Results

**11 - 17**of**17**### BioMedical Engineering OnLine ScanImage: Flexible software for operating laser scanning microscopes

"... Abstract Background: Laser scanning microscopy is a powerful tool for analyzing the structure and function of biological specimens. Although numerous commercial laser scanning microscopes exist, some of the more interesting and challenging applications demand custom design. A major impediment to cu ..."

Abstract
- Add to MetaCart

(Show Context)
Abstract Background: Laser scanning microscopy is a powerful tool for analyzing the structure and function of biological specimens. Although numerous commercial laser scanning microscopes exist, some of the more interesting and challenging applications demand custom design. A major impediment to custom design is the difficulty of building custom data acquisition hardware and writing the complex software required to run the laser scanning microscope.

### The Parallel Problems Server

"... Introduction We describe a novel architecture for a "linear algebra server" that operates in parallel on extremely large matrices. Matrices are created by the server and distributed across many machines. All operations therefore take place automatically in parallel. The server is extenisb ..."

Abstract
- Add to MetaCart

(Show Context)
Introduction We describe a novel architecture for a "linear algebra server" that operates in parallel on extremely large matrices. Matrices are created by the server and distributed across many machines. All operations therefore take place automatically in parallel. The server is extenisble and includes a general application interface to clients. This project is motivated by three observations. First, many widely-used algorithms in Computer Science can be realized as operations on matrices. Common techniques in smart text retrieval, object recognition and machine learning can all be described in this framework. Second, it is of utmost importance to be able to test new ideas quickly in an interactive setting. Finally, in order to understand the computational issues that arise with many algorithms it is necessary to test them on very large problems. There are commonly available solutions that address this general problem, but there are several difficulties. Interactive and easil

### SAR Images Speckle Reduction for Classification Using Wavelets on MultiMATLAB

, 1996

"... This work presents the results of the implementation on MultiMATLAB of a speckle reduction algorithm for SAR images using the wavelet transform. Speckle reduction is important for automatic target recognition and classification algorithms. The method is based on the application of a logarithmic tran ..."

Abstract
- Add to MetaCart

(Show Context)
This work presents the results of the implementation on MultiMATLAB of a speckle reduction algorithm for SAR images using the wavelet transform. Speckle reduction is important for automatic target recognition and classification algorithms. The method is based on the application of a logarithmic transformation to the image to convert the speckle noise into additive noise. Noise is reduced by applying soft thresholding on the wavelet coefficients. Daubechies wavelets are used to obtain the coefficients. The quality of the procedure is measured in terms of the standard deviation to mean ratio. The speedup obtained by using MultiMATLAB is presented. MultiMATLAB has proven to be a useful problem solving environment for parallel processing. 1 Introduction A synthetic aperture radar (SAR) is used to obtain high resolution images of the earth. It is used in areas such as Ecology, Hydrology, Oceanography, Geology, Interferometry, and Remote Sensing. Speckle is a problem caused by the coherent ...

### Collaborative Visualization using Facet Trees: Design and Implementation of a Prototype System

, 2000

"... The computational science and engineering process (build a model from real-ity, run the model, analyze the results for prediction and insight) is increasingly being applied to larger and more complex models by teams which are multidisci-plinary and geographically dispersed. The traditional solution ..."

Abstract
- Add to MetaCart

(Show Context)
The computational science and engineering process (build a model from real-ity, run the model, analyze the results for prediction and insight) is increasingly being applied to larger and more complex models by teams which are multidisci-plinary and geographically dispersed. The traditional solution is for participants to exchange information over the network (in long time scales) or by physically gathering around the model, which runs at a single powerful server. This thesis defines collaborative visualization as the ability for multiple par-ticipants in a team to create, preprocess, run, steer, postprocess, visualize, and analyze a model and its ’ associated data sets interactively and collaboratively. It states a set of criteria for a good collaborative solution to this problem. These criteria are: a human time scale to all operations, collaborative, networked in-teraction with the model, and high reuseability of existing code. Existing work has produced solutions to meet all criteria, but not all at once. A computation is viewed as a tree of values, where values encompass data,

### An Efficient Distributed Shared Memory Toolbox for MATLAB ∗

"... MATLAB, the most popular high-level language for scientific computing, has significant shortcomings when used for large-scale computationally intensive applications that require very high performance and/or significant amounts of memory. Many efforts such as ParaM, pMATLAB, Star-P, and Mathworks ’ D ..."

Abstract
- Add to MetaCart

(Show Context)
MATLAB, the most popular high-level language for scientific computing, has significant shortcomings when used for large-scale computationally intensive applications that require very high performance and/or significant amounts of memory. Many efforts such as ParaM, pMATLAB, Star-P, and Mathworks ’ Distributed Computing Toolbox (DCT) are currently underway to enable the convenient development of such applications directly in MATLAB. In this paper we describe GAMMA, an efficient distributed shared memory programming model for MATLAB built using the Global Arrays library suite. GAMMA defines a set of high-level abstractions for developing parallel MATLAB programs, and provides convenient support to build high-performance parallel libraries for high-level MAT-LAB models such as ParaM, Star-P and DCT. We discuss the inherent challenges for an efficient implementation of GAMMA, due to the conceptual discrepancies between the programming models being integrated. Experimental results on a Pentium cluster demonstrate the effectiveness of GAMMA. 1

### Menhir: An Environment for High Performance

"... Abstract. In this paper we present Menhir a compiler for generating sequential or parallel code from the Matlab language. The compiler has been designed in the context of using Matlab as a specification language. One of the major features of Menhir is its retargetability that allows generating paral ..."

Abstract
- Add to MetaCart

(Show Context)
Abstract. In this paper we present Menhir a compiler for generating sequential or parallel code from the Matlab language. The compiler has been designed in the context of using Matlab as a specification language. One of the major features of Menhir is its retargetability that allows generating parallel and sequential C or Fortran code. We present the compilation process and the target system description for Menhir. Preliminary performances are given and compared with MCC, the MathWorks Matlab compiler. 1