Abstract-This paper studies the problem of automatic detection of false rumors on Sina Weibo, the popular Chinese microblogging social network. Traditional feature-based approaches extract features from the false rumor message, its author, as well as the statistics of its responses to form a flat feature vector. This ignores the propagation structure of the messages and has not achieved very good results. We propose a graph-kernel based hybrid SVM classifier which captures the high-order propagation patterns in addition to semantic features such as topics and sentiments. The new model achieves a classification accuracy of 91.3% on randomly selected Weibo dataset, significantly higher than state-of-the-art approaches. Moreover, our approach can be applied at the early stage of rumor propagation and is 88% confident in detecting an average false rumor just 24 hours after the initial broadcast.
Background: Deep brain stimulation of the subthalamic nucleus (STN-DBS) has been reported to be effective for camptocormia in Parkinson’s disease (PD). However, the association between clinical effectiveness and the stimulated volumes or structural connectivity remains unexplored. Objective: To investigate the effectiveness of STN-DBS for treating camptocormia in PD and its association with volumes of tissue activated (VTA) and structural connectivity. Methods: We reviewed video recordings of patients who had undergone STN-DBS. The total and upper camptocormia (TCC and UCC) angles were measured to quantify changes in camptocormia. The Movement Disorders Society Unified Parkinson’s Disease Rating Scale III (MDS-UPDRS III) was used to assess motor symptoms. Pre- and postoperative brain images were collected for modeling volume of VTA and structural connectivity using Lead-DBS software. Results: Participants included 36 patients with PD (8 with TCC-camptocormia and 2 with UCC-camptocormia) treated with bilateral STN-DBS. After surgery, patients showed a significant improvement in postural alignment at follow-up (mean follow-up duration: 6.0±2.2 months). In the entire sample, higher structural connectivity to the right supplementary motor area (SMA) and right lateral premotor cortex along the dorsal plane (PMd) was associated with larger postsurgical improvements in axial signs and TCC angles after stimulation was turned on. In patients diagnosed with camptocormia, larger improvement in camptocormia angles after STN-DBS was associated with a larger VTA overlap with STN (R = 0.75, p = 0.032). Conclusion: This study suggests that both VTA overlap with STN and structural connectivity to cortical motor regions are associated with the effectiveness of STN-DBS for managing camptocormia in PD.
The rapid development of the smart grid has led to higher maintenance cost and greater scalability of transmission lines. An effective and secure monitoring system for power lines has become a bottleneck restricting the intellectualization of power grids. To address this problem, a novel method is proposed for the intelligent monitoring of power grids (Robot Delay-Tolerant Sensor Network, RDTSN) based on an inspection robot, Wireless Sensor Network (WSN) and Delay-Tolerant Sensor Network (DTSN) to achieve low-cost, energy-efficient, elastic and remote monitoring of power grids. With RDTSN, a smart grid can detect the fault of transmission lines and evaluate the operational state of power grids. To build an effective monitoring system for a smart grid, this research focuses on designing a methodology that achieves efficient and secure delivery of the data inspected on transmission lines. Multiple RDTSN scenarios are performed, in which different routing algorithms are explored to determine the optimal parameters, with a balance in network performance and financial cost. Furthermore, a data delivery strategy is introduced to ensure communication security.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.