In this paper, to study rumor spreading, we propose a novel susceptible-infected-removed (SIR) model by introducing the trust mechanism. We derive mean-field equations that describe the dynamics of the SIR model on homogeneous networks and inhomogeneous networks. Then a steady-state analysis is conducted to investigate the critical threshold and the final size of the rumor spreading. We show that the introduction of trust mechanism reduces the final rumor size and the velocity of rumor spreading, but increases the critical thresholds on both networks. Moreover, the trust mechanism not only greatly reduces the maximum rumor influence, but also postpones the rumor terminal time, which provides us with more time to take measures to control the rumor spreading. The theoretical results are confirmed by sufficient numerical simulations.
In this paper, an extended version of standard susceptible-infected (SI) model is proposed to consider the influence of a medium access control mechanism on virus spreading in wireless sensor networks. Theoretical analysis shows that the medium access control mechanism obviously reduces the density of infected nodes in the networks, which has been ignored in previous studies. It is also found that by increasing the network node density or node communication radius greatly increases the number of infected nodes. The theoretical results are confirmed by numerical simulations.
Abstract. Multi-class classification is an important and on-going research subject in machine learning and data mining. In this paper, we propose a new support vector algorithm, called OC-K-SVM, for multi-class classification based on one-class SVM. For k-class problem, this method constructs k classifiers, where each one is trained on data from one class. OC-K-SVM has parameters that enable us to control the number of support vectors and margin errors effectively, which is helpful in improving the accuracy of each classifier. We give some theoretical results concerning the significance of the parameters and show the robustness of classifiers. In addition, we have examined the proposed algorithm on several benchmark data sets, and our preliminary experiments confirm our theoretical conclusions.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.