检索结果-内蒙古大学图书馆

A Contactless Insulator Contamination Levels Detecting Method Based on Infrared Images Features and RBFNN

IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS 2019年第3期55卷 2455-2463页

作者： He, Hongying Luo, Diansheng Lee, Wei-Jen Zhang, Zhenyuan Cao, Yijia Lu, Tianguang Hunan Univ Changsha 410082 Hunan Peoples R China Univ Texas Arlington Arlington TX 76019 USA Univ Elect Sci & Technol China Chengdu 610054 Peoples R China Shanghai Jiao Tong Univ Shanghai 200240 Peoples R China

A contactless method uses infrared image features and radial basis function neural network (RBFNN) to detect contamination levels for porcelain insulators is proposed in this paper. First, theory evidence for contamination levels detection by infrared images is inferred. Then, the denoising and image segmentation is implemented to suppress the image noise and eliminate the affection of the background. Nine color moment features related to the contamination levels are extracted from the insulator images. Finally, an RBFNN is constructed to identify the contamination levels. The images features and ambient relative humidity are taken as the inputs of the RBFNN. For improve the precision of the detection, a new method based on the statistical probability of the values of each contamination feature component is proposed to select the initial hidden center parameters for RBFNN hidden nodes. An improved learning algorithm combined with the gradient descent algorithm and a random number control factor are proposed to modify the hidden center parameters and the weights vectors. Testing results show that the selected color moment features are effective on the contamination levels representation and the constructed RBFNN performs better than back propagation neural network (BPNN) and generalized regression neural network (GRNN) on contamination levels identification.

关键词： Color moment features contamination levels identification gradient descent algorithm hidden center parameters image processing infrared image insulators radial basis function neural network (RBFNN) random number control factor

来源：评论

学校读者我要写书评

暂无评论

Extended content-boosted matrix factorization algorithm for recommender systems 18th

Extended content-boosted matrix factorization algorithm for ...

引用

18th Annual International Conference on Knowledge-Based and Intelligent Information and Engineering Systems (KES)

作者： Krasnoshchok, Oleksandr Lamo, Yngve Bergen Univ Coll N-5020 Bergen Norway

Recommender technologies have been developed to give helpful predictions for decision making under uncertainty. An extensive amount of research has been done to increase the quality of such predictions, currently the methods based on matrix factorization are recognized as one of the most efficient. The focus of this paper is to extend a matrix factorization algorithm with content awareness to increase prediction accuracy. A recommender system prototype based on the resulting Extended Content-Boosted Matrix Factorization algorithm is designed, developed and evaluated. The algorithm has been evaluated by empirical evaluation, which starts with creating of an experimental design, then conducting off-line empirical tests with accuracy measurement. The result revealed further potential of the content awareness in matrix factorization methods, which has not been fully realized in the generalized alignment-biased algorithm by Nguyen and Zhu and uncovers opportunities for future research. (C) 2014 The Authors. Published by Elsevier B.V.

关键词： gradient descent algorithm Content Aware Collaborative Filtering algorithm

来源：评论

学校读者我要写书评

暂无评论

Adaptive Tracking Control Based on CMAC for nonlinear Systems

Adaptive Tracking Control Based on CMAC for nonlinear System...

引用

Annual International Conference on System Science and Engineering (ICSSE)

作者： Van-Phuong Ta Xuan-Kien Dang Thanh-Quyen Ngo Ho Chi Minh City Univ Technol & Educ Ho Chi Minh City Vietnam Hochiminh Univ Transport Ho Chi Minh City Vietnam Hochiminh Univ Ind Ho Chi Minh City Vietnam

ISBN: (纸本)9781538634226

In this study, we present control system based on cerebellar model articulation controller (CMAC) for nonlinear systems to achieve high precision trajectory tracking. The proposed control system includes the CMAC with its fast learning and good generalization capability is applied to approximate uncertainties or model parameter variation to attain error function minimum and a compensator controller (CC) is designed to cancel the approximation error for guaranteeing the stable of the system. The gradient descent method is used to turn online parameters of the CMAC and the stability of the control system can be guaranteed by the compensator controller. The experimental results of Tank Pressure Control and Tank Water Level Control Systems prove that the robustness and effectiveness of the proposed controller.

关键词： Cerebellar model articulation controller (CMAC) Compensator Controller (CC) adaptive tracking control gradient descent algorithm

来源：评论

学校读者我要写书评

暂无评论

Unmixing Of Hyperpectral Image Using Nonlinear Parametric Model 1

Unmixing Of Hyperpectral Image Using Nonlinear Parametric Mo...

