检索结果-内蒙古大学图书馆

The learning of fuzzy cognitive maps with noisy data: A rapid and robust learning method with maximum entropy

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Feng, Guoliang Lu, Wei Pedrycz, Witold Yang, Jianhua Liu, Xiaodong School of Control Science and Engineering Dalian University of Technology Dalian116023 China School of Automation Engineering Northeast Electric Power University Jilin132012 China School of Control Science and Engineering Dalian University of Technology Dalian116023 China Department of Electrical and Computer Engineering University of Alberta EdmontonABT6R 2V4 Canada Systems Research Institute Polish Academy of Sciences Warsaw00-901 Poland Department of Electrical and Computer Engineering Faculty of Engineering King Abdulaziz University Jeddah21589 Saudi Arabia

Numerous learning methods for fuzzy cognitive maps (FCMs), such as the Hebbian-based and the population-based learning methods, have been developed for modeling and simulating dynamic systems. However, these methods are faced with several obvious limitations. Most of these models are extremely time consuming when learning the large-scale FCMs with hundreds of nodes. Furthermore, the FCMs learned by those algorithms lack robustness when the experimental data contain noise. In addition, reasonable distribution of the weights is rarely considered in these algorithms, which could result in the reduction of the performance of the resulting FCM. In this article, a straightforward, rapid, and robust learning method is proposed to learn FCMs from noisy data, especially, to learn large-scale FCMs. The crux of the proposed algorithm is to equivalently transform the learning problem of FCMs to a classic-constrained convex optimization problem in which the least-squares term ensures the robustness of the well-learned FCM and the maximum entropy term regularizes the distribution of the weights of the well-learned FCM. A series of experiments covering two frequently used activation functions (the sigmoid and hyperbolic tangent functions) are performed on both synthetic datasets with noise and real-world datasets. The experimental results show that the proposed method is rapid and robust against data containing noise and that the well-learned weights have better distribution. In addition, the FCMs learned by the proposed method also exhibit superior performance in comparison with the existing methods. Copyright © 2019, The Authors. All rights reserved.

关键词： Fuzzy rules

Deep transfer learning based downlink channel prediction for FDD massive MIMO systems

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Yang, Yuwen Gao, Feifei Zhong, Zhimeng Ai, Bo Alkhateeb, Ahmed Department of Automation Tsinghua University Beijing100084 China Huawei Technologies Ltd. Shanghai210206 China State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing100044 China School of Electrical Computer and Energy Engineering Arizona State University TempeAZ85287 United States

—Artificial intelligence (AI) based downlink channel state information (CSI) prediction for frequency division duplexing (FDD) massive multiple-input multiple-output (MIMO) systems has attracted growing attention recently. However, existing works focus on the downlink CSI prediction for the users under a given environment and is hard to adapt to users in new environment especially when labeled data is limited. To address this issue, we formulate the downlink channel prediction as a deep transfer learning (DTL) problem, where each learning task aims to predict the downlink CSI from the uplink CSI for one single environment. Specifically, we develop the direct-transfer algorithm based on the fully-connected neural network architecture, where the network is trained on the data from all previous environments in the manner of classical deep learning and is then fine-tuned for new environments. To further improve the transfer efficiency, we propose the meta-learning algorithm that trains the network by alternating inner-task and across-task updates and then adapts to a new environment with a small number of labeled data. Simulation results show that the direct-transfer algorithm achieves better performance than the deep learning algorithm, which implies that the transfer learning benefits the downlink channel prediction in new environments. Moreover, the meta-learning algorithm significantly outperforms the direct-transfer algorithm in terms of both prediction accuracy and stability, which validates its effectiveness and superiority. Copyright © 2019, The Authors. All rights reserved.

关键词： Forecasting

Exponential convergence for distributed smooth optimization under the restricted secant inequality condition

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Yi, Xinlei Zhang, Shengjun Yang, Tao Johansson, Karl H. Chai, Tianyou Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm100 44 Sweden Department of Electrical Engineering University of North Texas DentonTX76203 United States State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China

This paper considers the distributed smooth optimization problem in which the objective is to minimize a global cost function formed by a sum of local smooth cost functions, by using local information exchange. The standard assumption for proving exponential/linear convergence of first-order methods is the strong convexity of the cost functions, which does not hold for many practical applications. In this paper, we first show that the continuous-time distributed primal-dual gradient algorithm converges to one global minimizer exponentially under the assumption that the global cost function satisfies the restricted secant inequality condition. This condition is weaker than the strong convexity condition since it does not require convexity and the global minimizers are not necessary to be unique. We then show that the discrete-time distributed primal-dual algorithm constructed by using the Euler's approximation method converges to one global minimizer linearly under the same condition. The theoretical results are illustrated by numerical simulations. Copyright © 2019, The Authors. All rights reserved.

