Point cloud segmentation plays an important role in AI applications such as autonomous driving, AR, and VR. However, previous point cloud segmentation neural networks rarely pay attention to the topological correctness of the segmentation results. In this paper, focusing on the perspective of topology awareness. First, to optimize the distribution of segmented predictions from the perspective of topology, we introduce the persistent homology theory in topology into a 3D point cloud deep learning framework. Second, we propose a topology-aware 3D point cloud segmentation module, TopoSeg. Specifically, we design a topological loss function embedded in TopoSeg module, which imposes topological constraints on the segmentation of 3D point clouds. Experiments show that our proposed TopoSeg module can be easily embedded into the point cloud segmentation network and improve the segmentation performance. In addition, based on the constructed topology loss function, we propose a topology-aware point cloud edge extraction algorithm, which is demonstrated that has strong robustness.

We study a risk-averse approach to multistage stochastic linear programming, where the conditional value-at-risk is incorporated into the objective function as the risk measure. We consider five decompositions of the resulting risk-averse model to solve it via the nested L-shaped method. We introduce separate approximations of the mean and the risk measure and also investigate the effectiveness of multiple cuts. As an application, we formulate a water allocation problem by risk-averse multistage programming, which has the advantage of controlling high-risk severe water shortage events. We apply the proposed formulation to the southeastern portion of Tucson, AZ to best use the limited water resources available to that region. In numerical experiments we (1) present a comparative computational study of the risk-averse nested L-shaped variants and (2) analyze the risk-averse approach to the water allocation problem.

Prosody affects the naturalness and intelligibility of speech. However, automatic prosody prediction from text for Chinese speech synthesis is still a great challenge and the traditional conditional random fields (CRF) based method always heavily relies on feature engineering. In this paper, we propose to use neural networks to predict prosodic boundary labels directly from Chinese characters without any feature engineering. Experimental results show that stacking feed-forward and bidirectional long short-term memory (BLSTM) recurrent network layers achieves superior performance over the CRF-based method. The embedding features learned from raw text further enhance the performance.