Results - Details
Search command : Author="Παπουτσίδης"
And Author="Ευάγγελος"
Current Record: 1 of 1
|
|
| Identifier |
uch.csd.msc//2006papoutsides |
| Title |
Σχεδίαση και ανάπτυξη μίας biomedical GRID υποδομής για την εφαρμογή αλγορίθμων εξόρυξης δεδομένων υψηλών επιδόσεων και λειτουργιών εξόρυξης γνώσης |
| Alternative Title |
A biomedical GRID infrastructure to enable high performing data mining and knowledge extraction operations |
| Creator |
Papoutsides, Evaggelos
|
| Abstract |
The breadth and depth of clinical and genetic information already available in the research community at large, present an enormous opportunity for improving our ability to reduce mortality, improve therapies and meet the demanding needs of individualized healthcare. The lack of a common infrastructure has prevented the clinical and research institutions from being able to mine and analyze disparate data sources. Research facilities have been working with islands of isolated data and informatics tools. Knowledge discovery in large data repositories can find interesting hidden patterns and trends representing them in an understandable way. But data mining is both a data-intensive and compute-intensive task. In real world applications sequential algorithms of data mining and data exploration are often unsuitable for datasets with enormous size, high-dimensionality and complex data structure. Grid computing promises unprecedented opportunities for unlimited computing and storage resources. The grid concept is coordinated resource sharing and problem solving in dynamic, multi-institutional virtual organizations. In the case of knowledge discovery we whish to explore how grid technology is able to provide an infrastructure to access information from different data sources and the computational power to enable high-performing data mining techniques. In such a context, this thesis represents an exploratory activity in studying various open issues related to the utilization of Grid technologies and Service Oriented Computing for the resolution of critical biomedical informatics challenges. As part of the work presented in this thesis, we have designed and developed a small grid environment; its users have the ability to perform the following actions: a) Access and retrieve data from clinical information systems, b) Query for (discover) the computational resources and data mining techniques (services) available in the grid. c) Execute a parallel implementation of Association Rules Mining (ARM) algorithm. The architecture of this environment was implemented on top of Globus Toolkit 4, using OGSA-DAI for access to data sources. The resources of the grid are governed by the TORQUE resource manager and mpiJava was used for the implementation of the parallel ARM algorithm.
|
| Issue date |
2006-04-01 |
| Date available |
2006-07-19 |
| Collection
|
School/Department--School of Sciences and Engineering--Department of Computer Science--Post-graduate theses
|
|
|
Type of Work--Post-graduate theses
|
| Permanent Link |
https://elocus.lib.uoc.gr//dlib/9/5/3/metadata-dlib-2006papoutsides.tkl
|
| Views |
355 |
Search
