Filters








661 Hits in 4.0 sec

A Hybrid Approach of Using Wavelets and Fuzzy Clustering for Classifying Multispectral Florescence In Situ Hybridization Images

Yu-Ping Wang, Ashok Kumar Dandpat
2006 International Journal of Biomedical Imaging  
In the paper we introduce a novel approach to improve the accuracy of pixel-wise classification. The approach is based on the combination of fuzzy clustering and wavelet normalization.  ...  Two wavelet-based algorithms are used to reduce redundancies and to correct misalignments between multichannel FISH images.  ...  Fuzzy-clustering-based classification Clustering is a technique to divide a multidimensional data set into clusters or classes of similar attributes.  ... 
doi:10.1155/ijbi/2006/54532 pmid:23165039 pmcid:PMC2324027 fatcat:5dtb7ycrqje3hdebso43vdmu6u

Load Forecasting Using Hybrid Models

Madasu Hanmandlu, Bhavesh Kumar Chauhan
2011 IEEE Transactions on Power Systems  
The number of fuzzy rules is found from a fuzzy curve corresponding to each input-output by counting the total number of peaks and troughs in the curve.  ...  This paper presents two hybrid neural networks derived from fuzzy neural networks (FNN): wavelet fuzzy neural network (WFNN) using the fuzzified wavelet features as the inputs to FNN and fuzzy neural network  ...  ACKNOWLEDGMENT The authors would like to thank Northern Region Load Dispatch Centre (NRLDC), New Delhi, India, and Indian Meteorological Department (IMD), Delhi Centre, India, for providing load data and  ... 
doi:10.1109/tpwrs.2010.2048585 fatcat:rd73ysyuvngktfpnnm5e3nweaa

Multiresolution fuzzy clustering of functional MRI data

M. Buerki, K. O. Lovblad, H. Oswald, A. C. Nirkko, P. Stein, C. Kiefer, G. Schroth
2003 Neuroradiology  
One of the most promising approaches is the fuzzy clustering algorithm (FCA), whose potential to detect activation patterns has already been demonstrated.  ...  Recent developments in the analysis of functional MRI data reveal a shift from hypothesis-driven statistical tests to unsupervised strategies.  ...  The multiresolution technique replaces the necessary random initialization of the FCA by a clustering of lowresolution copies of the dataset.  ... 
doi:10.1007/s00234-003-1026-9 pmid:12942214 fatcat:tlfrcg2h75auvj3qfg3adx67fy

Normalization of multicolor fluorescence in situ hybridization (M-FISH) images for improving color karyotyping

Yu-Ping Wang, Kenneth R. Castleman
2005 Cytometry Part A  
To evaluate the performance improvement brought about by these data normal-ization approaches, we used the downstream pixel classification accuracy as a measurement.  ...  In particular, we developed an automated registration technique to correct misalignment across the different fluor images (caused by chromatic aberration and other factors).  ...  Vibeesh Bose and Hyohoon Choi also contributed to software development. We thank P. Rogan and J. Knoll at the Genetics Laboratory of the Children's Mercy Hospital for fruitful discussions.  ... 
doi:10.1002/cyto.a.20116 pmid:15729736 fatcat:y3ngzpxnmjfgfihswoem4uz44i

Conferences & workshops: International conference on computer design '98

Daniel Pryor, Andreas Kuehlmann, Trevor J. Smedley, David R. Kincaid, Anne C. Elster
1998 IEEE Computational Science & Engineering  
to increase processing speed and memory density.'  ...  Developments in parallel computing are now allowing atomistic simulation using multiresolution algorithms, such as fast multipole methods.  ...  Multiple space-time scales To reconcile length scales, our multiresolution molecular dynamics alg~rithm,~ or MRMD, uses a fast multipole method3 that clusters atoms to form a higher abstraction.  ... 
doi:10.1109/99.735897 fatcat:tuiuihcoqfgybb47geoio5mlc4

DEEP LEARNING APPROACH FOR DENOISING CONTOURS AND CLASSIFICATION OF AUTOMATIC HEALTH TISSUE IMAGE WAVELETS VIA CNN

2021 International Journal of Biology Pharmacy and Allied Sciences  
They then use a multilayer neuronal  ...  Using five MRI face imaging files, we firstly employ post approaches like polynomial conducting to recover the precise outlines of distinct components including the cranium, cerebral liquid (CSF), grey  ...  We then employed technique. Curvelet domains remove noise simultaneous computation to speed up the  ... 
doi:10.31032/ijbpas/2021/10.11.1088 fatcat:3l264omt35arxeom4etdkhih5q

Online Learning of Activities from Video

Luis Patino, Francois Bremond, Monique Thonnat
2012 2012 IEEE Ninth International Conference on Advanced Video and Signal-Based Surveillance  
For the analysis of the trajectory, a multiresolution analysis is set such that a trajectory is segmented into a series of tracklets based on changing speed points thus allowing differentiating when people  ...  A clustering algorithm based on the transitive closure calculation of the fuzzy relations allows building the final structure of the scene.  ...  In addition to activity clustering, in order to enable dynamic adaptation to unexpected or newly observed data, we need a system able to learn the activity clusters on line.  ... 
doi:10.1109/avss.2012.50 dblp:conf/avss/PatinoBT12 fatcat:3w54xqjfunf57axxs7copneaa4

A wavelet-based coarse-to-fine image matching scheme in a parallel virtual machine environment