引用

IEEE International Conference on Recent Trends in Electronics, Information and Communication Technology (RTEICT)

作者： Navinkumar, Thacker Unnatiben Parmar, S. K. GCET EC Dept Anand Gujarat India

ISBN: (纸本)9781509007745

Hyperspectral image contains hundreds of bands so it is spectrally overloaded and contains extent information to differentiate spectrally unique material. Hyperspectral data generally used to identify the presence of material in scene. Almost all the hyperspectral cameras have spatial resolution limit (> 5m per pixel) due to that each pixel can be a mixture of several materials. The process ofunmixing is to unmixone of these mixed pixels. There are two models available to approximate mixing, (i) Linear Mixing Model (LMM) (ii) Nonlinear Mixing Model (NMM). Over a time, various approaches have been devised to address LMM and it's unmixing. In LMM, macrospectral mixtures are assumed. Nonlinear model comes under consideration due to microscopic mixing scale. In this paper, Generalized bilinear model is used which is nonlinear parametric model to get mixed data. Its accuracy depends on parametric form and parameter value chosen. It comes under convex optimization problem, so it can be solved using any optimization technique. gradient descent algorithm (GDA) is employed to solve this optimization problem. Advantage of GDA over other unmixing techniques is that it transforms nonlinear model into linear one. To improve unmixing result, it is indeed advisable to consider spatial correlation among abundances. A novel approach has been introduced in this paper which considers 2nd order neighborhood correlation between abundances. Using our approach one can achieve better segmentation.

关键词： hyperspectral image linear mixing model nonlinear mixing model unmixing generalized bilinear model gradient descent algorithm spatial correlation

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of nonlinear neural network controller based on simulator model in Damavand Tokamak

Design and Implementation of nonlinear neural network contro...

引用

24th Chinese Control and Decision Conference (CCDC)

作者： Tolouei, H. Kouhi, A. Rasouli, H. Rasouli, C. KN Toosi Univ Technol Control Dept Fac Elect Engn Adv Proc Automat & Control Lab APAC Tehran Iran Plasma Phys & Nuclear Fus Inst Inst Nucl Sci & Technol AEOI Tehran Iran

ISBN: (纸本)9781457720727

In this study, nonlinear neural network controller will be developed to control plasma radial motion in Damavand Tokamak. It is essential to have a good model in order to design a proper controller for plasma radial motion. To achieve this goal, actuator circuits are simulated and in consequence based on simulator model and simulated actuator circuits nonlinear neural network controller will be designed in Damavand Tokamak. Comparison between neural network controller output and PD controller output shows the efficiency of proposed approach.

关键词： Tokamak Actuator circuits nonlinear neural network controller gradient descent algorithm Momentum algorithm

来源：评论

学校读者我要写书评

暂无评论

Supervised Learning in a Single Layer Dynamic Synapses Neural Network

Supervised Learning in a Single Layer Dynamic Synapses Neura...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Yousefi, Ali Dibazar, Alireza A. Berger, Theodore W. Univ So Calif Neural Dynam Lab Los Angeles CA 90089 USA

ISBN: (纸本)9781424496365

The main focus of this paper is to introduce a new supervised learning algorithm for spiking neural networks. The learning algorithm minimizes the overall differences between spike times of target and test spike trains by utilizing a new quantitative similarity measure which has been defined in this work. The actual membrane potential of a post-synaptic neuron is adjusted at the time of spikes based on what has been measured from similarity measure in order to generate the desired membrane potential. Finally, by utilizing gradient descent algorithm, the parameters of the spiking neural network are tuned to generate the desired output membrane potential. The proposed algorithm was applied to tune the facilitation, depression, and synaptic weight constants of the Dynamic Synapses Neural Network - DSNN - for the aim of input-output functional mapping. The simulation results show that the system identification task converges to the global optimum. The rate-to-time coding simulation performs with more than 75 percent accuracy. The performance of both system identification and rate-to-time coding is due to adaptation of short and long term synaptic parameters which cannot be accomplished if only synaptic weight is adapted.

关键词： Adaptation models Calcium Energy states Filtering Heuristic algorithms Mathematical model Neurons depression weight constant facilitation weight constant gradient descent algorithm gradient methods input-output functional mapping learning (artificial intelligence) neural nets post-synaptic neuron rate-to-time coding simulation single layer dynamic synapses neural network spike train supervised learning algorithm synaptic weight constant

来源：评论

学校读者我要写书评

暂无评论

Adaptive Spherical Gaussian Kernel for fast Relevance Vector Machine Regression

Adaptive Spherical Gaussian Kernel for fast Relevance Vector...

引用

7th World Congress on Intelligent Control and Automation

作者： Yuan, Jin Yu, Tao Wang, Kesheng Liu, Xuemei Shanghai Univ CIMS Shanghai 200072 Peoples R China Norwegian Univ Sci & Technol Dept Prod & Qual Engn N-7491 Trondheim Norway Shandong Agr Univ Sch Mech & Elect Engn Tai An Shandong 271018 Peoples R China

ISBN: (纸本)9781424421138

As a popular and competent kernel function in Kernel based machine learning techniques, conventional Gaussian kernel has unified kernel width with each of basis functions, which make impliedly a basic assumption: the response signal represents below certain frequency and the noise represents above such certain frequency. However, in many case, this assumption does not hold. To overcome this limitation, a novel adaptive spherical Gaussian kernel is utilized for nonlinear regression, and the stagewise optimization algorithm for maximizing Bayesian evidence in sparse Bayesian learning framework is proposed for model selection. Extensive empirical study shows its effectiveness and flexibility of model on representing regression problem with higher levels of sparsity and higher performance than classical RVM. The attractive ability of this approach is to automatically choose the right kernel widths locally fitting RVs from the training dataset;which could keep right level smoothing at each scale of signal.

