Abstract: As information overload grows day by day, systems that can automatically summarize documents becomes increasingly studied and used. In this paper we have given a novel statistical approach for text summarization of a single source document by sentence extraction using font features. We rank each sentence in the document by assigning a weight value to each word of the sentence and a boost factor is also added to those terms which appear in bold, italic or underlined or any combination of these features. In this paper we improved our result in comparison to our previous paper: [14]

• Publication Date: 23-Jun-2012
• DOI: 219
• Views: 0
• Downloads: 0

Abstract: This research proposes a novel three dimensionalcellular automata (3-D CA) scheme for pseudo random number generationwhich is highly secure than the two dimensional cellular automata (2-D CA). It removes security and boundary problems with the 2-D CA. The use of 1-D CA was very common in late 80s which was then improved with 2-D CA. Research literature shows that 2-D CA is suffering from security and boundary problems.The proposed scheme is implemented usingC++ to test its performance against others similar systems using DIHARD and ENT standard test suites. Simulations are performed on 200 sets for both DIHARD and ENT. Simulation results show that the proposed scheme performs better than that of the older versionespecially in termsof security and boundary. In DIEHARD and ENT test the proposed scheme produces better success rate than older versions.

• Publication Date: 23-Jun-2012
• DOI: 978-981-07-2683-6
• Views: 0
• Downloads: 0