Filters








17,544 Hits in 17.5 sec

Damage Detection of the Rod in the Crossflow Using Surrogate-Based Modelling

S. Upnere, J. Auzins
2021 Latvian Journal of Physics and Technical Sciences  
The performance of two surrogate modelling approaches has been evaluated. These models are the Response Surface Method and Legendre polynomial approximations.  ...  The selection of sample points is implemented with a new type of orthogonal design.  ...  ACKNOWLEDGEMENTS The research has been partially conducted with the financial support of the Latvian Council of Science project "Creation of Design of Experiments and Metamodel-ing Methods for Optimization  ... 
doi:10.2478/lpts-2021-0039 fatcat:profvppsbzezlfmmq6e2fpvfua

Optimal model-based sensorless adaptive optics for epifluorescence microscopy

Paolo Pozzi, Oleg Soloviev, Dean Wilding, Gleb Vdovin, Michel Verhaegen, Jennifer C. Fung
2018 PLoS ONE  
We report on a universal sample-independent sensorless adaptive optics method, based on modal optimization of the second moment of the fluorescence emission from a point-like excitation.  ...  Our method employs a sample-independent precalibration, performed only once for the particular system, to establish the direct relation between the image quality and the aberration.  ...  Acknowledgments The research leading to these results has received funding from the European Research Coun Author Contributions Conceptualization: Paolo Pozzi.  ... 
doi:10.1371/journal.pone.0194523 pmid:29558510 pmcid:PMC5860766 fatcat:x5z7jebxjzcn7n3yxpqbz4gxtu

Digital terrain modeling with orthogonal polynomials
Цифровое моделирование рельефа с использованием ортогональных полиномов

I. V. Florinsky, A. N. Pankratov
2015 Machine Learning and Data Analysis  
Methods: We developed a spectral analytical method and algorithm based on high-order orthogonal expansions using the Chebyshev polynomials of the first kind with the subsequent Fejér summation.  ...  Results: To test the method and algorithm, a DEM of the Northern Andes containing 230,880 points (the elevation matrix 480×481) has been used.  ...  In this paper we describe a spectral analytical method and algorithm based on high-order orthogonal expansions using the Chebyshev polynomials of the first kind with the subsequent Fejér summation.  ... 
doi:10.21469/22233792.1.12.01 fatcat:plkamr7rxfekhe2xjcjsiv7kai

Digital terrain modeling with the Chebyshev polynomials [article]

I. V. Florinsky, A. N. Pankratov
2015 arXiv   pre-print
We developed a spectral analytical method and algorithm based on high-order orthogonal expansions using the Chebyshev polynomials of the first kind with the subsequent Fejer summation.  ...  The test results demonstrated a good performance of the developed method and algorithm. They can be utilized as a universal tool for analytical treatment in digital terrain modeling.  ...  Acknowledgements The study was supported by RFBR grant 15-07-02484.  ... 
arXiv:1507.03960v2 fatcat:hewg56yav5cstku4mv626zzi3q

Prediction of stroke-related diagnostic and prognostic measures using robot-based evaluation

Sayyed Mostafa Mostafavi, Janice I. Glasgow, Sean P. Dukelow, Stephen H. Scott, Parvin Mousavi
2013 2013 IEEE 13th International Conference on Rehabilitation Robotics (ICORR)  
We compare our results with a previously applied approach based on linear regression and show the superiority of our modeling approach.  ...  robot-based metrics.  ...  PCI was used as a non-linear modeling approach in this study, whereby the clinical score-robotic metrics relationship was modeled based on correlation and polynomial fitting.  ... 
doi:10.1109/icorr.2013.6650457 pmid:24187274 dblp:conf/icorr/MostafaviGDSM13 fatcat:fbeohv6zvrgathp6b4oqnqczii

PRINCIPAL POLYNOMIAL ANALYSIS

VALERO LAPARRA, SANDRA JIMÉNEZ, DEVIS TUIA, GUSTAU CAMPS-VALLS, JESUS MALO
2014 International Journal of Neural Systems  
This paper presents a new framework for manifold learning based on a sequence of principal polynomials that capture the possibly nonlinear nature of the data.  ...  The proposed Principal Polynomial Analysis (PPA) generalizes PCA by modeling the directions of maximal variance by means of curves, instead of straight lines.  ...  ellipsoids based on the PPA metric.  ... 
doi:10.1142/s0129065714400073 pmid:25164247 fatcat:772cwgsyu5bypentgqcf7yi4ju

Two-dimensional Chebyshev polynomials for image fusion

Zaid Omar, Nikolaos Mitianoudis, Tania Stathaki
2010 28th Picture Coding Symposium  
This paper presents a novel method for fusing images in a domain concerning multiple sensors and modalities.  ...  Using Chebyshev polynomials as basis functions, the image is decomposed to perform fusion at feature level. Results show favourable performance compared to previous efforts on image fusion using ICA.  ...  are orthogonal with respect to the weight function W (x) = 1 √ 1−x 2 and valid over the interval [-1, 1].  ... 
doi:10.1109/pcs.2010.5702526 dblp:conf/pcs/OmarMS10 fatcat:7coakkjdh5hrng5mjiicqccjke

Hybrid Method Based on NARX models and Machine Learning for Pattern Recognition [article]