关键词： Continuous time systems

Robust semi-global leader-following practical consensus of a group of linear systems with imperfect actuators

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2017年第7期60卷 195-206页

作者： Liangren SHI Zhiyun ZHAO Zongli LIN Department of Automation Shanghai Jiao Tong University Key Laboratory of Advanced Control and Optimization for Chemical Processes(East China University of Science and Technology) Ministry of Education Charles L. Brown Department of Electrical and Computer Engineering University of Virginia

This paper considers the problem of semi-global leader-following consensus of a multi-agent system whose agent dynamics are represented by linear systems. The input output characteristics of the follower agent actuators, such as those of saturation and dead-zone, are imperfect, not precisely known, and subject to the effect of disturbances. Two consensus control algorithms, of the low-and-high gain feedback type and the low gain based variable structure control type, are proposed for solving the consensus problem. It is shown that both of these control algorithms achieve semi-global leader-following practical consensus in the presence of the imperfectness of the actuators when the communication topology among the follower agents is represented by a strongly connected and detailed balanced directed graph and the leader agent is a neighbor of at least one follower agent. The theoretical results are illustrated by numerical simulation.

关键词： consensus leader-following actuator saturation dead-zone low-and-high gain feedback low gain based variable structure control

Time Optimal Robust Fleet Management of Micro UAV Through Timed Games Formulation

学校读者我要写书评

暂无评论

Time Optimal Robust Fleet Management of Micro UAV Through Ti...

control Technology and Applications (CCTA),

作者： Henrik Schiøler Luminita Totu Jan Dimon Kim Guldstrand Larsen Jakob Haahr Taankvist Section for Control and Automation Aalborg Universty Aalborg Denmark Department for Computer Science Aalborg Universty Aalborg Denmark Aalborg Universitet Aalborg DK

We consider the case of fleet management of a moderate number of Unmanned Aerial Vehicles (UAV or UAS) in confined space, e.g. indoor. Indoor operation of UAVs requires indoor localization capabilities as well as a sufficiently precise 3D map of the facility, whereas fleet management of multiple UAV adds an extra dimension of complexity. Additional complexity is mainly introduced by constraints ensuring collision free operation. Based on earlier work on mapping, path planning and localization we suggest fleet management through a Timed Game formulation and Winning Strategy controller synthesis using the tool Uppaal Tiga.

关键词： Automata Games Unmanned aerial vehicles Uncertainty Path planning Schedules Clocks

Analysis of Harmonics Detection and their Filtration by using Active Band Pass Filter for Domestic Appliances

学校读者我要写书评

暂无评论

Analysis of Harmonics Detection and their Filtration by usin...

IEEE International Conference on automation Science and Engineering (CASE)

作者： Ehtisham Lodhi Zeeshan Lodhi Zhu Fenghua Gang Xiong Feiyue Wang Waheed ur Rehman Tariku Sinshaw The SKL for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Department of Electrical and Computer Engineering COMSATS University Islamabad Abbottabad Campus Pakistan Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan Guangdong China Beijing Engineering Research Center of Intellectual System and Technology Chinese Academy of Sciences Beijing China College of Mechanical Engineering and Applied Electronics Technologies Beijing University of Technology Beijing China

ISBN: (数字)9781728169040

ISBN: (纸本)9781728169057

In modern era, one of the rising power quality (PQ) concern is harmonics distortion (HD). The HD is usually produced by increase in the utilization of nonlinear user loads at domestic level. It not only spoils the PQ but also have harmful effects on electrical appliances. So, this paper presents a new approach to mitigate the HD in home appliances rapidly by utilizing the active band pass filter (ABPF). The fast Fourier transform (FFT) technique is employed for the detection of harmonics in appliances. The band pass filter dramatically affects the response time of active filter. The suggested control methodology is capable to eliminate harmonics from distorted input voltage waveform and provides a pure sinusoidal waveform. The prototype of this model is also implemented. Experimental results along with simulation show that the proposed model is quite effective in eliminating HD despite load variations and also useful to compensate the reactive power in electronic home appliances. Hence, this technique is cost effective for domestic users with high quality performance in all aspects.

关键词： Power harmonic filters Harmonic analysis Band-pass filters Harmonic distortion Home appliances

Analysis of Influencing Factors on Carbon Monoxide Utilization Rate of Blast Furnace Based on Multi-Timescale Characteristics 36

学校读者我要写书评

暂无评论

Analysis of Influencing Factors on Carbon Monoxide Utilizati...

