review of CL. Different from previous reviews that mainly focus on the catastrophic forgetting phenomenon in CL, this paper surveys CL from a more macroscopic perspective based on the Stability Versus Plasticity mechanism. Analogous to biological counterpart, "smart" AI agents are supposed to i) remember previously learned information (information retrospection);ii) infer on new information continuously (information prospection:);iii) transfer useful information (information transfer), to achieve high-level CL. According to the taxonomy, evaluation metrics, algorithms, applications as well as some open issues are then introduced. Our main contributions concern i) rechecking CL from the level of artificial general intelligence;ii) providing a detailed and extensive overview on CL topics;iii) presenting some novel ideas on the potential development of CL. © 2021, CC BY.

关键词： Petroleum reservoir evaluation

来源：评论

学校读者我要写书评

暂无评论

Virtual DC Generator Control Strategy Based on Differential Compensation

Virtual DC Generator Control Strategy Based on Differential ...

引用

IEEE Energy Conversion Congress and Exposition

作者： Na Zhi Youguo Ding Liang Du Faculty of Automation and Information Engineering Xi’an University of technology Xi’an China Department of Electrical and Computer Engineering Temple University Philadelphia PA United States

An improved control strategy for virtual DC motor (VDCM) with storage energy interface in DC microgrids is proposed in this paper. Through adding differential compensations to feedforward channels in traditional VDCM controls, resiliency of DC microgrids can be enhanced with improved converter damping against disturbances from load variations and renewable energy sources. Three compensation methods are presented, and their impacts on DC bus voltage stabilization are analyzed. The proposed framework is validated by simulations, and results verify the enhancement of the inertia of the converter.

关键词： Voltage control Damping Microgrids Steady-state DC machines Stability analysis Energy storage

来源：评论

学校读者我要写书评

暂无评论

Optimization Algorithm for Reduction the Size of Dixon Resultant Matrix:A Case Study on Mechanical Application

引用

computers, Materials & Continua 2019年第2期58卷 567-583页

作者： Shang Zhang Seyedmehdi Karimi Shahaboddin Shamshirband Amir Mosavi College of Computer and Information Technology China Three Gorges UniversityYichangChina Department of Mathematics Jouybar branchIslamic Azad UniversityJouybarIran Department for Management of Science and Technology Development Ton Duc Thang UniversityHo Chi Minh CityVietnam Faculty of Information Technology Ton Duc Thang UniversityHo Chi Minh CityVietnam Department Institute of Structural Mechanics Bauhaus University of WeimarGermany Institute of Automation Kando Kalman Faculty of Electrical EngineeringObuda University1431 BudapestHungary

In the process of eliminating variables in a symbolic polynomial system,the extraneous factors are referred to the unwanted parameters of resulting *** paper aims at reducing the number of these factors via optimizing the size of Dixon *** optimal configuration of Dixon matrix would lead to the enhancement of the process of computing the resultant which uses for solving polynomial *** do so,an optimization algorithm along with a number of new polynomials is introduced to replace the polynomials and implement a complexity ***,the monomial multipliers are optimally positioned to multiply each of the ***,through practical implementation and considering standard and mechanical examples the efficiency of the method is evaluated.

关键词： Dixon resultant matrix symbolic polynomial system elimination theory optimization algorithm computational complexity

来源：评论

学校读者我要写书评

暂无评论

LDCNN-DTI: A Novel Light Deep Convolutional Neural Network for Drug-Target Interaction Predictions

LDCNN-DTI: A Novel Light Deep Convolutional Neural Network f...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Shudong Wang Zhenzhen Du Mao Ding Renteng Zhao Alfonso Rodriguez-Paton Tao Song College of Computer Science and Technology China University of Petroleum Qingdao China School of Electrical Engineering and Automation Tiangong University Tianjin China The Second Hospital of Shandong University Jinan China Trinity earth Technology Co.Ltd Faculty of Computer Science Polytechnical University of Madrid Campus de Montegancedo Boadilla del Monte Madrid Spain

ISBN: (数字)9781728162157

ISBN: (纸本)9781728162164

In computational drug discovery, accurately predicting drug-target interaction (DTI) is vital for drug repositioning and developing new drugs. With DTI data rapidly accumulated in recent years, it is recently hot to use deep learning technology to predict DTIs, but still a challenge to design light learning frameworks by using less protein descriptors. In this work, to address the challenge, a novel light deep convolutional neural network (namely LDCNN) is proposed to predict DTIs, in which a small number of protein descriptors are produced by convolving amino acid sequences of different lengths. As results, it is obtained that LDCNN can reduce the number of neurons in convolution layers and filters by 50%, with lose of AUC 1.3% and AUPR 4% comparing with DeepConv method. Our LDCNN models can give hints in designing light deep learning models for DTI prediction.

