Search results

To further promote application of BIM technology in construction of prefabricated buildings, influencing factors and evolution laws of willingness to apply BIM technology are explored from the perspective of willingness of participants.

In this paper, a tripartite game model involving the design firm, component manufacturer and construction firm is constructed and a system dynamics method is used to explore the influencing factors and game evolution path of three parties' application of BIM technology, from three perspectives, cost, benefit and risk.

The government should formulate measures for promoting the application of BIM according to different BIM application willingness of the parties. When pursuing deeper BIM application, the design firm should pay attention to reducing the speculative benefits of the component manufacturer and the construction firm. The design firm and the component manufacturer should pay attention to balancing the cost and benefit of the design firm while enhancing collaborative efforts. When the component manufacturer and the construction firm cooperate closely, it is necessary to pay attention to balanced distribution of interests of both parties and lower the risk of BIM application.

This study fills a research gap by comprehensively investigating the influencing factors and game evolution paths of willingness of the three parties to apply BIM technology to prefabricated buildings. The research helps to effectively improve the building quality and construction efficiency, and is expected to contribute to the sustainability of built environment in the context of circular economy in China.

This paper proposes a solution for recognizing human faces under mask-wearing. The lower part of human face is occluded and could not be used in the learning process of face recognition. So, the proposed solution is developed to recognize human faces on any available facial components which could be varied depending on wearing or not wearing a mask.

The proposed solution is developed based on the FaceNet framework, aiming to modify the existing facial recognition model to improve the performance of both scenarios of mask-wearing and without mask-wearing. Then, simulated masked-face images are computed on top of the original face images, to be used in the learning process of face recognition. In addition, feature heatmaps are also drawn out to visualize majority of parts of facial images that are significant in recognizing faces under mask-wearing.

The proposed method is validated using several scenarios of experiments. The result shows an outstanding accuracy of 99.2% on a scenario of mask-wearing faces. The feature heatmaps also show that non-occluded components including eyes and nose become more significant for recognizing human faces, when compared with the lower part of human faces which could be occluded under masks.

The convolutional neural network based solution is tuned up for recognizing human faces under a scenario of mask-wearing. The simulated masks on original face images are augmented for training the face recognition model. The heatmaps are then computed to prove that features generated from the top half of face images are correctly chosen for the face recognition.