No abstract

No abstract

The fast semantic segmentation algorithm of 3D laser point clouds for large scenes is of great significance for mobile information measurement systems, but the point cloud data is complex and generates problems such as disorder, rotational invariance, sparsity, severe occlusion, and unstructured data. We address the above problems by proposing the random sampling feature aggregation module ATSE module, which solves the problem of effective aggregation of features at different scales, and a new semantic segmentation framework PointLAE, which effectively presegments point clouds and obtains good semantic segmentation results by neural network training based on the features aggregated by the above module. We validate the accuracy of the algorithm by training on Semantic3D, a public dataset of large outdoor scenes, with an accuracy of 90.3, while verifying the robustness of the algorithm on Mvf CNN datasets with different sparsity levels, with an accuracy of 86.2, and on Bjfumap data aggregated by our own mobile environmental information collection platform, with an accuracy of 77.4, demonstrating that the algorithm is good for mobile information complex scale data in mobile information collection with great recognition effect.

Early diagnosis of breast cancer is critical for effective treatment. Artificial intelligence (AI) technology has shown promise in assisting physicians with diagnosis. However, the combination of qualitative and quantitative information in surveillance data leads to ambiguity and uncertainty. Belief rule bases (BRB) can address these issues by incorporating confidence distributions. However, existing BRB models rely on offline training and lack adaptability to changes in patient metrics. In addition, the ethical implications of using BRB for breast cancer diagnosis require attention to the interpretability of the model. Therefore, this paper presents an online belief rule base breast cancer diagnosis method with interpretability. The method uses online learning to achieve dynamic growth. It also overcomes the problem of interpretability loss in the optimization process by implementing interpretability constraints. The proposed method achieves competitive accuracy and interpretability in breast cancer diagnosis, as demonstrated by experiments using a large dataset of breast cancer cases.