检索结果-内蒙古大学图书馆

MFGB: Molecular Properties Prediction leveraging Self-supervised Morgan Fingerprint Representation Learning

学校读者我要写书评

暂无评论

MFGB: Molecular Properties Prediction leveraging Self-superv...

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Shuyan Fang Yu Liu Song Liu School of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Provincial Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan University of Science and Technology Wuhan China Hubei Provincial Key Laboratory of Occupational Hazard Identification and Control Hubei Province Wuhan University of Science and Technology Wuhan China

Simple molecular graphs or molecular line notations are insufficient for molecular representation learning models that automatically learn molecule representations to acquire deep semantic features about chemistry. Therefore, we proposed the Morgan Fingerprint Graph, a novel molecular graph model constructed with the nodes of the Morgan Fingerprint Identifier, whose nodes incorporate various properties of the atom neighborhood. Based on our Morgan Fingerprint Graph, we trained a BERT-based molecular representation model MFGB which employs a local rather than global attention module to adapt the model to the Morgan Fingerprint Graph. The attention module of MFGB regulates the exchange of information in the attention layer based on the connection information of the atoms in the molecules. To verify the effectiveness of MFGB, we selected several mainstream datasets for evaluation. The results demonstrated that our method improve the performance of molecular properties prediction. In addition, we analyzed MFGB from both the over-smoothing and the attention perspectives. The analysis indicates that the node vector representations learned from the Morgan Fingerprint Graph are generally less smoothing, and the attention distributions of MFGB match the partial charge density distribution of the molecules.

关键词：

Learning data-adaptive nonparametric kernels

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Liu, Fanghui Huang, Xiaolin Gong, Chen Yang, Jie Li, Li Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Department of Automation Tsinghua University

Kernel methods have been extensively used in a variety of machine learning tasks such as classification, clustering, and dimensionality reduction. For complicated practical tasks, the traditional kernels, e.g., Gaussian kernel and sigmoid kernel, or their combinations are often not sufficiently flexible to fit the data. In this paper, we present a Data-Adaptive Nonparametric Kernel (DANK) learning framework in a data-driven manner. To be specific, in model formulation, we impose an adaptive matrix on the kernel/Gram matrix in an entry-wise strategy. Since we do not specify the formulation of the adaptive matrix, each entry in the adaptive matrix can be directly and flexibly learned from the data. Therefore, the solution space of the learned kernel is largely expanded, which makes our DANK model flexible to capture the data with different local statistical properties. Specifically, the proposed kernel learning framework can be seamlessly embedded to support vector machines (SVM) and support vector regression (SVR), which has the capability of enlarging the margin between classes and reducing the model generalization error. Theoretically, we demonstrate that the objective function of our DANK model embedded in SVM/SVR is gradient-Lipschitz continuous. Thereby, the training process for kernel and parameter learning in SVM/SVR can be efficiently optimized in a unified framework. Further, to address the scalability issue in nonparametric kernel learning framework, we decompose the entire optimization problem in DANK into several smaller easy-to-solve problems, so that our DANK model can be efficiently approximated by this partition. The effectiveness of this approximation is demonstrated by both empirical studies and theoretical guarantees. Experimentally, the proposed DANK model embedded in SVM/SVR achieves encouraging performance on various classification and regression benchmark datasets when compared with other representative kernel learning based algorithms. Copyrig

关键词： Matrix algebra

Predefined-time terminal sliding mode control of robot manipulators

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liang, Chang-Duo Ge, Ming-Feng Liu, Zhi-Wei Wang, Yan-Wu Karimi, Hamid Reza School of Mechanical Engineering and Electronic Information China University of Geosciences Wuhan430074 China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Key Laboratory of Image Processing and Intelligent Control Ministry of Education Huazhong University of Science and Technology Wuhan430074 China Department of Mechanical Engineering Politecnico di Milano Milan20156 Italy

In this paper, we present a new terminal sliding mode control to achieve predefined-time stability of robot manipulators. The proposed control is developed based on a novel predefined-time terminal sliding mode (PTSM) surface, on which the states are forced to reach the origin in a predefined time, i.e., the settling time is independent to the initial condition and can be explicitly user-defined via adjusting some specific parameters called the predefined-time parameters. It is also demonstrated that the proposed control can provide satisfactory steady-state performance in the case of both external disturbances and parametric uncertainties. Besides, we present a formal systemic analysis method to derive the sufficient conditions for guaranteeing the predefined-time convergence of the closed-loop system. Finally, the effectiveness and performance of the presented control scheme are illustrated through both theoretical comparisons and numerical simulations. Copyright © 2020, The Authors. All rights reserved.

