检索结果-内蒙古大学图书馆

Proceedings of the 41st International Conference on Machine Learning

作者： Qunxi Zhu Wei Lin Research Institute of Intelligent Complex Systems Fudan University China Research Institute of Intelligent Complex Systems and School of Mathematical Sciences LMNS and SCMS and State Key Laboratory of Medical Neurobiology and MOE Frontiers Center for Brain Science Institutes of Brain Science Fudan University China and Shanghai Artificial Intelligence Laboratory China

Continuous-time generative models, such as Flow Matching (FM), construct probability paths to transport between one distribution and another through the simulation-free learning of the neural ordinary differential equations (ODEs). During inference, however, the learned model often requires multiple neural network evaluations to accurately integrate the flow, resulting in a slow sampling speed. We attribute the reason to the inherent (joint) heterogeneity of source and/or target distributions, namely the singularity problem, which poses challenges for training the neural ODEs effectively. To address this issue, we propose a more general framework, termed Switched FM (SFM), that eliminates singularities via switching ODEs, as opposed to using a uniform ODE in FM. Importantly, we theoretically show that FM cannot transport between two simple distributions due to the existence and uniqueness of initial value problems of ODEs, while these limitations can be well tackled by SFM. From an orthogonal perspective, our framework can seamlessly integrate with the existing advanced techniques, such as minibatch optimal transport, to further enhance the straightness of the flow, yielding a more efficient sampling process with reduced costs. We demonstrate the effectiveness of the newly proposed SFM through several numerical examples.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Improved Variational Mode Decomposition with Adaptive Initial Center Frequency for Bearing Fault Feature Extraction

An Improved Variational Mode Decomposition with Adaptive Ini...

引用

Chinese Automation Congress (CAC)

作者： Ying Wang Xun Lang Jiande Wu Yuzhen Li Peng Li Yufeng Zhang Department of Electronic Engineering Information School Yunnan University Kunming China Yunnan Key Laboratory of Intelligent Systems and Computing Yunnan University Kunming China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

Variational mode decomposition (VMD) is extensively utilized in the field of industrial signal processing due to its superior anti-mixing and denoising capabilities. However, in practice, the performance of VMD is significantly influenced by the initial center frequency $\omega^{1}$ . An improper setting of $\omega^{1}$ can significantly reduce the stability of decomposition, resulting in the loss or masking of feature information by noise. To address the above issue, an improved VMD algorithm is proposed in this work. Our algorithm redefines $\omega^{1}$ based on the narrowband characteristics of intrinsic mode function (IMF). Under the new definition, $\omega^{1}$ can be adaptively adjusted based on the signal spectrum processed by Wiener filtering. This adjustment significantly enhances the flexibility and anti-mixing performance of the original VMD. To validate our proposed method, comparative experiments were conducted using two sets of fault data from Case Western Reserve University (CWRU). The results demonstrate that our method is more effective and superior in extracting fault features.

关键词： Vibrations Fault diagnosis Wiener filters Automation Noise Signal processing algorithms Feature extraction Maintenance Optimization Narrowband

来源：评论

学校读者我要写书评

暂无评论

Estimation and compensation of periodic disturbance using internal-model-based equivalent-input-disturbance approach

引用

Science China(Information Sciences) 2022年第8期65卷 150-163页

作者： Qicheng MEI Jinhua SHE Zhentao LIU Min WU School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems School of Engineering Tokyo University of Technology

This paper presents an improved equivalent-input-disturbance(EID) approach to deal with periodic disturbances. The approach has two degrees of freedom. One is an improved EID compensator, in which a repetitive controller is inserted in this study. The other is a conventional servo system for a reference *** improved EID compensator estimates and compensates for periodic disturbances without steady-state error, and the servo system ensures a satisfactory tracking performance. The improved EID compensator is designed using the linear-matrix-inequality(LMI) method. Three parameters in an LMI are selected using the particle-swarm-optimization(PSO) algorithm. The state-feedback gain of the conventional servo system is designed using the linear-quadratic-regulator(LQR) method. Simulation results of a rotational control system demonstrate the validity of the approach and its advantage over others.

