Please use this identifier to cite or link to this item:
http://ea.donntu.edu.ua:8080/jspui/handle/123456789/7337
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Шелестов, А.Ю. | - |
dc.contributor.author | Скакун, С.В. | - |
dc.contributor.author | Куссуль, О.М. | - |
dc.date.accessioned | 2012-03-07T07:02:05Z | - |
dc.date.available | 2012-03-07T07:02:05Z | - |
dc.date.issued | 2008-07-04 | - |
dc.identifier.citation | Шелестов А.Ю., Скакун С.В., Куссуль О.М. Агентный подход к реализации модели поведения пользователей Grid-систем// Наукові праці Донецького національного технічного університету, серія «Інформатика, кібернетика та обчислювальна техніка»,вып. 9 (132), Донецк, ДонНТУ, 2008. – С.8-14. | en_US |
dc.identifier.issn | 1996-1588 | - |
dc.identifier.uri | http://ea.donntu.edu.ua/handle/123456789/7337 | - |
dc.description.abstract | We propose an agent approach to the implementation of model of users behavior in Grid systems. Proposed model is based on the analysis of statistical data about jobs that were completed by the user in Grid system. In order to distinguish normal and abnormal user’s behavior we use feed-forwards neural networks. We verified the proposed approach on data that were collected by GridICE monitoring system in GILDA-EGEE. The results of experiments showed that our model was able to distinguish abnormal user’s behavior in 90%. | en_US |
dc.publisher | Донецкий национальный технический университет | en_US |
dc.subject | Grid-системы | en_US |
dc.subject | модели поведения | en_US |
dc.subject | агенты | en_US |
dc.title | Агентный подход к реализации модели поведения пользователей Grid-систем | en_US |
dc.title.alternative | Agent approach to implementation of model of users behavior in Grid systems | en_US |
dc.type | Article | en_US |
Appears in Collections: | Випуск 9 (132) |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
08saypgs.pdf | 207,04 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.