The rapid growth of scientific literature calls for automatic and efficient ways to facilitate extracting experimental data on protein phosphorylation. Such information is of great value for biologists in studying cellular processes and diseases such as cancer and diabetes. Existing approaches like RLIMS-P are mainly rule based. The performance lays much reliance on the completeness of rules. We propose an SVM-based system known as MinePhos which outperforms RLIMS-P in both precision and recall of information extraction when tested on a set of articles randomly chosen from PubMed.
A Link Level Load-Aware Queue Scheduling algorithm (LLLAQS) on MAC layer is proposed in this paper in order to suppress the data transmission on congested links and balance the load in the wireless mesh networks. The algorithm not only takes the load on the congested node into consideration but also differentiates the congested links and non-congested links. By scheduling the traffic on the non-congested or lightcongested links for a congested node, the proposed algorithm can balance the traffic load more smartly than the traditional queue scheduling schemes. The simulation results in NS2 show that our queue scheduling algorithm outperforms other existing queue scheduling algorithms in terms of the network throughput, the average delay, and the drop ratio.
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.