Filters








16,013 Hits in 6.6 sec

Weight assignment for adaptive image restoration by neural networks

S.W. Perry, L. Guan
2000 IEEE Transactions on Neural Networks  
This paper presents a scheme for adaptively training the weights, in terms of varying the regularization parameter, in a neural network for the restoration of digital images.  ...  The flexibility of neural-network-based image restoration algorithms easily allow the variation of restoration parameters such as blur statistics and regularization value spatially and temporally within  ...  In [23] , the authors used a model-based neural network approach to adaptively vary the restoration parameter.  ... 
doi:10.1109/72.822518 pmid:18249747 fatcat:3im2uoumqze4hfu5hn6xxphn2q

Advanced Techniques for Networked Systems with Applications

Zhiyong Chen, Haitao Zhang, Lijun Zhu, Steffi Knorn, Zhao Cheng
2017 Mathematical Problems in Engineering  
Chaotic time series prediction is a challenging problem for neural networks due to its uncertainty. Q. Li and R.-C.  ...  Cooperative control of networked systems is a fast-growing field, in which mathematical methods are typically used to investigate the theories and algorithms that address efficiency, availability, and  ...  Chaotic time series prediction is a challenging problem for neural networks due to its uncertainty. Q. Li and R.-C.  ... 
doi:10.1155/2017/3849019 fatcat:cq7d33zgircttpm5muyhwdszwa

Resilience Neural-Network-Based Methodology Applied on Optimized Transmission Systems Restoration

Josip Tosic, Srdjan Skok, Ljupko Teklic, Mislav Balkovic
2022 Energies  
The grid is analyzed using a large amount of data, which results in an adequate number of training data for artificial neural networks.  ...  This load-optimized restoration is dependent on sectioning of the transmission system based on artificial neural networks.  ...  The methodology proposed a combination of optimization constraints along with using a large set of data to train artificial neural networks.  ... 
doi:10.3390/en15134694 fatcat:7e4j5wdxqffrvhubjggtm3i3o4

Incorporating local statistics in image error measurement for adaptive image restoration

Ling Guan
2006 Optical Engineering: The Journal of SPIE  
In particular, an extended neural network algorithm is proposed to perform the restoration. It is shown that this technique is efficient, effective, and robust.  ...  Instead of using a conventional grayscale-based error measurement such as the mean squared error, we compare local statistical information about regions in two images using a new error measure.  ...  Perry was with the School of Electrical and Information Engineering, University of Sydney, and while P. Varjavandi was with the Department of Electrical and Computer Engineering, Ryerson University.  ... 
doi:10.1117/1.2181927 fatcat:tdvxuziv2bgyhneugx44fshcy4

Digital Images Securisation by Artificial Neural Networks

Tarik Hajji, Mohammed Ouazzani Jamil, El Miloud Jaraa
2017 2017 14th International Conference on Computer Graphics, Imaging and Visualization  
The objective of this work is to make the presentation of a new method that uses the power of artificial neural networks to the restoration and correction of errors in digital images in the case of a bad  ...  We will also present in this work, a new study to choose the structure of artificial neural networks most efficient and personalized learning algorithm to teach the neural network the recovery mechanism  ...  And also we made a comparative study to choose the structure of neural network the most effective for the compression and restoration of digital images.  ... 
doi:10.1109/cgiv.2017.12 fatcat:m6jpumizz5fovh4742fumqiu3m

Editor's Note

Manju Khari
2018 International Journal of Interactive Multimedia and Artificial Intelligence  
using artificial neural networks (ANNs) and is a very fast tool to estimate voltages and re/active power loss with a high accuracy compared to the traditional methods [12] .  ...  A Novel Smart Grid State Estimation Method Based on Neural Networks (Egypt) Abdel-Nasseret al. presents a novel method called SE-NN (state estimation using neural network) for smart grid state estimation  ... 
doi:10.9781/ijimai.2018.05.001 fatcat:4nhjspnibjbsbcqxd3auuhdifu

Intelligent Training in Control Centres Based on an Ambient Intelligence Paradigm [chapter]

Luiz Faria, António Silva, Carlos Ramos, Zita Vale, Albino Marques
2010 Lecture Notes in Computer Science  
This article describes a new approach in the Intelligent Training of Operators in Power Systems Control Centres, considering the new reality of Renewable Sources, Distributed Generation, and Electricity  ...  Markets, under the emerging paradigms of Cyber-Physical Systems and Ambient Intelligence.  ...  ITS is the approach we are using, combining several Artificial Intelligence techniques, namely: Multi-Agent Systems, Neural Networks, Constraint-based Modeling, Intelligent Planning, Knowledge Representation  ... 
doi:10.1007/978-3-642-13022-9_15 fatcat:ehnsmp2vdrfyhp37ikrbs5xdcy

Analysis Model of Image Colour Data Elements Based on Deep Neural Network

Chao Jiang, Zhen Jiang, Daijiao Shi, Gengxin Sun
2022 Computational Intelligence and Neuroscience  
Finally, using the properties of transfer learning and convolution neural network, an image colour element analysis model based on depth neural network is established.  ...  data reconstruction accuracy, and the analysis results have strong adaptability.  ...  SK2021A0260; Research on color digitization analysis and knowledge reuse of "Phoenix Painting" in Anhui province, No. SK2021A0263).  ... 
doi:10.1155/2022/7631788 pmid:35898791 pmcid:PMC9313933 fatcat:pb7p7v4bivgv7hf4jafzrhmgui

