Filters








7,572 Hits in 5.5 sec

Automatic change detection in multimodal serial MRI: application to multiple sclerosis lesion evolution

Marcel Bosc, Fabrice Heitz, Jean-Paul Armspach, Izzie Namer, Daniel Gounot, Lucien Rumbach
2003 NeuroImage  
The automatic analysis of subtle changes between MRI scans is an important tool for assessing disease evolution over time. Manual labeling of evolutions in 3D data sets is tedious and error prone.  ...  The method was assessed using receiver operating characteristics (ROC) analysis, and validated in a protocol involving two neurologists.  ...  Acknowledgments This research was supported by the Ligue Française Contre la Sclérose en Plaques, and the CNRS (multilaboratory project IRMC).  ... 
doi:10.1016/s1053-8119(03)00406-3 pmid:14568441 fatcat:lejapkhvdjcpzcidn7zxghbbnm

Hierarchical design of artificial proteins and complexes toward synthetic structural biology

Ryoichi Arai
2017 Biophysical Reviews  
Topics covered include combinatorial and protein-engineering approaches for directed evolution of artificial binding proteins and membrane proteins, binary code strategy for structural and functional de  ...  In this paper, I review recent remarkable progress of an array of approaches for hierarchical design of artificial proteins and complexes that signpost the path forward toward synthetic structural biology  ...  This article is part of a Special Issue on 'Biomolecules to Bionanomachines -Fumio Arisaka 70th Birthday' edited by Damien Hall, Junichi Takagi and Haruki Nakamura.  ... 
doi:10.1007/s12551-017-0376-1 pmid:29243094 pmcid:PMC5899735 fatcat:k724ocy7knaxtjbklk5dwmfedu

EVOLUTION OF FRACTAL SHAPES FOR ARTISTS AND DESIGNERS

EVELYNE LUTTON
2006 International journal on artificial intelligence tools  
We analyse in this paper the way randomness is considered and used in ArtiE-Fract.  ...  It seems obvious for the people who use ArtiE-Fract that this system is a versatile tool for creation, especially regarding the specific use of controlled random components.  ...  Iterated Function Systems (IFS) theory is a convenient mathematical tool to define "fractal" images, and has been used with success in many "fractal" image compression applications.  ... 
doi:10.1142/s0218213006002850 fatcat:ogix3gt6cvgg3gay4ehj24qhvy

Affine-null metric formulation of Einstein's equations

J. Winicour
2013 Physical Review D  
The details are presented of a new evolution algorithm for the characteristic initial-boundary value problem based upon an affine parameter rather than the areal radial coordinate used in the Bondi-Sachs  ...  relativistic astrophysical systems.  ...  The research was supported by NSF grants PHY-0854623 and PHY-1201276 to the University of Pittsburgh.  ... 
doi:10.1103/physrevd.87.124027 fatcat:polrjwlhyjcnnjruzxldrpskca

Mathematical models in microbial systems biology

Jörg Stelling
2004 Current Opinion in Microbiology  
Guided by common themes such as modularity, optimality and robustness, iterative model development promises further progress towards a system-level understanding. Addresses  ...  Recently, model-based analysis of microorganisms has begun, for instance, to reveal functional modules in metabolic and transcriptional networks, to predict cellular behavior from genome-scale physicochemical  ...  Acknowledgements I thank Katja Bettenbrock and Uwe Sauer for helpful suggestions on the manuscript, and Bernhard O Palsson for sharing data before publication.  ... 
doi:10.1016/j.mib.2004.08.004 pmid:15451507 fatcat:zuqu6l24g5hxtmsaqmp7uhg3du

Data mining–based hierarchical cooperative coevolutionary algorithm for TSK-type neuro-fuzzy networks design

Chi-Yao Hsu, Sheng-Fuu Lin, Jyun-Wei Chang
2012 Neural computing & applications (Print)  
The proposed DMHCCA consists of two-level evolutions: the neurolevel evolution (NULE) and the network-level evolution (NWLE).  ...  Simulation results using DMHCCA are reported and compared with other existing models.  ...  47.36 228.59 158.66 Table 5 5 Range of 3D rigid transformation parameters 3D rigid transformation parameter The range of affine transformation parameter / (degree), for roll [-10, 10] u (  ... 
doi:10.1007/s00521-012-0943-0 fatcat:7umhc7hhpjb5bmp2nycztcn2hi

Multi-Reference Shape Priors for Active Contours

Alban Foulonneau, Pierre Charbonnier, Fabrice Heitz
2008 International Journal of Computer Vision  
Examples illustrate the ability of the model to deal with large affine deformation and to take into account a set of reference shapes of different topologies. A. Foulonneau ( ) · P.  ...  We introduce our prior into a two-class segmentation functional, showing its benefits on segmentation results in presence of severe occlusions and clutter.  ...  the number of iterations using (40), for this stage.  ... 
doi:10.1007/s11263-008-0163-3 fatcat:adjverf6l5csfhyvzv3c3z33ze

Alignment using genetic programming with causal trees for identification of protein functions

Chun-Min Hung, Yueh-Min Huang, Ming-Shi Chang
2006 Nonlinear Analysis  
A hybrid evolutionary model is used to propose a hierarchical homology of protein sequences to identify protein functions systematically.  ...  This work presents a decision model that can minimize the cost of making a decision for predicting protein functions using the hierarchical homologies.  ...  Therefore, a distinctive characteristic of the TPS can always decompose a geometrical transformation into a global affine transformation and a local non-affine warping component.  ... 
doi:10.1016/j.na.2005.09.048 pmid:32288048 pmcid:PMC7117053 fatcat:czde4tve7bgxbfkdqgb4zt6nqe

