Sustainable development, which has become the priority study of architectural design, is receiving increasing attention with global climate change. At the same time, the building industry is urgently changing towards intelligent and digitalized tendencies. As a result, Building Information Modeling (BIM) and the Internet of Things (IoT) make crucial contributions to the transforming process. However, there is little knowledge of the integration of BIM–IoT in sustainable building from a macro perspective. Moreover, most existing research adopts a literature review method and lacks objective quantitative analysis. Few papers use bibliometric analysis to study the respective BIM and IoT research fields. Furthermore, few studies use Citespace software tools to analyze the integrated application of BIM–IoT. Therefore, this paper aims to investigate the research frontiers and knowledge structure in BIM–IoT integration and the relationship between BIM-IoT and sustainable building and explore the research hotspots, trends, and future research directions. A quick and objective method was proposed to understand the research status of these new and rapidly developing fields. This paper uses topic search in the web of science core collection to obtain relevant literature and then uses Citespace for bibliometric analysis based on the literature review. Controlled terms and subject terms statistics from the Engineering Index core database search results are also used to briefly examine the fields’ research frontiers and hotspots as obtained from Citespace. The results show that: (1) The research on BIM–IoT integration focuses on building intelligence with BIM as the basis of application, and research on BIM–IoT integration within the field of sustainable building is currently focused on the first three phases of the life cycle. (2) The development of sustainable buildings needs to be considered on its human and social dimensions. BIM provides a platform for sharing information and communication among stakeholders involved in the building’s entire life cycle. At the same time, IoT allows occupants to better participate in buildings’ sustainable design and decision making. (3) In the future, more emerging technologies such as cloud computing and big data are required to better promote sustainable buildings and thus realize the construction of sustainable smart cities. At the same time, researchers should also pay attention to the sustainable transformation of existing buildings.

In computer-aided diagnosis methods for breast cancer, deep learning has been shown to be an effective method to distinguish whether lesions are present in tissues. However, traditional methods only classify masses as benign or malignant, according to their presence or absence, without considering the contextual features between them and their adjacent tissues. Furthermore, for contrast-enhanced spectral mammography, the existing studies have only performed feature extraction on a single image per breast. In this paper, we propose a multi-input deep learning network for automatic breast cancer classification. Specifically, we simultaneously input four images of each breast with different feature information into the network. Then, we processed the feature maps in both horizontal and vertical directions, preserving the pixel-level contextual information within the neighborhood of the tumor during the pooling operation. Furthermore, we designed a novel loss function according to the information bottleneck theory to optimize our multi-input network and ensure that the common information in the multiple input images could be fully utilized. Our experiments on 488 images (256 benign and 232 malignant images) from 122 patients show that the method’s accuracy, precision, sensitivity, specificity, and f1-score values are 0.8806, 0.8803, 0.8810, 0.8801, and 0.8806, respectively. The qualitative, quantitative, and ablation experiment results show that our method significantly improves the accuracy of breast cancer classification and reduces the false positive rate of diagnosis. It can reduce misdiagnosis rates and unnecessary biopsies, helping doctors determine accurate clinical diagnoses of breast cancer from multiple CESM images.

The rapid increase in building components on the building information model (BIM) object database has created new demand for BIM product recommendations to improve design efficiency. Current efforts mainly focus on the shape and contents of the products, instead of stylistic consistency, which is a crucial factor during the practical design process. To tackle such a problem, this paper proposes a novel framework to capture stylistic features based on long-range design dependencies with structural preservation, of which the snapshots of BIM products have been used to extract the stylistic features; core patches with strong style, generated by the pre-trained saliency model, are the root nodes; stylistic correlations are calculated as the hyperedges by tree-based operations; deep features and design features are proposed to represent the low-level and style distribution based on the study of design theory; and an ensemble learning strategy is introduced to solve the unbalanced classifier performance. An ablation study is conducted to validate the effectiveness of the proposed framework, in which comparative experiments with state-of-the-art baselines demonstrate the advantages of the proposed method.

This study addresses the challenge of font retrieval in design by proposing a novel approach utilizing contrastive learning to establish a shared embedding space for texts and fonts. In contrast to previous methods limited to word-level queries, our method enables text-font retrieval at the sentence level. We collected text-font pair data from web pages and design templates on the Internet, finetuned the CLIP model on these pairs, and obtained text and font encoders for our application. The top-k fonts were then retrieved using the cosine distance between input text and font embeddings. Our approach offers three key advantages: (1) retrieving fonts with sentence-level text as input, which is intuitively consistent with design behaviors; (2) leveraging text-font pair data available on the Internet without manual annotation; and (3) scalability, the trained font encoder can encode new font candidates without retraining the model. We introduced an evaluation metric for font retrieval results. The results indicate that the retrieved fonts in the top 3 score better than those from baseline methods, and the top 1 retrieved font is competitive with the fonts selected by experienced graphic designers.