scholarly journals A delay damage model selection algorithm for NARX neural networks

1997 ◽  
Vol 45 (11) ◽  
pp. 2719-2730 ◽  
Author(s):  
Tsung-Nan Lin ◽  
C.L. Giles ◽  
B.G. Horne ◽  
Sun-Yuan Kung
Keyword(s):  
Neural Networks ◽  
Model Selection ◽  
Damage Model ◽  
Selection Algorithm

scholarly journals Accounting for cell lineage and sex effects in the identification of cell-specific DNA methylation using a Bayesian model selection algorithm

PLoS ONE ◽  
2017 ◽  
Vol 12 (9) ◽  
pp. e0182455 ◽  
Author(s):  
Nicole White ◽  
Miles Benton ◽  
Daniel Kennedy ◽  
Andrew Fox ◽  
Lyn Griffiths ◽  
...  
Keyword(s):  
Dna Methylation ◽  
Model Selection ◽  
Bayesian Model ◽  
Cell Lineage ◽  
Bayesian Model Selection ◽  
Selection Algorithm ◽  
Sex Effects

scholarly journals Non-linear contour-based multidirectional intra coding

2018 ◽  
Vol 7 ◽  
Author(s):  
Thorsten Laude ◽  
Jan Tumbrägel ◽  
Marco Munderloh ◽  
Jörn Ostermann
Keyword(s):  
Model Selection ◽  
Image Coding ◽  
Reference Area ◽  
Selection Algorithm ◽  
Still Image ◽  
Intra Coding ◽  
Coding Efficiency ◽  
Contour Model ◽  
Non Linear ◽  
Contour Models

AbstractIntra coding is an essential part of all video coding algorithms and applications. Additionally, intra coding algorithms are predestined for an efficient still image coding. To overcome limitations in existing intra coding algorithms (such as linear directional extrapolation, only one direction per block, small reference area), we propose non-linear Contour-based Multidirectional Intra Coding. This coding mode is based on four different non-linear contour models, on the connection of intersecting contours and on a boundary recall-based contour model selection algorithm. The different contour models address robustness against outliers for the detected contours and evasive curvature changes. Additionally, the information for the prediction is derived from already reconstructed pixels in neighboring blocks. The achieved coding efficiency is superior to those of related works from the literature. Compared with the closest related work, BD rate gains of 2.16% are achieved on average.

scholarly journals Inspeção Automática de Defeitos em Madeiras de Pinus usando Visão Computacional

2008 ◽  
Vol 15 (2) ◽  
pp. 203-218
Author(s):  
Luiz E. S. Oliveira ◽  
Paulo R. Cavalin ◽  
Alceu S. Britto Jr ◽  
Alessandro L. Koerich
Keyword(s):  
Neural Networks ◽  
Genetic Algorithms ◽  
Feature Selection ◽  
Defect Detection ◽  
Color Image ◽  
Support Vector ◽  
Grayscale Image ◽  
Selection Algorithm ◽  
Feature Selection Algorithm ◽  
Vector Machines

This paper addresses the issue of detecting defects in Pine wood using features extracted from grayscale images. The feature set proposed here is based on the concept of texture and it is computed from the co-occurrence matrices. The features provide measures of properties such as smoothness, coarseness, and regularity. Comparative experiments using a color image based feature set extracted from percentile histograms are carried to demonstrate the efficiency of the proposed feature set. Two different learning paradigms, neural networks and support vector machines, and a feature selection algorithm based on multi-objective genetic algorithms were considered in our experiments. The experimental results show that after feature selection, the grayscale image based feature set achieves very competitive performance for the problem of wood defect detection relative to the color image based features.

Sign in / Sign up

Export Citation Format

Share Document