第36届中国控制会议

作者： Jianqi An Yuwan Yang Min Wu Takao Terano School of Automation China University of Geosciences Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Department of Computer Science School of ComputingTokyo Institute of Technology

ISBN: (纸本)9781538629185

In the blast furnace,due to the different changing frequency of different operations,and the different reaction time of gas,liquid and solid materials,there exists multi-timescale characteristics in the iron-making ***,not enough attention has been paid to this characteristic,most of the analyses on the blast furnace state before are under a fixed time ***,this paper makes a analysis of influencing factors on carbon monoxide utilization rate of blast furnace based on multi-timescale ***,the factors that affect the carbon monoxide utilization rate are analyzed from different time ***,in the short time scale,the individual influencing time scale of the permeability index,total pressure difference and top temperature is found by the support vector machine（SVM） *** in the long time scale,the influencing time scale of burdening is *** the validity of each model is verified by the field data of the blast furnace.

关键词： Multi-time scales Carbon monoxide utilization Support vector machine Blast furnace

Linear convergence of first- And zeroth-order primal-dual algorithms for distributed nonconvex optimization

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Yi, Xinlei Zhang, Shengjun Yang, Tao Chai, Tianyou Johansson, Karl H. Division of Decision and Control Systems School of Electrical Engineering and Computer Science Kth Royal Institute of Technology Digital Futures Stockholm100 44 Sweden Department of Electrical Engineering University of North Texas DentonTX76203 United States State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China

This paper considers the distributed nonconvex optimization problem of minimizing a global cost function formed by a sum of local cost functions by using local information *** first propose a distributed first-order primal-dual algorithm. We show that it converges sublinearly to a stationary point if each local cost function is smooth and linearly to a global optimum under an additional condition that the global cost function satisfies the Polyak-Lojasiewicz condition. This condition is weaker than strong convexity, which is a standard condition for proving linear convergence of distributed optimization algorithms, and the global minimizer is not necessarily unique. Motivated by the situations where the gradients are unavailable, we then propose a distributed zeroth-order algorithm, derived from the proposed distributed first-order algorithm by using a deterministic gradient estimator, and show that it has the same convergence properties as the proposed first-order algorithm under the same conditions. The theoretical results are illustrated by numerical simulations. Copyright © 2019, The Authors. All rights reserved.

关键词： Cost functions

TransMut: a program to predict HLA-I peptide binding and optimize mutated peptides for vaccine design by the Transformer-derived self-attention model

学校读者我要写书评

暂无评论

Research Square

Research Square 2021年

作者： Chu, Yanyi Zhang, Yan Wang, Qiankun Zhang, Lingfeng Wang, Xuhong Wang, Yanjing Wang, Jianmin Jiang, Xue Salahub, Dennis Russell Xiong, Yi Wei, Dong-Qing State Key Laboratory of Microbial Metabolism Shanghai-Islamabad-Belgrade Joint Innovation Center on Antibacterial Resistances Joint International Research Laboratory of Metabolic & Developmental Sciences School of Life Sciences and Biotechnology Shanghai Jiao Tong University Shanghai200030 China Department of Chemistry CMS - Centre for Molecular Simulation IQST - Institute for Quantum Science and Technology University of Calgary 2500 University Drive NW CalgaryABT2N 1N4 Canada Department of Clinical Oncology The University of Hong Kong-Shenzhen Hospital Shenzhen China School of Electrical Engineering and Computer Science University of Ottawa 75 Laurier Ave. OttawaONK1N 6N5 Canada The Ministry of Education Key Laboratory of System control and information processing Department of Automation School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai200030 China Integrative Biotechnology & Translational Medicine Yonsei University Incheon21983 Korea Republic of Peng Cheng Laboratory Vanke Cloud City Phase I Building 8 Xili Street Nanshan District Guangdong Shenzhen518055 China

Computational prediction of the interaction between human leukocyte antigen (HLA) and peptide (pHLA) can speed up epitope screening and vaccine design. Here, we develop the TransMut framework composed of TransPHLA for pHLA binding prediction and AOMP for mutated peptide optimization, which can be generalized to any binding and mutation task of biomolecules. Firstly, TransPHLA is developed by using a Transformer-derived self-attention model to predict pHLA binding, which is significantly superior to 11 previous methods on pHLA binding prediction, neoantigen and human papilloma virus vaccine identification. For vaccine design, the AOMP program is then developed to automatically optimize mutated peptides to search for mutant peptides with higher affinity to the target HLA and with high homology to the source peptide. Among 3660 non-binding pHLAs, 3630 were successfully mutated. Of these, 94% were verified by the IEDB recommended method, and 88% have homology higher than 80% to the source peptide. © 2021, CC BY.

关键词： Peptides