Deep learning techniques have become transformative forces in the field of Computer Graphics, including voxels, point clouds, and meshes. However, the integration of deep learning with Computer-Aided Design (CAD) has not yet reached a mature stage due to the lack of support for a rich variety of high-level CAD features. In parametric and feature-based modeling, various advanced CAD feature operations require unique identifiers to specify topological elements like surface and edge, known as naming mechanism. Unfortunately, this mechanism is currently unavailable in CAD deep learning due to its difficulty in formulation and representation. Therefore, this paper proposes a novel method for combining naming and CAD learning, which is the first work that applies name to specify model topological elements in CAD deep learning. Specifically, we create a dataset which records the name identifier information of elements contained in CAD models, together with model construction history for reconstruction. Subsequently, we propose a deep learning approach for predicting topological element names from model construction history, which shows a high prediction rate in the experiments. Additionally, with the help of name identifiers, we introduce high-level feature operations into CAD deep learning modeling and conduct an extended model generation experiment to show the practicality of our method. The impressive generation results prove that our method opens a new direction to bridge the gap between CAD deep learning and practical CAD modeling. The code and dataset are available at https://github.com/fazhihe/NamingCAD.

As a new design and manufacture paradigm, Cloud-Based Collaborative Design (CBCD) has motivated designers to outsource their product data and design computation onto the cloud service. Despite non-negligible benefits of CBCD, there are potential security threats for the outsourced product data, such as intellectual property, design intentions and private identity, which has become an interest point. This paper presents a novel secure product data exchange (PDE) in the processes of CBCD. Different from general cloud security mechanism, our method is content-based. We first show an outline of the collaborative scenario to describe the architecture of the proposed secure CBCD, in which a security mechanism is combined with the data exchange service to achieve secure PDE. Second, we present a novel grid-based geometric deformation method for the security mechanism with three processes: the original shapes of a source Computer Aided Design (CAD) model can be hidden by deforming the control grid; then the deformed grid can be exchanged to target system where a deformed target CAD model can be reconstructed; at last, the deformed target CAD model can be recovered to the original shape after recovering the deformed grid. Finally, typical CAD model tests demonstrate that our method can keep the sensitive information of source model and also maintain the same level of data exchange error.

In the co-design process of hardware/software (HW/SW) system, especially for large and complicated embedded systems, HW/SW partitioning is a challenging step. Among different heuristic approaches, particle swarm optimization (PSO) has the advantages of simple implementation and computational efficiency, which is suitable for solving large-scale problems. This paper presents a conformity particle swarm optimization with fireworks explosion operation (CPSO-FEO) to solve large-scale HW/SW partitioning. First, the proposed CPSO algorithm simulates the conformist mentality from biology research. The CPSO particles with psychological conformist always try to move toward a secure point and avoid being attacked by natural enemy. In this way, there is a greater possibility to increase population diversity and avoid local optimum in CPSO. Next, to enhance the search accuracy and solution quality, an improved FEO with new initialization strategy is presented and is combined with CPSO algorithm to search a better position for the global best position. This combination can keep both the diversified and intensified searching. At last, the experiments on benchmarks and large-scale HW/SW partitioning demonstrate the efficiency of the proposed algorithm.