4 April 2023 in Scientific Reports
To provide theoretical support for the safety control of rectangular pipe jacking tunnels crossing an existing expressway, a method for predicting the surface settlement of a rectangular pipe jacking tunnel is proposed in this study. Therefore, based on the high approximation of the BP neural network to any function under the multiparameter input, the PSO-BP mixed prediction model of the ground subsidence of the ultrashallow buried large section rectangular pipe jacking tunnel is established by taking into account the adaptive mutation method, adopting the improved particle swarm optimization (IPSO) algorithm with adaptive inertia weight and mutation particles in the later stage to determine the optimal hyperparameters of the prediction model. Through the case study of an ultrashallow large cross-section rectangular pipe jacking tunnel, this algorithm is compared with the traditional algorithm and combined with field monitoring data for analysis and prediction. The prediction results show that compared with the traditional BP neural network prediction model, AWPSO-BP model and PWPSO-BP model, the improved PSO-BP mixed prediction model shows a more stable prediction effect when the change in surface subsidence is gentle and the concavity and convexity are large. The predicted subsidence value is close to the actual value, and the accuracy and robustness of the prediction are significantly improved.
12 July 2023 in ACM Transactions on Multimedia Computing, Communications, and Applications
Detecting points of interest is a fundamental problem in 3D shape analysis and can be beneficial to various tasks in multimedia processing. Traditional learning-based detection methods usually rely on each vertex’s geometric features to discriminate points of interest from other vertices. Observing that points of interest are related to not only geometric features on themselves but also the geometric features of surrounding vertices, we propose a novel context-aware 3D points of interest detection algorithm by adopting the spatial attention mechanism in this article. By designing a context attention module, our approach presents a novel deep neural network to simultaneously pay attention to the geometric features of vertices and their local contexts during extracting points of interest. To obtain satisfactory extraction results, our method adaptively assigns different weights to those features in a data-driven way. Extensive experimental results on SHREC 2007, SHREC 2011, and SHREC 2014 datasets show that our algorithm achieves superior performance over existing methods.