关键词： equivalent input disturbance (EID) linear matrix inequality (LMI) linear quadratic regulator (LQR) particle swarm optimization (PSO) periodic disturbance repetitive control

来源：评论

学校读者我要写书评

暂无评论

Progress of the Impact of Terahertz Radiation on Ion Channel Kinetics in Neuronal Cells

引用

Neuroscience Bulletin 2024年第12期40卷 1960-1974页

作者： Yanjiang Liu Xi Liu Yousheng Shu Yuguo Yu Research Institute of Intelligent and Complex Systems Fudan UniversityShanghai200433China MOE Frontiers Center for Brain Science and State Key Laboratory of Medical Neurobiology Fudan UniversityShanghai200433China Institute of Science and Technology for Brain-Inspired Intelligence Fudan UniversityShanghai200433China Department of Neurology Huashan HospitalFudan UniversityShanghai20043China Institute for Translational Brain Research Fudan UniversityShanghai200433China Department of Neurosurgery Jinshan Hospital of Fudan UniversityShanghai201508China Shanghai Artificial Intelligence Laboratory Shanghai200232China

In neurons and myocytes,selective ion channels in the plasma membrane play a pivotal role in transducing chemical or sensory stimuli into electrical signals,underpinning neural and cardiac *** advancements in biomedical research have increasingly spotlighted the interaction between ion channels and electromagnetic fields,especially terahertz(THz)*** review synthesizes current findings on the impact of THz radiation,known for its deep penetration and non-ionizing properties,on ion channel kinetics and membrane fluid *** is organized into three parts:the biophysical effects of THz exposure on cells,the specific modulation of ion channels by THz radiation,and the potential pathophysiological consequences of THz *** the biophysical mechanisms underlying these effects could lead to new therapeutic strategies for diseases.

关键词： Ion channel kinetics Terahertz radiation Electromagnetic field interactions Neuron Cell membrane

来源：评论

学校读者我要写书评

暂无评论

Design of an intelligent Monitoring System for Operating States in a Coal Mine Drilling Process 41

Design of an Intelligent Monitoring System for Operating Sta...

引用

第41届中国控制会议

作者： Xiao Yang Luefeng Chen Sheng Du Chengda Lu Wangnian Li Min Wu School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Xi'an Research Institute Co.Ltd. China Coal Technology and Engineering Group

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

With the development trend of intelligent drilling in coal mines,an intelligent monitoring system for operating states in a drilling process is developed to solve the problems of incomplete display of drilling parameters and ineffective *** system realizes the remote monitoring of drilling *** mainly adopts the Fuzzy C-Means clustering algorithm to cluster the drilling *** it combines expert empirical knowledge to classify coal seams into soft,hard and alternating soft and hard coal *** boundary values are calculated according to the boundary ***,three drilling operating states,rated,conservative and over-excited,are judged to provide guidance for the drilling process control.

关键词： Drilling process intelligent monitoring Fuzzy C-Means clustering Operating states

来源：评论

学校读者我要写书评

暂无评论

TIME-INDEPENDENT SPIKING NEURON VIA MEMBRANE POTENTIAL ESTIMATION FOR EFFICIENT SPIKING NEURAL NETWORKS

arXiv

引用

arXiv 2024年

作者： Chen, Hanqi Yu, Lixing Zhan, Shaojie Yao, Penghui Shao, Jiankun School of Information Science and Engineering Yunnan University Yunnan Key Laboratory of Intelligent Systems and Computing Yunnan China State Key Laboratory of Explosion Science and Technology Beijing Institute of Technology Beijing China

The computational inefficiency of spiking neural networks (SNNs) is primarily due to the sequential updates of membrane potential, which becomes more pronounced during extended encoding periods compared to artificial neural networks (ANNs). This highlights the need to parallelize SNN computations effectively to leverage available hardware parallelism. To address this, we propose Membrane Potential Estimation Parallel Spiking Neurons (MPE-PSN), a parallel computation method for spiking neurons that enhances computational efficiency by enabling parallel processing while preserving the intrinsic dynamic characteristics of SNNs. Our approach exhibits promise for enhancing computational efficiency, particularly under conditions of elevated neuron density. Empirical experiments demonstrate that our method achieves state-of-the-art (SOTA) accuracy and efficiency on neuromorphic datasets. Codes are available at https://***/chrazqee/MPE-PSN. © 2024, CC BY.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Exchange Strategies for Multi-Colony Ant Algorithms in Dynamic Environments 13

