Search

To construct an accurate crash prediction model, the road safety performance function (SPF), which provides a safety guide for the management department, is often used. In traditional parametric SPFs, the importance of traffic features is calculated using analytic expression, but the model is inaccurate and low in generalization. This article proposes a machine learning-based method to replace parametric SPFs, this framework is built based on integrated visual feature importance, global model training, and a structure self-organizing scheme. From the analysis, this model can not only predict multiregional car crashes accurately but can also provide a feature importance and selection guide for the management department to better understand it. At last, experiments using real-world data collected from Highway 401 Ontario Canada and several highways in the U.S. show that the proposed framework outperformed other State-of-the-Art models in terms of interpretability, accuracy, generalizability, and model conciseness.

Matching with a semantic map can feed accurate prior information into perception and localization modules in the intelligent vehicle system. This article proposes a simultaneous matching, localization, and detection (SMLAD) method from a semantic LiDAR map for intelligent vehicles, which integrates the separated steps of map matching, vehicle localization, and semantic detection into maximum a posteriori probability (MAP) inference problem in the particle filter framework. Firstly, semantic objects, such as cubes, poles, walls, and ground, are extracted from the query point cloud by LiDAR segmentation method. Then semantic likelihood models (SLMs) are generated from the extracted semantic objects with kernel density estimation (KDE). Finally, the likelihood between the map and the query point cloud is calculated from SLMs that contributes to weight assignment in the particle filter framework. And the proposed point-to-likelihood association allows simultaneous map matching, localization, and detection afterwards. The proposed SMLAD method has been validated with both the public KITTI dataset and the real tests. Experimental results demonstrate that the proposed SMLAD method can achieve up to 10-cm localization accuracy on both test datasets, and the detection results can be derived simultaneously by mapping accurate semantic objects from the map into the query point cloud.

Operational optimal control (OOC) is an essential component of wastewater treatment process (WWTP). The control variables usually are high-dimensional, nonlinear, and strongly coupled, which can easily fail traditional optimization control methods. Mathematically, these operational variables usually are in the unknown low-dimensional space embedded in the high-dimensional space. Therefore, the OOC problem of WWTP can be resolved as an optimization challenge involving low-dimensional space, and the unknown low-dimensional space is presented in the form of a set of controlled variables in a high-dimensional space, which is normal in real-world industries. Here, a dimension-reducible data-driven optimization control framework for WWTP is proposed. Considering the difficulty in elucidating the whole space of set points, a neural network is designed to approximate the constraint relationship between control variables. The search process is based on optimization methods in low-dimensional space embedded into Euclidean spaces. Furthermore, the convergence of the process is ensured via mathematical analysis. Finally, the experimental simulation of wastewater treatment revealed that this approach is effective for an optimal solution in control systems.