Evolutionary Neural Architecture Search for Image Restoration [article]

Gerard Jacques van Wyk, Anna Sergeevna Bosman
2019 arXiv   pre-print
Convolutional neural network (CNN) architectures have traditionally been explored by human experts in a manual search process that is time-consuming and ineffectively explores the massive space of potential  ...  The performance of architectures discovered by the proposed method is evaluated on a variety of image restoration tasks applied to the ImageNet64x64 dataset, and compared with human-engineered CNN architectures  ...  The chosen loss function across all experiments was the mean squared error (MSE), as it is commonly used for image restoration.  ... 
arXiv:1812.05866v2 fatcat:n6rnm7zltbadhpoxze7gyafgpy

2020 Index IEEE Transactions on Cybernetics Vol. 50

2020 IEEE Transactions on Cybernetics  
., and Gao, H., Reference Trajectory Reshaping Optimi-zation and Control of Robotic Exoskeletons for Human-Robot Co-Manipulation; TCYB Aug. 2020 3740-3751 Wu, X., Jiang, B., Yu, K., Miao, c., and Chen,  ...  ., +, TCYB Sept. 2020 4076-4086 Error analysis Adaptive Synchronization of Reaction-Diffusion Neural Networks and Its Application to Secure Communication.  ...  ., +, TCYB Oct. 2020 4469-4480 Image restoration Hyperspectral Image Restoration Using Weighted Group Sparsity-Regu- larized Low-Rank Tensor Decomposition.  ... 
doi:10.1109/tcyb.2020.3047216 fatcat:5giw32c2u5h23fu4drupnh644a

A recursive soft-decision approach to blind image deconvolution

K.-H. Yap, Ling Guan, Wanquan Liu
2003 IEEE Transactions on Signal Processing  
A nested neural network, called the hierarchical cluster model is employed to provide an adaptive, perception-based restoration.  ...  This paper presents a new approach to blind image deconvolution based on soft-decision blur identification and hierarchical neural networks.  ...  HIERARCHICAL NEURAL NETWORK FOR IMAGE RESTORATION A.  ... 
doi:10.1109/tsp.2002.806985 fatcat:zkuepn5v7befdpfnix4shki4ba

An Integrated System for the Analysis and the Recognition of Characters in Ancient Documents [chapter]

Stefano Vezzosi, Luigi Bedini, Anna Tonazzini
2002 Lecture Notes in Computer Science  
multilayer neural network.  ...  For each page, the system reduces noise by wavelet-based filtering, extracts and segments the text lines into characters by a fast adaptive thresholding, and performs OCR by a feed-forward back-propagation  ...  We used a multilayer feedforward network, with a hidden layer, trained with an adaptive back-propagation algorithm, that uses the batch gradient descent with momentum and variable learning rate, to avoid  ... 
doi:10.1007/3-540-45869-7_5 fatcat:r43fuvxvbbgxzm6pissgaorgee

Nonlinear System Identification using Neural Networks and Trajectory-Based Optimization [article]

Hamid Khodabandehlou, Mohammed Sami Fadali
2018 arXiv   pre-print
Two different global optimization approaches are used to train a recurrent neural network to identify two challenging nonlinear models, the cascaded tanks, and the Bouc-Wen system.  ...  In this paper, we study the identification of two challenging benchmark problems using neural networks.  ...  They studied the application of feedforwad neural networks, radial basis function networks, Runge-Kutta neural networks and adaptive neuro fuzzy inference systems to nonlinear system identification with  ... 
arXiv:1804.10346v2 fatcat:753o4l4jengh3olxwg3a2hvi4e

Neural Network based Decentralized Excitation Control of Large Scale Power Systems

Wenxin Liu, J. Sarangapani, G.K. Venayagamoorthy, D.C. Wunsch, D.A. Cartes
2006 The 2006 IEEE International Joint Conference on Neural Network Proceedings  
This paper presents a neural network (NN) based decentralized excitation controller design for large scale power systems.  ...  NNs are used to approximate the unknown/imprecise dynamics of the local power system and the interconnections.  ...  Section II presents a brief background on universal approximation property of neural networks and stability of nonlinear system. Section III presents the model transformation, and bound analysis.  ... 
doi:10.1109/ijcnn.2006.246943 dblp:conf/ijcnn/LiuSVWC06 fatcat:q4sw53lutnegjnb5bybif4tizq

Nonlinear System Identification using Neural Networks and Trajectory-based Optimization

Hamid Khodabandehlou, M. Fadali
2019 Proceedings of the 16th International Conference on Informatics in Control, Automation and Robotics  
Two different global optimization approaches are used to train a recurrent neural network to identify two challenging nonlinear models, the cascaded tanks and the Bouc-Wen system.  ...  Nonlinear System Identification using Neural Networks and Trajectory-based Optimization.  ...  Efe and Kaynak studied the identification of nonlinear systems using feedforwad neural networks, radial basis function networks, Runge-Kutta neural networks and adaptive neuro-fuzzy inference systems,  ... 
doi:10.5220/0007772605790586 dblp:conf/icinco/KhodabandehlouF19 fatcat:vaofx7gepfemzfnekikazkjbr4
« Previous Showing results 1 — 15 out of 16,013 results