Exchange Strategies for Multi-Colony Ant Algorithms in Dynam...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Mavrovouniotis, Michalis Li, Changhe Yazdani, Danial Handjimitsis, Diofantos Eratosthenes Centre of Excellence Limassol Cyprus Cyprus University of Technology Department of Civil Engineering and Geomatics Limassol Cyprus School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China University of Technology Sydney Faculty of Engineering & Information Technology Sydney Australia

ISBN: (纸本)9798350308365

In dynamic optimization problems where optimal solutions change over time, traditional ant colony optimization (ACO) algorithms face limitations. This study explores the adaptation of multi-colony ACO algorithms, known for their enhanced search capabilities in stationary problems, to tackle optimization problems in dynamic environments. Various strategies for exchanging information between colonies, which is a critical factor influencing algorithm performance, are investigated. Using the dynamic traveling salesman problem as a foundation, we generate test cases to reflect real-world complexities. Our results on a set of problem instances reveal that the choice of communication strategy between colonies significantly impacts the adaptability and efficiency of multi-colony ACO algorithms in tracking moving optimum. © 2024 IEEE.

关键词： Ant colony optimization

来源：评论

学校读者我要写书评

暂无评论

An algorithm for solving satisfiability problem based on the structural information of formulas

引用

Frontiers of Computer Science 2021年第6期15卷 191-193页

作者： Zaijun ZHANG Daoyun XU Jincheng ZHOU College of Computer Science and Technology Guizhou UniversityGuiyang 550025China Key Laboratory of Complex Systems and Intelligent Computing and School of Mathematics and Statistics Qiannan Normal University for NationalitiesDuyun 558000China School of Computer and Information Qiannan Normal University for NationalitiesDuyun 558000China

1 Introduction The propositional satisfiability(SAT)problem is an important and prototypical NP-hard problem in theoretical computer science[1].Many efforts have been made for designing high-performance SAT *** existing practical techniques for solving SAT problems are mainly divided into two categories:complete search technique and stochastic local search technique.

关键词： satisfiability technique computer

来源：评论

学校读者我要写书评

暂无评论

Dense Color Constraints based 6D object pose estimation from RGB-D images 41

Dense Color Constraints based 6D object pose estimation from...

引用

第41届中国控制会议

作者： Zilun Wang Yi Liu Chi Xu School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems CRRC Zhuzhou Locomotive Co. Ltd. National Innovation Center of Advanced Rail Transit Equipment

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

A key problem for 6 D pose estimation based on RGB-D image input is how to make full use of these two different data *** previous work simply took the depth map as the input of the fourth channel of CNN,or carried out the fusion of features extracted from these two data sources with different *** their fusion did not impose the right constraints and lost some valuable *** this work,we propose that DCC(Dense Color Constraints).6 D pose estimation performance can be improved effectively by using dense corresponding color *** show the most advanced end-to-end performance in LineMod datasets.

关键词： Computer Vision Deep Learning Pose Estimation

来源：评论

学校读者我要写书评

暂无评论

Drug-target interaction prediction using high order nonlinear features via neural factorization machines 4

Drug-target interaction prediction using high order nonlinea...

引用

2022 4th International Conference on Artificial Intelligence Technologies and Applications, ICAITA 2022

作者： Qian, Quan Zhu, Yuan School of Automation China University of Geosciences Wuhan430074 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

Medication design and repositioning are sped up by the prediction of drug-target interactions (DTIs). Two main kinds of prediction methods are commonly used, which are based on chemical structure feature extraction and deep learning methods. However, on the one hand, the DTI prediction approaches based on chemical structural feature extraction may not wholly explore the possible network characteristics in the data. On the other hand, many deep learning methods call for numerous layers of neural networks to be layered to learn higher-order feature interaction information. To sum up, the existing computation methods often have the limitations of gradient disappearance and overfitting. This study presents a novel method (JRD-NFM) by calculating Jaccard similarities, getting an eigenvector through Restarted random walk (RWR), and generating low-dimensional feature vectors by Disposition Component Analysis (DCA). Besides decoding the topological features and similarity information of target and drug node, it can also get the context information of a single network. Considering the advantages of Neural Factorization Machines (NFM) in extracting high-order nonlinear features and processing sparse data, this study use NFM to classifier the collection data to integrate drug and target biochemical structure information. The experimental results demonstrate that JRD-NFM can outperform widely used deep learning methods and conventional chemical structure approaches. It could provide fresh ideas for combining molecular structure and heterogeneous network data to predict DTIs. © Published under licence by IOP Publishing Ltd.

关键词： Feature extraction

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：