关键词： Drugs Neurons Biological neural networks Predictive models Feature extraction Diffusion tensor imaging Convolution

来源：评论

学校读者我要写书评

暂无评论

A fault diagnosis benchmark of technical systems with incomplete data — six solutions

引用

Control engineering Practice 2025年 164卷

作者： Daniel Jung Erik Frisk Mattias Krysander Anna Sztyber-Betley Francesco Corrini Andrea Arici Nicolas Anselmi Mirko Mazzoleni Jiamin Xu Siwen Mo Zixuan Xu Chongpan Yang Zhile Du Hossein Safaeipour Mehdi Forouzanfar Vahid Mirahi Anna Pinnarelli Vicenç Puig Qiao Deng Yufei Liu Homayoun Najjaran Vehicular Systems Department of Electrical Engineering Linköping University Linköping SE-581 83 Sweden Faculty of Mechatronics Warsaw University of Technology Warsaw 02-525 Poland Department of Management Information and Production Engineering University of Bergamo Via G. Marconi 5 Dalmine (BG) 24044 Italy School of Automation Central South University Changsha 410083 China Department of Electrical Engineering Ahv.C. Islamic Azad University Ahvaz Iran Department of Mechanical Energy and Management Engineering (DIMEG) University of Calabria Rende Italy Institute of Robotics and Industrial Informatics (CSIC-UPC) University of Catalonia Barcelona Spain Department of Electrical and Computer Engineering University of Victoria Victoria V8W 2Y2 BC Canada

This paper presents a benchmark problem for fault diagnosis of an internal combustion engine that has been formulated and solved. The objective is to design a diagnosis system using and incomplete model information training data that only contains a limited set of fault realizations. Six different solutions to the benchmark, that were presented at the IFAC Safeprocess symposium 2024, are described and evaluated. The contribution of this paper is the benchmark and the presentation of six different solutions in one paper. The paper is intended to provide a starting point for engineers and researchers who work with fault diagnosis and monitoring of technical systems.

关键词： Fault detection and isolation Model-based diagnosis Data-driven fault diagnosis

来源：评论

学校读者我要写书评

暂无评论

A multi-view approach for predicting microbedisease associations by fusing the linear and nonlinear features

A multi-view approach for predicting microbedisease associat...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Ming Liu Wei Dai Wei Peng Yu Fu Yi Pan Faculty of Information Engineering and Automation Kunming University of Science and Technology Computer Technology Application Key Lab of Yunnan Province Kunming University of Science and Technology Kunming China Medical school Kunming University of Science and Technology Kunming China Georgia State University Atlanta GA USA

ISBN: (数字)9781728162157

ISBN: (纸本)9781728162164

Microbes play a crucial role in human health and disease. Understanding the relationship between microbes and diseases is conducive to the treatment and diagnosis of diseases. Recently, many computational methods have been proposed to predict disease-microbe associations. However, most of the existing methods only consider a single model and explore the disease-microbe associations from a single view. To improve the prediction accuracy, we propose a novel multi-view approach that fuses the linear and nonlinear features to predict new potential associations between diseases and microbes. We first design a non-negative matrix tri-factorization method to extract the linear features of diseases and microbes. We input the linear features from the non-negative matrix tri-factorization model and bi-random walk model into a capsule neural network to obtain the diseases and microbes' nonlinear features. Finally, we leverage a logistic regression model to combine the non-negative matrix tri-factorization model predictions, bi-random walk model predictions and the capsule neural network predictions to obtain the final association scores between microbes and diseases. We apply our method to predict human microbedisease associations. Experimental results show that our fusion model outperforms the non-negative matrix tri-factorization model, bi-random walk model and other existing models.

关键词： Diseases Predictive models Neural networks Feature extraction Computational modeling Logistics Kernel

来源：评论

学校读者我要写书评

暂无评论

Bebop 2 Quadrotor as a Platform for Research and Education in Robotics and Control engineering

Bebop 2 Quadrotor as a Platform for Research and Education i...

引用

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： Wojciech Giernacki Piotr Kozierski Jacek Michalski Marek Retinger Rafal Madonski Pascual Campoy Institute of Robotics and Machine Intelligence Faculty of Control Robotics and Electrical Engineering of Poznan University of Technology Poznań Poland Institute of Computing Science (Faculty of Computing and Telecommunications) and with the Institute of Robotics and Machine Intelligence (Faculty of Control Robotics and Electrical Engineering) Poznan University of Technology Poznań Poland International Energy College Energy Electricity Research Center Jinan University Zhuhai China Computer Vision and Aerial Robotics (CVAR) Centre for Automation and Robotics Technical University of Madrid (UPM) Madrid Spain