关键词： Relevance Vector Machine (RVM) Gaussian kernel function Regression gradient descent algorithm Bayesian evidence

来源：评论

学校读者我要写书评

暂无评论

Learning of Recurrent Convolutional Neural Networks with Applications in Pattern Recognition 36

Learning of Recurrent Convolutional Neural Networks with App...

引用

第36届中国控制会议

作者： Qiaoyun Wang He Huang School of Electronic and Information Engineering Soochow University

ISBN: (纸本)9781538629185

Convolutional neural network(CNN) has been successfully applied in character *** further reduce the error rate of classification,based on traditional CNN,a recurrent-type CNN(RCNN) is presented in this *** ElmanJordan recurrent model is embedded in the full connection layer of the proposed *** optimizing the structure of the traditional CNN and making full use of the better learning ability of recurrent neural network,the proposed RCNN has a better recognition ability for input signals with *** verify the performance of the developed RCNN,some experiments are accomplished on the Chinese car plates and MNIST *** experimental results show that,compared with traditional CNN and Elman-type CNN,a much smaller error rate can be guaranteed by our model.

关键词： Recurrent convolutional neural networks gradient descent algorithm Elman-Jordan recurrent neural networks pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Detection of pollutant source in groundwater using hybrid optimization model

引用

International Journal of Energy and Water Resources 2022年第1期6卷 81-93页

作者： Ayaz, M. Ansari, S.A. Singh, O.K. Civil Engineering Section University Polytechnic Aligarh Muslim University Aligarh Aligarh 202002 India Department of Civil Engineering Zakir Husain College of Engineering and Technology Aligarh Muslim University Aligarh 202002 India

Detection of groundwater pollution source is an inverse problem. To solve this inverse problem, it has been posed into an optimization problem. In this study, a hybrid optimization model has been developed for detection of groundwater pollution sources in terms of its source characteristics, namely, source location, source strength and duration of activity of pollution source. In this hybrid optimization model, the Genetic algorithm model has been linked with the gradient descent optimization model. The global convergence property of Genetic algorithm has been utilized to find the optimal solution near global minima. This solution is then used as an initial guess to the gradient descent optimization model to find the global minima. The performance of developed hybrid model has been evaluated for two-dimensional case for error free and erroneous concentration data. Performance results show a significant improvement in the prediction error of groundwater pollution source parameters. The prediction error using GA model was found to be equal to 10.806%, 13.930% and 25.211% in source location, duration of activity and source strength, respectively, while using hybrid optimization model the prediction error were improved to 0.461%, 7.178% and 9.999%. The novelty of the present work is that it requires the observed concentration data of one observation well only for complete identification of pollution source. Also, a prior knowledge of probable locations of potential pollution sources is not required in this model. © Islamic Azad University (IAU) 2021.

关键词： Genetic algorithm gradient descent algorithm Groundwater pollution Inverse problem Remediation strategy

来源：评论

学校读者我要写书评

暂无评论

Optimal Synthesis of the Slider-crank Mechanism for Path Generation Based on the Generalized Kinematic Mapping of Constrained Plane Motions 14

Optimal Synthesis of the Slider-crank Mechanism for Path Gen...

引用

14th International-Federation-for-the-Promotion-of-Mechanism-and-Machine-Science World Congress

作者： Chen, Genliang Wang, Hao Yu, Weidong Zhao, Yong Shanghai Jiao Tong Univ Shanghai Key Lab Digital Mfg Thin Walled Struct State Key Lab Mech Syst & Vibrat Shanghai 200240 Peoples R China

ISBN: (纸本)9789860460988

This paper presents a new strategy for the optimal synthesis of the planar slider-crank mechanism for continuous path generations. Based on the generalized kinematic mapping of constrained plane motions, the desired path for the coupler link is mapped into the three-dimensional projective space as a spatial surface, which is regarded as the target kinematic manifold. Also, the potential motions of the coupler link constrained by the crank and the slider are projected on the target manifold in the image space, whose difference can be regarded as an alternative description for the kinematic conflict of the mechanism with the design requirement. Thus, a metric for the structure error between the candidate mechanism and the ideal one for the desired path is set up in terms of the area of a ruled surface, the distance surface intercepted from the target manifold, which is also selected as the objective function for the optimal synthesis. To obtain the final optimum based on the initial design variables with high convergence rate, the gradient descent algorithm is introduced. A numerical example for the optimal synthesis of the planar slider-crank mechanism for an elliptic trajectory is studied to validate the effectiveness of the proposed approach.

关键词： Optimal synthesis Planar slider-crank mechanism Continuous path generations Generalized kinematic mapping gradient descent algorithm

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：