Search

Despite notable advancements in bot detection methods based on Graph Neural Networks (GNNs). The efficacy of Graph Neural Networks relies heavily on the homophily assumption, which posits that nodes with the same label are more likely to form connections between them. However, the latest social bots are capable of concealing themselves by extensively interacting with authentic user accounts, forging extensive connections on social graphs, and thus deviating from the homophily assumption. Consequently, conventional Graph Neural Network methods continue to face significant challenges in detecting these novel types of social bots. To address this issue, we proposed SqueezeGCN, an adaptive neighborhood aggregation with the Squeeze Module for Twitter bot detection based on a GCN. The Squeeze Module uses a parallel multi-layer perceptron (MLP) to squeeze feature vectors into a one-dimensional representation. Subsequently, we adopted the sigmoid activation function, which normalizes values between 0 and 1, serving as node aggregation weights. The aggregation weight vector is processed by a linear layer to obtain the aggregation embedding, and the classification result is generated using a MLP classifier. This design generates adaptive aggregation weights for each node, diverging from the traditional singular neighbor aggregation approach. Our experiments demonstrate that SqueezeGCN performs well on three widely acknowledged Twitter bot detection benchmarks. Comparisons with a GCN reveal improvements of 2.37%, 15.59%, and 1.33% for the respective datasets. Furthermore, our approach demonstrates improvements when compared to state-of-the-art algorithms on the three benchmark datasets. The experimental results further affirm the exceptional effectiveness of our proposed algorithm for Twitter bot detection. [ABSTRACT FROM AUTHOR]

Smart classrooms, made possible by the growing use of Internet information technology in the sphere of education, as one of the important foundations for the realization of smart education, have become the current hot direction of the development of educational information innovation and intend to propose some ideas and directions for smart sports teaching research in IA colleges and universities. The smart classroom is an intelligent and efficient classroom created by the "Internet +" way of thinking and the new generation of information technologies such as big data and cloud computing. This article puts forward the exploratory research methods of smart sports classrooms in colleges and universities in the IA, methods, such as document retrieval, expert interviews, questionnaire surveys, and practical research, and field investigation method, which are used in the exploration and research of college smart sports classrooms in the IA experiment. According to the findings of this study, 96.34 percent of students have a positive attitude toward the smart sports classroom teaching model, which is favorable to the growth of smart sports classroom teaching. [ABSTRACT FROM AUTHOR]

Short chain chlorinated paraffins (SCCPs) have received increased interest worldwide since they were added to the list of controlled POPs in Annex A of the Stockholm Convention in 2017. Although many toxicological studies have already shown that SCCPs are hepatotoxic, nephrotoxic, and thyrotoxic to rodents, there have been few studies to date that have characterized changes in the metabolic pathways targeted by SCCPs. In this study, a UPLC-Q-TOF-MS based plasma metabolomics approach was used to investigate the toxicity of SCCPs in rats. Liver and kidney injury occurred rapidly after high-dose SCCP exposure, and the most relevant pathways affected were energy metabolism, amino acid metabolism, glycerophospholipid metabolism, nucleotide metabolism, and vitamin B metabolism. Exposure to SCCPs inhibited the tricarboxylic acid cycle and accelerated degradation. Fluctuating levels of phospholipids and nucleotides may have contributed to the neurotoxicity of SCCPs. In addition, the down regulation of folic acid induced by SCCPs may have led to malformations during the early development of laboratory animals. These results suggested that high exposure levels of SCCPs may have serious health risks and more research is needed to assess the health status of relevant occupational groups. • UPLC-Q-TOF-MS metabolic profiling of liver and kidney in SCCPs-induced injury. • PCA trajectories depict the evolution of the metabolic response in SCCPs. • SCCPs induces impairment in energy metabolism and some molecular metabolism. • Identification of some potential biomarkers of SCCPs toxicity in rat. [ABSTRACT FROM AUTHOR]