关键词： Sliding mode control

Level attraction and PT symmetry in indirectly coupled microresonators

学校读者我要写书评

暂无评论

Physical Review A 2020年第4期102卷 043527-043527页

作者： Zhao-Hui Peng Chun-Xia Jia Yu-Qing Zhang Ji-Bing Yuan Le-Man Kuang Institute of Modern Physics and Department of Physics College of Physics and Electronic Science Hunan University of Science and Technology Xiangtan 411201 China Key Laboratory of Low-Dimensional Quantum Structures and Quantum Control of Ministry of Education Department of Physics and Synergetic Innovation Center for Quantum Effects and Applications Hunan Normal University Changsha 410081 China College of Physics and Electronic Engineering and Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang Normal University Hengyang 421008 China

Benefiting from the tunability of their phase delay and gain, we show the possibility of realizing level attraction, parity-time (PT)-, and anti-PT-symmetric photonic structures with indirectly coupled active and passive microresonators mediated by drop-filter waveguides. We find that level attraction originates from two mechanisms, i.e., exceptional point and resonance, and it may emerge not only for dissipative coupling but also coherent coupling and hybrid coupling after considering the gain and loss of microresonators, which confirms the universality of level attraction in the coupled photonic system. On the other hand, the transition from PT to anti-PT symmetry or vice versa may be realizable by tuning their phase delay and gain; thus the indirectly coupled microresonators may provide an excellent platform for exhibiting the unique features of PT and anti-PT symmetry. Furthermore, we also reveal the intrinsic relationship of the line shape and phase behavior of the reflection spectrum with PT symmetry, anti-PT symmetry, and level attraction.

关键词： Nanophotonics Optics & lasers Quantum optics Optical microcavities Waveguides Quantum theory

Tracking Performance of Networked Systems with Limited Bandwidth and Colored Noise

学校读者我要写书评

暂无评论

Tracking Performance of Networked Systems with Limited Bandw...

Chinese Automation Congress (CAC)

作者： Bin Zhang Xiaowei Jiang Li Sun Xianhe Zhang 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 Key Laboratory of System Control and Information Processing Ministry of Education Shanghai China School of Statistics and Mathematics Zhongnan University of Economics and Law Wuhan China School of Electrical Engineering and Automation Hubei Normal University Huangshi China

This study investigated the optimal tracking performance (OTP) of multi-input multi-output (MIMO), discrete- time networked control systems (NCSs). The limits of tracking performance (TP) under the influences of bandwidth, encoding- decoding, and additive coloured Gaussian noise (ACGN) are derived using the techniques of coprime decomposition and all-pass decomposition. The results reveal the negative impact of non-minimum phase (NMP) zeros and unstable poles of the plant as well as network communication constraints on the TP of NCSs. Finally, a numerical simulation is discussed and verifies our conclusions.

关键词： Networked control systems Gaussian noise Bandwidth Numerical simulation Downlink Decoding Colored noise

Asynchronous Decentralized Federated Learning for Collaborative Fault Diagnosis of PV Stations

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Liu, Qi Yang, Bo Wang, Zhaojian Zhu, Dafeng Wang, Xinyi Ma, Kai Guan, Xinping The Department of Automation Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China School of Electrical Engineering Yanshan University Qinhuangdao066004 China

Due to the different losses caused by various photovoltaic (PV) array faults, accurate diagnosis of fault types is becoming increasingly important. Compared with a single one, multiple PV stations collect sufficient fault samples, but their data is not allowed to be shared directly due to potential conflicts of interest. Therefore, federated learning can be exploited to train a collaborative fault diagnosis model. However, the modeling efficiency is seriously affected by the model update mechanism since each PV station has a different computing capability and amount of data. Moreover, for the safe and stable operation of the PV system, the robustness of collaborative modeling must be guaranteed rather than simply being processed on a central server. To address these challenges, a novel asynchronous decentralized federated learning (ADFL) framework is proposed. Each PV station not only trains its local model but also participates in collaborative fault diagnosis by exchanging model parameters to improve the generalization without losing accuracy. The global model is aggregated distributedly to avoid central node failure. By designing the asynchronous update scheme, the communication overhead and training time are greatly reduced. Both the experiments and numerical simulations are carried out to verify the effectiveness of the proposed method. © 2022, CC BY.