ISBN: (数字)9781728142784

ISBN: (纸本)9781728142791

In conducting research and teaching in fields related to unmanned aerial vehicles (UAVs), it is particularly important to select a universal, safe, open research platform and tools for rapid prototyping. Ready-to-use, low-cost micro-class UAVs such as Bebop 2 are successfully used in that regard. This article presents how to use the potential of this flying robot with Robot Operating System (ROS). The most important software solutions for the developed experimental testbed FlyBebop are characterized here. Their capabilities in research and education are exemplified using three distinct cases: 1) research results on the method of optimal, in-flight, iterative self-tuning of UAV position controller parameters (based only on current measurements), 2) the use of the reinforcement learning method in the autonomous landing of a single drone on a moving vehicle, 3) planning the movement of UAVs for autonomous video recording along the planned path in the arrangement: "cameraman drone" and "lighting technician drones".

关键词： Drones Robots Education Cameras Sensors Tools

来源：评论

学校读者我要写书评

暂无评论

Comparison of the Effectiveness of Various Structures of Regulators for Controlling an Object of the Sixth Order

Comparison of the Effectiveness of Various Structures of Reg...

引用

2019 International Multi-Conference on engineering, computer and Information Sciences, SIBIRCON 2019

作者： Zhmud, Vadim Dimitrov, Lubomir Nosek, Jaroslav Roth, Hubert Novosibirsk State Technical University Dept. of Automation Novosibirsk Russia Technical University of Sofia Sofia Bulgaria Technical University of Liberec Faculty of Mechatronics Computer Science and Interdisciplinary Research Liberec Czech Republic University of Siegen Department of Automatic Control Engineering Siegen Germany Germany

ISBN: (纸本)9781728144016

Object control requires the calculation of a regulator. One of the most effective methods for calculating the regulator is the method of numerical optimization of the regulator. This paper discusses the solution of the problem of controlling a linear object of the sixth order, the parameters of which are such that this high order significantly and negatively affects the possibilities of successfully managing this object. Using the traditional approach to the design problem of the controller (regulator) allows us to formally solve the problem;however, the result of this solution is not satisfactory. The use of additional derivation does not give any noticeable improvement. A solution to this problem is proposed by using pseudo-local feedback, moreover, this connection is supposedly most effective if it covers one of two identical links in the object model. This allows for a smoother attenuation of the frequency response of the object in the region where the action of these two links begins to affect. For pseudo-local communication, an additional PID controller is used, the coefficients of which are also determined by the method of numerical optimization. The optimization result allows us to conclude that the presence of an integral element in this controller is optional. The calculation result of such a composite controller meets the most stringent requirements for the quality of control, since in such a system the speed is increased at least twice, the oscillations, which were about 10% in amplitude, are completely eliminated, the robustness of the system is ensured, which is verified by changing all the controller coefficients by 5% up and down, and also by changing the time constant of the element of the pseudolocal loop by 10% up and down, changes in the transition process of the system in this case remain are acceptable. © 2019 IEEE.

关键词： Feedback

来源：评论

学校读者我要写书评

暂无评论

Optical Solitons with Cubic–Quartic Complex Ginzburg–Landau Equation Using a Novel Approach

SSRN

引用

SSRN 2022年

作者： Arnous, Ahmed H. Nofal, Taher A. Biswas, Anjan González-Gaxiola, O. Moraru, Luminita Moldovanu, Simona Department of Mathematics and Physics Grambling State University GramblingLA71245 United States Research Group Department of Mathematics King Abdulaziz University Jeddah21589 Saudi Arabia Department of Mathematics and Applied Mathematics Sefako Makgatho Health Sciences University Medunsa Pretoria 0204 South Africa Department of Applied Sciences Cross–Border Faculty of Humanities Economics and Engineering Dunarea de Jos University of Galati 111 Domneasca Street Galati800201 Romania Department of Applied Mathematics National Research Nuclear University 31 Kashirskoe Hwy Moscow115409 Russia Applied Mathematics and Systems Department Universidad Autonoma Metropolitana–Cuajimalpa Vasco de Quiroga 4871 Mexico City05348 Mexico Faculty of Sciences and Environment Department of Chemistry Physics and Environment Dunarea de Jos University of Galati 47 Domneasca Street 800008 Romania Department of Computer Science and Information Technology Faculty of Automation Computers Electrical Engineering and Electronics Dunarea de Jos University of Galati 47 Domneasca Street Galati800008 Romania Taif University Saudi Arabia

The present work retrieves cubic–quartic optical soliton solutions to the complex Ginzburg–Landau equation that is considered with five forms of nonlinear refractive index. The proposed algorithm reveals a full spectrum of optical solitons as well as hybrid type solitons whose existence are guaranteed with the listed parameter constraints. © 2022, The Authors. All rights reserved.

关键词： Solitons

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：