The digital documentation and analysis of cultural heritage increasingly rely on high-precision three-dimensional point cloud data, which often suffers from missing regions due to limitations in acquisition conditions, hindering subsequent analyses and applications. Point cloud completion techniques, by predicting and filling these missing regions, are vital for restoring the integrity of cultural heritage structures, enhancing restoration accuracy and efficiency. In this paper, for challenges in processing large-scale cultural heritage point clouds, particularly the slow processing speed and visualization impairments from uneven point density during completion, we propose a point cloud completion employing centroid-based voxel feature extraction, which significantly accelerates feature extraction for massive point clouds. Coupled with an efficient upsampling module, it achieves a uniform point distribution. Experimental results show that the proposed method matches SOTA performance in completion accuracy while surpassing in point density uniformity, demonstrating capability in handling larger-scale point cloud data, and accelerating the processing of voluminous point clouds. In general, the proposed method markedly enhances the efficiency and quality of large-scale point cloud completion, holding significant value for the digital preservation and restoration of cultural heritage.

Large-scale 3D-scanned point clouds enable the accurate and easy recording of complex 3D objects in the real world. The acquired point clouds often describe both the surficial and internal 3D structure of the scanned objects. The recently proposed edge-highlighted transparent visualization method is effective for recognizing the whole 3D structure of such point clouds. This visualization utilizes the degree of opacity for highlighting edges of the 3D-scanned objects, and it realizes clear transparent viewing of the entire 3D structures. However, for 3D-scanned point clouds, the quality of any edge-highlighting visualization depends on the distribution of the extracted edge points. Insufficient density, sparseness, or partial defects in the edge points can lead to unclear edge visualization. Therefore, in this paper, we propose a deep learning-based upsampling method focusing on the edge regions of 3D-scanned point clouds to generate more edge points during the 3D-edge upsampling task. The proposed upsampling network dramatically improves the point-distributional density, uniformity, and connectivity in the edge regions. The results on synthetic and scanned edge data show that our method can improve the percentage of edge points more than 15% compared to the existing point cloud upsampling network. Our upsampling network works well for both sharp and soft edges. A combined use with a noise-eliminating filter also works well. We demonstrate the effectiveness of our upsampling network by applying it to various real 3D-scanned point clouds. We also prove that the improved edge point distribution can improve the visibility of the edge-highlighted transparent visualization of complex 3D-scanned objects.

In the context of growing global energy demand and increasingly severe environmental pollution, ensuring the stable dispatch of new energy sources and the effective management of power resources has become particularly important. This study focuses on the reliability and stability issues of new energy dispatch considering the complementary advantages of multiple energy types. It aims to enhance dispatch stability and energy utilization through an innovative Distributed Overlapping Coalition Formation (DOCF) model. A distributed algorithm utilizing tabu search is proposed to solve the complex optimization problem in power resource allocation. The overlapping coalitions consider synergies between different types of resources and intelligently allocate based on the heterogeneous demands of power loads and the supply capabilities of power stations. Simulation results demonstrate that DOCF can significantly improve power grid resource utilization efficiency and dispatch stability. Particularly in handling intermittent power resources such as solar and wind energy, the proposed model effectively reduces peak shaving time and improves the overall network energy efficiency. Compared with the preference relationship based on selfish and Pareto sequence, the PGG-TS algorithm based on BMBT has an average utility of 10.2% and 25.3% in terms of load, respectively. The methodology and findings of this study have important theoretical and practical value for guiding actual energy management practices and promoting the wider utilization of renewable energy.

In this paper, we propose a method to visualize large-scale colliding point clouds by highlighting their collision areas, and apply the method to visualization of collision simulation. Our method uses our recent work that achieved precise three-dimensional see-through imaging, i.e., transparent visualization, of large-scale point clouds that were acquired via laser scanning of three-dimensional objects. We apply the proposed collision visualization method to two applications: (1) The revival of the festival float procession of the Gion Festival, Kyoto city, Japan. The city government plans to revive the original procession route, which is narrow and not used at present. For the revival, it is important to know whether the festival floats would collide with houses, billboards, electric wires, or other objects along the original route. (2) Plant simulations based on laser-scanned datasets of existing and new facilities. The advantageous features of our method are the following: (1) A transparent visualization with a correct depth feel that is helpful to robustly determine the collision areas; (2) the ability to visualize high collision risk areas and real collision areas; and (3) the ability to highlight target visualized areas by increasing the corresponding point densities.

To address traditional beer detection limitations, this study proposes a rapid NIRS-based method for detecting key indicators and verifying authenticity. Designing Single-task (STL) and Multi-task learning (MTL) strategies, it employs Variable Importance in Projection for wavelength selection. Deep spectral features were extracted utilizing a Multi-Head Attention (MHA)-fused Convolutional Neural Network (CNN-MHA), Long Short-Term Memory (LSTM-MHA), and hybrid CNN-LSTM-MHA networks. To further enhance model performance, the Bayesian Optimization Algorithm globally optimized network hyperparameters in STL, alongside hyperparameters and multi-task loss weights in MTL. Partial least squares regression, support vector machine regression, and partial least squares discriminant analysis models were established using these features. Results indicate that the MTL-based CNN-LSTM-MHA network effectively learns shared features across multiple tasks, significantly improving model generalization. Specifically, the coefficients of determination ($R^2$) for alcohol content and original wort concentration in the validation set were 0.996 and 0.997, respectively, with relative root mean square errors (rRMSE) of 2.024% and 2.515%. In the independent test set, the $R^2$ were 0.995 and 0.991, with rRMSE of 2.515% and 2.087%, respectively. Furthermore, 100% classification accuracy was achieved across all datasets. This method provides an efficient technical solution for beer market regulation and real-time detection in production processes.