With the rapid development of urbanization, the boom of vehicle numbers has resulted in serious traffic accidents, which led to casualties and huge economic losses. The ability to predict the risk of traffic accident is important in the prevention of the occurrence of accidents and to reduce the damages caused by accidents in a proactive way. However, traffic accident risk prediction with high spatiotemporal resolution is difficult, mainly due to the complex traffic environment, human behavior, and lack of real-time traffic-related data. In this study, we collected big traffic accident data. By analyzing the spatial and temporal patterns of traffic accident frequency, we presented the spatiotemporal correlation of traffic accidents. Based on the patterns we found in analysis, we proposed a high accurate deep learning model based on recurrent neural network toward the prediction of traffic accident risk. The predictive accident risk can be potential applied to the traffic accident warning system. The proposed method can be integrated into an intelligent traffic control system toward a more reasonable traffic prediction and command organization.

The importance of morphogens is a central concept in developmental biology. Multiple-fate patterning and the robustness of the morphogen gradient are essential for embryo development. The ways by which morphogens diffuse from a local source to form long distance gradients can differ from one morphogen to the other, and for the same morphogen in different organs. This paper will study the mechanism by which morphogens diffuse through the aid of membrane-associated non-receptors and will investigate how the membrane-associated non-receptors help the morphogen to form long distance gradients and to achieve good robustness. Such a mechanism has been reported for some morphogens that are rapidly turned over. We will establish a set of reaction-diffusion equations to model the dynamical process of morphogen gradient formation. Under the assumption of rapid morphogen degradation, we discuss the existence, uniqueness, local stability, approximation solution, and the robustness of the steady-state gradient. The results in this paper show that when the morphogen is rapidly turned over, diffusion of the morphogen through membrane-associated non-receptors is a possible strategy to form a long distance multiple-fate gradient that is locally stable and is robust against the changes in morphogen synthesis rate.

No abstract

No abstract

DNA methylation patterns have profound impacts on genome stability, gene expression and development. The molecular base of DNA methylation patterns has long been focused at single CpG sites level. Here, we construct a kinetic model of DNA methylation with collaborations between CpG sites, from which a correlation function was established based on experimental data. The function consists of three parts that suggest three possible sources of the correlation: movement of enzymes along DNA, collaboration between DNA methylation and nucleosome modification, and global enzyme concentrations within a cell. Moreover, the collaboration strength between DNA methylation and nucleosome modification is universal for mouse early embryo cells. The obtained correlation function provides insightful understanding for the mechanisms of inheritance of DNA methylation patterns.