Suchergebnisse

In previous election of a country for its democratic elections in which social media was targeted as a way to convince the social media users to attract their votes, an analysis of BigData on these elections tweets is performed to gather some interesting information. The parties which have been active on social media during elections were identified through hashtag and keyword frequency of occurrences; the top twitter users who influenced the public in election's were identified by identifying the most re tweeted tweets and finally a comprehensive sentiment analysis were done on the big data set to check "Election trolling" where opposition parties insult and attack each other to get an idea of the political maturity of a country twitter users, with a high percentage negative sentiments it was deduced that people of that country lack political maturity.

Intrusion Detection System (IDS) is a very important research area in the field of information and network security. In this paper, we discuss, analyze and evaluate some of the classifiers based on Artificial Intelligence (AI) which are used to detect and classify networks attacks for an intrusion detection system. We will use WEKA (A machine learning tool) software for testing and evaluating the performance of the classifiers on a well-known famous IDS (Intrusion Detection Systems) dataset "NSL-KDD" dataset. The NSL-KDD dataset contains sufficient amount of network attacks and it was developed in a military network by MIT Lincoln Labs. Once we got the individual results of all the classifiers then we will compare their performance on the basis of some performance parameters. We also used discretize filter to enhance the overall performance of the classifiers