CLIP-CLOP: CLIP-Guided Collage and Photomontage [article]

Piotr Mirowski, Dylan Banarse, Mateusz Malinowski, Simon Osindero, Chrisantha Fernando
2022 arXiv   pre-print
, thereby allowing humans to reclaim some control of the process and achieve greater creative freedom.  ...  The unabated mystique of large-scale neural networks, such as the CLIP dual image-and-text encoder, popularized automatically generated art.  ...  anonymous reviewers for helpful discussions and suggestions.  ... 
arXiv:2205.03146v2 fatcat:r7ljanbg3zhifjuuimhorcxyai

Chaotic Time Series Prediction Using Immune Optimization Theory

Yuanquan Shi, Xiaojie Liu, Tao Li, Xiaoning Peng, Wen Chen, Ruirui Zhang, Yanming Fu
2010 International Journal of Computational Intelligence Systems  
In PIOT, the concepts and formal definitions of antigen, antibody and affinity being used for time series prediction are given, and the mathematical models of immune optimization operators being used for  ...  To demonstrate the effectiveness of PIOT, the three typical chaotic nonlinear time series are generated by nonlinear dynamics systems that are Lorenz, Mackey-Glass and Henon, respectively, and are used  ...  function, Fig. 4 (a) that its maximum out-degree equals two; according to the structure characteristics of antibody and the hierarchical traverse method of tree 29 , a antibody encoding consisting of  ... 
doi:10.2991/ijcis.2010.3.s1.4 fatcat:qgrjr5xfozbdbm5wxgq4oveik4

Chaotic Time Series Prediction Using Immune Optimization Theory

Yuanquan Shi, Xiaojie Liu, Tao Li, Xiaoning Peng, Wen Chen, Ruirui Zhang, Yanming Fu
2010 International Journal of Computational Intelligence Systems  
In PIOT, the concepts and formal definitions of antigen, antibody and affinity being used for time series prediction are given, and the mathematical models of immune optimization operators being used for  ...  To demonstrate the effectiveness of PIOT, the three typical chaotic nonlinear time series are generated by nonlinear dynamics systems that are Lorenz, Mackey-Glass and Henon, respectively, and are used  ...  function, Fig. 4 (a) that its maximum out-degree equals two; according to the structure characteristics of antibody and the hierarchical traverse method of tree 29 , a antibody encoding consisting of  ... 
doi:10.1080/18756891.2010.9727752 fatcat:zwjs3onrinfafoacmbpmpzhmc4

Segmentation-based video coding system allowing the manipulation of objects

P. Salembier, F. Marques, M. Pardas, J.R. Morros, I. Corset, S. Jeannin, L. Bouchard, F. Meyer, B. Marcotegui
1997 IEEE transactions on circuits and systems for video technology (Print)  
The coding strategy relies on a joint optimization in the rate-distortion sense of the partition definition and of the coding techniques to be used within each region.  ...  The analysis defines the time evolution of the partition, as well as the elimination or the appearance of regions that are homogeneous either spatially or in motion.  ...  It results in a set of six parameters defining an affine transformation for each region. Then, a region adjacency graph (RAG) is constructed.  ... 
doi:10.1109/76.554418 fatcat:dtgsjocvqnep7i6xxo76ueejga

Multi-Functioning in Virtual Monitoring of Thin-Walled Bridges

Alexander Tesár
2013 Selected Scientific Papers: Journal of Civil Engineering  
The approach enables multiple functions in virtual monitoring of bridges made of integrated thin-walled members with their hierarchical configuration.  ...  Theoretical, numerical and experimental in situ assessment of the problem is presented. Some results of structural application are submitted.  ...  Acknowledgements The authors are indebted to Slovak Grant Agencies VEGA and APVV for supporting and sponsoring the scientific activities reported.  ... 
doi:10.2478/sspjce-2013-0008 fatcat:la4dcqnwdnbhvgkbcz74cag244

Computational Intelligence in Remote Sensing Image Registration: A survey

Yue Wu, Jun-Wei Liu, Chen-Zhuo Zhu, Zhuang-Fei Bai, Qi-Guang Miao, Wen-Ping Ma, Mao-Guo Gong
2020 International Journal of Automation and Computing  
In recent years, computational intelligence has been widely used in many fields and achieved remarkable performance.  ...  In the part of remote sensing image registration based on evolutionary calculation, the principles of evolutionary algorithms and swarm intelligence algorithms are elaborated and their application in remote  ...  The mapping function learning phase mainly learns the mapping function by using unregistered images and their affine transformed images, and the registration phase uses the above-mentioned trained DNN  ... 
doi:10.1007/s11633-020-1248-x fatcat:2adppeabnvhmzdylnl6udodluy

Quasi-Bayes linear regression for sequential learning of hidden Markov models

Jen-Tzung Chien
2002 IEEE Transactions on Speech and Audio Processing  
Experiments on supervised and unsupervised speaker adaptation demonstrate that the sequential adaptation using QBLR is efficient and asymptotical to batch learning using MLLR and MAPLR in recognition performance  ...  Our attempt is to sequentially improve speaker-independent speech recognition system to handle the nonstationary environments via the linear regression adaptation of HMMs.  ...  In [25] , an online Bayesian learning of affine transformation parameters was proposed for speaker adaptation.  ... 
doi:10.1109/tsa.2002.800555 fatcat:hlsjqubxfjdqdaobwufb2odcsy
« Previous Showing results 1 — 15 out of 7,572 results