تشخیص حملات ترافیک انتقالی شبکه با استفاده از منطق فازی مبتنی بر گروه مدل مخفی مارکوف

•   آرشیو : نسخه تابستان 1398
•   موضوع : بازیابی اطلاعات
• نویسنده/گان : سیده معصومه موسوی، سیده طاهره موسوی
•   کلید واژه : خلاصه سازی متن، تحلیل احساسات، الگوریتم بهینه سازی فاخته، ابزار ارزیابی ROUGE
•   Title : Text summarization by efficient algorithms
•   Abstract :
  With the rapid growth of information and data, finding appropriate and efficient information is of particular importance. The purpose of the summarizing the text is to provide a summary of the contents according to the information required by the user. Nowadays due to the abundance of documents in the Internet, most of which contains unnecessary information, emphasizes the importance of summarizing texts to reduce study time. The dramatic increase in this type of information reveals importance of existence of tools for automated evaluation of textual resources more than ever.
  Aautomatic summarization of texts is one of the solutions that reduces wasting of users' time. Summary is essentially the process of compressing a resource, so that the result contains important information about that resource. In other words, extracting important parts of one or more texts is called summarizing. Despite several techniques there is still a fundamental challenge to producing an optimal solution for summarizing texts. In this research, by using the cuckoo search algorithm and combining it with emotion analysis, the accuracy of the extracted summaries is increased and a way to solve the optimization problem in several fields is presented. The research process includes preprocessing, Gaussian distribution, fitness function and execution of text summarization algorithm.
  The preprocessing step includes sentence segmentation, tokenization or markup, deletion of the pause word, and sub-tasks including deletion of
  the root of the words. The proposed algorithm of this research is evaluated on 10 different documents collected from DUC2007 data set. DUC2007 data included a total of 45 items, each containing 25 documents. This dataset is an open source dataset. The ROUGE-1.5.5 package has been used to evaluate the summary text with evaluation criteria.
  Summary system in comparison with other summarizing systems in terms of ROUGE score in Recall, Precision and F-measure criteria shows better results.
•   مراجع :
  1- Rajabioun, Ramin. "Cuckoo optimization algorithm." Applied soft computing 11, no. 8 (2011): 5508-5518.
  
  2- Richmond, W. K. (1965). Teachers and machines: an introduction to the theory and practice of programmed learning. Collins.
  
  3- Shaikh, M. A. M., Prendinger, H., & Mitsuru, I. (2007, September). Assessing sentiment of text by semantic dependency and contextual valence analysis. In International conference on affective computing and intelligent interaction (pp. 191-202). Springer, Berlin, Heidelberg.
  
  4- Zheng, H., & Zhou, Y. (2012). A novel cuckoo search optimization algorithm based on Gauss distribution. Journal of Computational Information Systems, 8(10), 4193-4200.
  
  5- Rautray, R., & Balabantaray, R. C. (2018). An evolutionary framework for multi document summarization using Cuckoo search approach: MDSCSA. Applied computing and informatics, 14(2), 134-144.
  
  6- Sarkar, K. (2013). Automatic Single Document Text Summarization Using Key Concepts in Documents. JIPS, 9(4), 602-620.
  
  7- Nenkova, A. (2005). Automatic text summarization of newswire: Lessons learned from the document understanding conference
  
  8- Mosa, Mohamed Atef, Arshad Syed Anwar, and Alaa Hamouda. "A survey of multiple types of text summarization based on swarm intelligence optimization techniques." (2018).
  
  9- Rouane, Oussama, Hacene Belhadef, and Mustapha Bouakkaz. "Combine clustering and frequent itemsets mining to enhance biomedical text summarization." Expert Systems with Applications 135 (2019): 362-373.
•  صفحات : 58-67
•   دانلود فایل ( 578 KB )