No abstract

Abstract. The rapid growth of Internet-based applications pushes broadband satellite networks to carry on IP traffic. In previously proposed connectionless routing schemes in satellite networks, the metrics used to calculate the paths do not reflect the total delay a packet may experience. In this paper, a new Satellite Grouping and Routing Protocol (SGRP) is developed. In each snapshot period, SGRP divides Low Earth Orbit (LEO) satellites into groups according to the footprint area of the Medium Earth Orbit (MEO) satellites. Based on the delay reports sent by LEO satellites, MEO satellite managers compute the minimum-delay paths for their LEO members. Since the signaling traffic is physically separated from the data traffic, link congestion does not affect the responsiveness of delay reporting and routing table calculation. The snapshot and group formation methods as well as fast reacting mechanisms to address link congestion and satellite failures are described in detail. The performance of SGRP is evaluated through simulations and analysis.

No abstract

No abstract

Twitter Spam has become a critical problem nowadays. Recent works focus on applying machine learning techniques for Twitter spam detection, which make use of the statistical features of tweets. In our labelled tweets dataset, however, we observe that the statistical properties of spam tweets vary over time, and thus the performance of existing machine learning based classifiers decreases. This issue is referred to as "Twitter Spam Drift". In order to tackle this problem, we firstly carry out a deep analysis on the statistical features of one million spam tweets and one million non-spam tweets, and then propose a novel Lfun scheme. The proposed scheme can discover "changed" spam tweets from unlabelled tweets and incorporate them into classifier's training process. A number of experiments are performed to evaluate the proposed scheme. The results show that our proposed Lfun scheme can significantly improve the spam detection accuracy in real-world scenarios.