Aiming at the prediction of environmental vibrations induced by elevated high-speed railway, a machine-learning method is developed by combining random forest algorithm and Bayesian optimization, which using the dataset from on-site experiments . When it comes to achieving a rapid and effective prediction of environmental vibration, there is few research on com-parisons and verifications of different algorithms, and neither on parameter tuning and optimi-zation of machine learning algorithms. In this paper, a field experiment is firstly carried out to measure the ground vibrations caused by high-speed trains running on bridge, and then the en-vironmental vibration characteristics are analyzed in view of ground accelerations and weighted vibration levels. Subsequently, three machine-learning algorithms of linear regression, support vector machine and random forest are developed by using experimental database, and their prediction performance are discussed. Finally, two optimization models for the hyperparameter set of random forest algorithm are further compared. It turns out that the integrated random forest algorithm has higher accuracy in predicting environmental vibration than linear regression and support vector machine; the Bayesian optimization has excellent performance and high efficiency in achieving efficient and in-depth optimization of parameters, and can be combined with the RF machine learning algorithm to effectively predict the environmental vibrations induced by the high-speed railway.

Abstract: Periodontal disease is the main reason for tooth loss in adults. Tissue engineering and regenerative medicine are the advanced technologies used to manage soft and hard tissue defects caused by periodontal disease. We developed a transforming growth factor-β3 chitosan sponge (TGF-β3/CS) to repair periodontal soft and hard tissue defects. We investigated the proliferation and osteogenic differentiation behaviors of primary human periodontal ligament stem cells (hPDLSCs) to discuss the bioactivity and application of TGF-β3 in periodontal disease. We separately used Calcein-AM/PI double-labeling or CM-Dil-labeling coupled with fluorescence microscopy to trace the survival and function of the cells after implantation in vitro or in vivo. The mineralization of osteogenic differentiated hPDLSCs was confirmed by measuring ALP activity and calcium content. The levels of COL I, ALPL, TGF-βRI, TGF-βRII, and Pp38/t-p38 were tested using Western blot to explore the mechanism of bone repair prompted by TGF-β3. When hPDLSCs were inoculated with different concentrations of TGF-β3/CS (62.5–500 ng/mL), ALP activity was the highest in TGF-β3 (250 ng/mL) group after seven days (P < 0.05 vs. control); the calcium content in each group increased significantly after 21 and 28 days (P < 0.001 vs. control). The best result was achieved in the TGF-β3 (500 ng/mL) group. All results showed that TGF-β3/CS can promote osteogenic differentiation of hPDLSC and may be involved in the p38 MAPK signaling pathway. TGF-β3/CS has the potential for application in the repair of incomplete alveolar bone defects.

Activation of the NLRP3 inflammasome plays a crucial role in innate immune response. During cell division, the NLRP3 inflammasome activation must be strictly controlled. Here, we discovered the anaphase promoting complex subunit 10 (Anapc10, APC10), a substrate recognition protein of the anaphase promoting complex/cyclosome (APC/C), is a critical mediator of the NLRP3 inflammasome activation. APC10 protein interacts with NLRP3, and co-localizes with NLRP3 protein in the cytoplasm. During interphase, APC10 interacts with NLRP3 to promote the NLRP3 inflammasome activation. During mitosis, APC10 disassociates from the NLRP3 inflammasome to inhibit the inflammatory responses. This study reveals a distinct mechanism by which APC10 serves as a switch of the NLRP3 inflammasome activation during cell cycle.