Datamining Optimization of Steganalysis by means of Neural Network

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F70883521%3A28140%2F10%3A63508853" target="_blank" >RIV/70883521:28140/10:63508853 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Datamining Optimization of Steganalysis by means of Neural Network

Popis výsledku v původním jazyce

In the view of global data growth in all industry fields, emphasis should be put on the quality and the information content as well as on the data optimization of processes which work with this data. This paper deals with a possibility to optimize by means of data mining a process of steganalysis solved by neural networks. One of the basic methods of data mining classification can reduce a dimension of data which is performed by NN later. To obtain a datamining model algorithm J48 was used and also several testing methods which classify instances with 64 attributes into two classes. For comparison with the originally published neural networks model, neural networks were used again to verify the data mining model. Conclusion is focused on holding an accuracy of classification and prediction of the model with additional refers to time savings caused by reduction of used data.

Název v anglickém jazyce

Datamining Optimization of Steganalysis by means of Neural Network

Popis výsledku anglicky

In the view of global data growth in all industry fields, emphasis should be put on the quality and the information content as well as on the data optimization of processes which work with this data. This paper deals with a possibility to optimize by means of data mining a process of steganalysis solved by neural networks. One of the basic methods of data mining classification can reduce a dimension of data which is performed by NN later. To obtain a datamining model algorithm J48 was used and also several testing methods which classify instances with 64 attributes into two classes. For comparison with the originally published neural networks model, neural networks were used again to verify the data mining model. Conclusion is focused on holding an accuracy of classification and prediction of the model with additional refers to time savings caused by reduction of used data.

Druh

D - Stať ve sborníku

CEP obor

BD - Teorie informace

OECD FORD obor

—

Projekt

<a href="/cs/project/GA102%2F09%2F1680" target="_blank" >GA102/09/1680: Evoluční návrh řídicích algoritmů</a><br>

Návaznosti

Z - Vyzkumny zamer (s odkazem do CEZ)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2010

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Internet, bezpečnost a konkurenceschopnost organizací. Řízení procesů a využití moderních teerminálových technologií

ISBN

978-83-61645-16-0

ISSN

—

e-ISSN

—

Počet stran výsledku

6

Strana od-do

—

Název nakladatele

Univerzita Tomáše Bati ve Zlíně, Fakulta aplikované informatiky

Místo vydání

Zlín

Místo konání akce

Zlín

Datum konání akce

1. 1. 2010

Typ akce podle státní příslušnosti

EUR - Evropská akce

Kód UT WoS článku

—