Crash risk identification and prediction are expected to play an important role in traffic accident prevention. However, most of the existing studies focus only on highways, not on multi-lane weaving areas. In this paper, a potential collision risk identification and conflict prediction model based on extending Time-to-Collision-Machine Learning (TTC-ML) for multi-lane weaving zone was proposed. The model can accurately learn various features, such as vehicle operation characteristics, risk and conflict distributions, and physical zoning characteristics in the weaving area. Specifically, TTC was used to capture the collision risk severity, and ML extracted vehicle trajectory features. After normalizing and dimensionality reduction of the vehicle trajectory dataset, Naive Bayes, Logistic Regression, and Gradient Boosting Decision Tree (GBDT) models were selected for traffic conflict prediction, and the experiments showed that the GBDT model outperforms two remaining models in terms of prediction accuracy, precision, false-positive rate (FPR) and Area Under Curve (AUC). The research findings of this paper help traffic management departments develop and optimize traffic control schemes, which can be applied to Intelligent Vehicle Infrastructure Cooperative Systems (IVICS) dynamic warning.

Introduction: The tumor microenvironment (TME) is mainly characterized by abnormally elevated intracellular redox levels and excessive oxidative stress. However, the balance of the TME is also very fragile and susceptible to be disturbed by external factors. Therefore, several researchers are now focusing on intervening in redox processes as a therapeutic strategy to treat tumors. Here, we have developed a liposomal drug delivery platform that can load a Pt(IV) prodrug (DSCP) and cinnamaldehyde (CA) into a pH-responsive liposome to enrich more drugs in the tumor region for better therapeutic efficacy through enhanced permeability and retention effect.Methods: Using the glutathione-depleting properties of DSCP together with the ROS-generating properties of cisplatin and CA, we synergistically altered ROS levels in the tumor microenvironment to damage tumor cells and achieve anti-tumor effects in vitro.Results: A liposome loaded with DSCP and CA was successfully established, and this liposome effectively increased the level of ROS in the tumor microenvironment and achieved effective killing of tumor cells in vitro.Conclusion: In this study, novel liposomal nanodrugs loaded with DSCP and CA provided a synergistic strategy between conventional chemotherapy and disruption of TME redox homeostasis, leading to a significant increase in antitumor effects in vitro.

No abstract