P. H. O. Silva, A. S. Cerqueira, E. G. Nepomuceno
2021 arXiv   pre-print
This work presents a novel technique that integrates the methodologies of machine learning and system identification to solve multiclass problems.  ...  The efficiency of the method was tested by running case studies investigated in machine learning, obtaining better absolute results when compared with classical classification algorithms.  ...  ACKNOWLEDGEMENTS We thank CAPES, CNPq, INERGE, FAPEMIG and Federal University of Juiz de Fora (UFJF) for the support.  ... 
arXiv:2106.04021v1 fatcat:cimrvwesnfgjbgdd7ln74hneje

Data-driven sparse polynomial chaos expansion for models with dependent inputs [article]

Zhanlin Liu, Youngjun Choe
2021 arXiv   pre-print
The proposed algorithm recursively constructs orthonormal polynomials using a set of monomials based on their correlations with the output.  ...  Typical approaches include building PCEs based on the Gram-Schmidt algorithm or transforming the dependent inputs into independent inputs.  ...  In addition, as it is presented in Figure 1 , the proposed model with a higher polynomial order achieves a smaller cross-validation error than the model with a lower polynomial order.  ... 
arXiv:2101.07997v2 fatcat:s6boqliwffdr3kj4x7kswhrsyu

Decision Tree Classification of Spatial Data Patterns From Videokeratography Using Zernike Polynomials [chapter]

M. D. Twa, S. Parthasarathy, T. W. Raasch, M. A. Bullimore
2003 Proceedings of the 2003 SIAM International Conference on Data Mining  
In this study we propose the use of Zernike polynomials to model the global shape of the cornea and use the polynomial coefficients as features for a decision tree classifier.  ...  Extensive experimental results, including a detailed study on enhancing model performance via adaptive boosting and bootstrap aggregation leads us to conclude that the proposed method can be highly accurate  ...  common metric in biomedical literature is the specificity of a classification model.  ... 
doi:10.1137/1.9781611972733.1 dblp:conf/sdm/TwaPRB03 fatcat:3uqmcs4lfva7vdiz4qvygtohga

Comparison of surrogate-based uncertainty quantification methods for computationally expensive simulators [article]

N. E. Owen, P. Challenor, P. P. Menon, S. Bennani
2017 arXiv   pre-print
metric, based on an independent validation design.  ...  Polynomial chaos and Gaussian process emulation are methods for surrogate-based uncertainty quantification, and have been developed independently in their respective communities over the last 25 years.  ...  The main class of methods here are based on cross-validation exercises, and leave-one-out cross validation is a popular approach.  ... 
arXiv:1511.00926v4 fatcat:7csoly5c4jag3gtogrvbivlxie

Low-Complexity Image and Video Coding Based on an Approximate Discrete Tchebichef Transform

Paulo A. M. Oliveira, Renato J. Cintra, Fabio M. Bayer, Sunera Kulasekera, Arjuna Madanayake
2017 IEEE transactions on circuits and systems for video technology (Print)  
The DTT transform kernel does not depend on the input data and fast algorithms can be developed to real time applications.  ...  The fast algorithm of the proposed transform is multiplication-free and requires a reduced number of additions and bit-shifting operations.  ...  Acknowledgment Arjuna Madanayake thanks the Xilinx University Program (XUP) for the Xilinx Virtex-6 Sx475 FPGA device installed in on the ROACH2 board.  ... 
doi:10.1109/tcsvt.2016.2515378 fatcat:ial2s7rahbewbkyq6vudlfnhb4

Stochastic sensitivity analysis for timing and amplitude of pressure waves in the arterial system

V. G. Eck, J. Feinberg, H. P. Langtangen, L. R. Hellevik
2015 International Journal for Numerical Methods in Biomedical Engineering  
Acknowledgement The work is supported by funding from Statoil ASA through the Simula School of Research and Innovation, and by a Center of Excellence grant from the Research Council of Norway through the  ...  Thanks also go to Vinzenz Gregor Eck, Stuart Clark, Karoline Hagane, Samwell Tarly, and a random distribution of unnamed bug fixers for their contributions.  ...  It is based on a linear regression fit between an orthogonal polynomial expansion and the model samples. Chaospy provides a few methods for this task.  ... 
doi:10.1002/cnm.2711 pmid:25684213 fatcat:ly7udoiharandg3dpkjmfl7m7a

Comparison of Surrogate-Based Uncertainty Quantification Methods for Computationally Expensive Simulators

N. E. Owen, P. Challenor, P. P. Menon, S. Bennani
2017 SIAM/ASA Journal on Uncertainty Quantification  
metric, based on an independent validation design.  ...  Polynomial chaos and Gaussian process emulation are methods for surrogate-based uncertainty quantification, and have been developed independently in their respective communities over the last 25 years.  ...  The main class of methods here are based on cross-validation exercises, and leave-one-out cross validation is a popular approach.  ... 
doi:10.1137/15m1046812 fatcat:qf6tqlwetbadpl75k2ocihkuby

Research issues in image registration for remote sensing

Roger D. Eastman, Jacqueline Le Moigne, Nathan S. Netanyahu
2007 2007 IEEE Conference on Computer Vision and Pattern Recognition  
Despite considerable investigation thejield has not settled on a dejinitive solution for most applications and a number of questions remain open.  ...  We conclude that remote sensing applications put particular demands on image registration algorithms to take into account domain-specijic knowledge of geometric transformations and image content.  ...  Acknowledgments We would like to acknowledge the invaluable contri-  ... 
doi:10.1109/cvpr.2007.383423 dblp:conf/cvpr/EastmanMN07 fatcat:kv4ic67kb5dw3bpc7wc5uv6qai
« Previous Showing results 1 — 15 out of 17,544 results