J. You, P. Bhattacharya
2000 IEEE Transactions on Image Processing  
The proposed image matching algorithms were implemented on a network of workstation clusters using parallel virtual machine (PVM).  ...  wavelet transform, 2) adaptive thresholding selection based on compactness measures of fuzzy sets in image feature space, and 3) a guided searching strategy for the best matching from coarse level to  ...  ACKNOWLEDGMENT The authors would like to thank an anonymous reviewer for the constructive comments made. The authors would like to thank M. Hitchings and S.  ... 
doi:10.1109/83.862635 pmid:18262992 fatcat:xkyvc6rn2vffvebahqcvqnxmny

State of the Art in Ray Tracing Animated Scenes

Ingo Wald, William R. Mark, Johannes Günther, Solomon Boulos, Thiago Ize, Warren Hunt, Steven G. Parker, Peter Shirley
2009 Computer graphics forum (Print)  
Consequently, there is so far no approach that is best in all cases, and determining the best technique for a particular problem can be a challenge.  ...  Ray tracing has long been a method of choice for off-line rendering, but traditionally was too slow for interactive use.  ...  Acknowledgments We are grateful to a large number of people that have provided feedback and/or insight into their respective papers and systems.  ... 
doi:10.1111/j.1467-8659.2008.01313.x fatcat:ezggrka36feb5bamnbljpvxzle

State of the Art in Ray Tracing Animated Scenes [article]

Ingo Wald, William R. Mark, Johannes Günther, Solomon Boulos, Thiago Ize, Warren Hunt, Steven G. Parker, Peter Shirley
2007 Eurographics State of the Art Reports  
Consequently, there is so far no approach that is best in all cases, and determining the best technique for a particular problem can be a challenge.  ...  Ray tracing has long been a method of choice for off-line rendering, but traditionally was too slow for interactive use.  ...  Acknowledgments We are grateful to a large number of people that have provided feedback and/or insight into their respective papers and systems.  ... 
doi:10.2312/egst.20071056 fatcat:5ywddhbt2vgqxjufltfqzau6va

3D flow features visualization via fuzzy clustering

Huaxun Xu, Zhi-Quan Cheng, Ralph R. Martin, Sikun Li
2011 The Visual Computer  
A fuzzy c-means-like clustering algorithm is used to evaluate the importance of each voxel.  ...  In this paper, we use a novel framework in which fuzzy sets are used to determine flow features: Fuzzy relationships assess structural properties of features.  ...  We now further discuss GPU implementation of the fuzzy membership computation, and explain how a multiresolution technique is used to process and visualize the feature regions with greater detail than  ... 
doi:10.1007/s00371-011-0577-8 fatcat:5ssjwjd3sjcplg7tcn32y7gbvq

Mammographic Segmentation Using WaveCluster

Michael Barnathan
2012 Algorithms  
These results highlight the potential of WaveCluster as a useful addition to the mammographic segmentation repertoire.  ...  Our approach was able to segment the breast profile from all 150 images, leaving minor residual noise adjacent to the breast in three.  ...  approaches used in the literature include fuzzy c-means [2, 3] and watershed segmentation [5] .  ... 
doi:10.3390/a5030318 fatcat:qkqp6z7bn5c2xhyjog6o6jmh2m

Unsupervised Activity Extraction on Long-Term Video Recordings Employing Soft Computing Relations [chapter]

Luis Patino, Murray Evans, James Ferryman, François Bremond, Monique Thonnat
2011 Lecture Notes in Computer Science  
In this work we present a novel approach for activity extraction and knowledge discovery from video employing fuzzy relations.  ...  A clustering algorithm based on the transitive closure calculation of the fuzzy relations allows finding spatio-temporal patterns of activity.  ...  The technique is unsupervised and is based on the use of fuzzy relations to model Spatial and temporal properties from detected mobile objects.  ... 
doi:10.1007/978-3-642-23968-7_10 fatcat:qwrscfspmvcwfkni4xihinvdhy

Multiresolution edge detection using enhanced fuzzy c-means clustering for ultrasound image speckle reduction

Stavros Tsantis, Stavros Spiliopoulos, Aikaterini Skouroliakou, Dimitrios Karnabatidis, John D. Hazle, George C. Kagadis
2014 Medical Physics (Lancaster)  
than the total coefficient number, which in turn also speeded up the processing time.  ...  FCM clustering The FCM algorithm is an iterative clustering algorithm in which each data point is assigned to a cluster to a degree specified by a fuzzy membership grade.  ...  US image characteristics in all three anatomic structures and could thus assist in the daily clinical evaluation process.  ... 
doi:10.1118/1.4883815 pmid:24989413 fatcat:gvnkxbgapbgznezbi5cvyk7wre

Speeding up the EM algorithm for mixture model-based segmentation of magnetic resonance images

Shu-Kay Ng, Geoffrey J. McLachlan
2004 Pattern Recognition  
In this paper, we show how this modiÿed EM algorithm can be speeded up further by adopting a multiresolution kd-tree structure in performing the E-step.  ...  Mixture models implemented via the expectation-maximization (EM) algorithm are being increasingly used in a wide range of problems in pattern recognition such as image segmentation.  ...  Acknowledgements The authors wish to thanks the Editor and the referee for helpful comments on the paper. The authors wish to thanks Dr. Andrew Moore and Mr.  ... 
doi:10.1016/j.patcog.2004.02.012 fatcat:vyxdklfqyrah7fd7kquxwxlq2m
« Previous Showing results 1 — 15 out of 661 results