关键词： Failure analysis

Temperature control for Nano-Scale Films by Spatially-Separated Atomic Layer Deposition Based on Generalized Predictive control

学校读者我要写书评

暂无评论

IEEE Transactions on Nanotechnology 2015年第6期14卷 1094-1103页

作者： He, Wen-Jie Zhang, Hai-Tao Chen, Zhiyong Lin, Ji-Long Tian, Kan Shan, Bin Chen, Rong State Key Laboratory of Digital Manufacturing Equipment and Technology School of Mechanical Science and Engineering Huazhong University of Science and Technology Wuhan430074 China Key Laboratory of Image Processing and Intelligent Control School of Automation State Key Laboratory of Digital Manufacturing Equipment and Technology Huazhong University of Science and Technology Wuhan430074 China School of Electrical Engineering and Computer Science University of Newcastle CallaghanNSW2308 Australia China-EU Institute for Clean and Renewable Energy Huazhong University of Science and Technology Wuhan430074 China State Key Laboratory of Material Processing and Die and Mould Technology School of Materials Science and Engineering Huazhong University of Science and Technology Wuhan430074 China

This paper established a closed-loop temperature control system for a spatially-separated atomic layer deposition (S-ALD) reactor using generalized predictive control (GPC) algorithm. The GPC-based closed-loop control system rapidly and precisely stabilized the reactor temperature in the presence of thermal field disturbances. Compared with the proportion-integration differentiation (PID) control commonly used for S-ALD, the closed-loop GPC system attenuated reaction temperature oscillations when producing two-element nano-scale thin films. Furthermore, the proposed GPC system demonstrated the superiority in multi-element nano-laminates depositing efficiency by reducing the settling time with a substrate moving between different reactors. Electrical and optical properties of films verified the feasibility of the proposed GPC system. Finally, experimental results presented that the microstructure of the deposited ALD nanometer thin film was improved with the developed GPC system, compared with the PID strategy. © 2002-2012 IEEE.

关键词： Atomic layer deposition

Ordination-fuzzy min-max neural network classifier on unlabelled pattern classification

学校读者我要写书评

暂无评论

Moshi Shibie yu Rengong Zhineng/Pattern Recognition and Artificial Intelligence 2007年第2期20卷 173-179页

作者： Hu, Jing Yang, Jing Gao, Jun Laboratory of Image Information Processing School of Computer and Information Hefei University of Technology Hefei 230009 China Center for Biomimetic Sensing and Control Research Institute of Intelligent Machines Chinese Academy of Sciences Hefei 230031 China

An ordination-fuzzy min-max neural network (OFMM) based on non-metric multidimensional scaling (MDS) is proposed to solve the classification problems of unlabelled input pattern. Firstly, all the input patterns are sorted by MDS to get their similarity measures. Then these measures are used to supervise the following expansion and contraction stage of hyperboxes for classification. OFMM shows the improvements in the validity of unlabelled patterns classification, the network structure, and training time. The experimental results on standard dataset demonstrate that OFMM is a practical and effective classifier which is superior to the traditional general-fuzzy min -max neural network (GFMM).

关键词： Classifiers Fuzzy min-max neural network (FMMN) Multidimensional scaling (MDS) Similarity measures Unlabelled pattern

A non commutative generalization BL-rings

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Tsafack, Surdive Atamewoue Tchinda, Arnaud Fobasso Feng, Yuming Ndjeya, Selestin Key Laboratory of Intelligent Information Processing and Control Chongqing Three Gorges University Wanzhou Chongqing404100 China Department of Mathematics University of Yaounde 1 Cameroon Chongqing Engineering Research Center of Internet of Things and Intelligent Control Technology Chongqing Three Gorges University Wanzhou Chongqing404100 China Department of Mathematics Higher Teacher Training College University of Yaounde 1 Cameroon

The purpose of this work is to extend the study of the commutative rings whose lattice of ideals can be a structure of BL-algebra as carry out by Heubo et al in 2018, to non commutative rings appointed in the work as pseudo BL-rings. We study and characterize rings whose ideals form a pseudo BL-algebra, we describe them in terms of their subdirectly irreductible factors. We obtain that these are (up to isomorphism) to a subring of a direct sums of unitary special primary rings and discrete valuation *** Codes 03B50, 06D99. © 2021, CC BY.

关键词： Algebra