Si Zhang

Dr. Si Zhang

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 August 2024 in Buildings
Verified
Journal Article
Open access
PDF file
WJWei Junjie
Wei Junjie
YHYuexia Hu
Yuexia Hu
SZSi Zhang
Si Zhang
SLShuyu Liu
Shuyu Liu
Semantic segmentation of building facades has enabled much intelligent support for architectural research and practice in the last decade. Faced with the free facade of modern buildings, however, the accuracy of segmentation decreased significantly, partly due to its low regularity of composition. The freely organized facade composition is likely to weaken the features of different elements, thus increasing the difficulty of segmentation. At present, the existing facade datasets for semantic segmentation tasks were mostly developed based on the classical facades, which were organized regularly. To train the pixel-level classifiers for the free facade segmentation, this study developed a finely annotated dataset named Irregular Facades (IRFs). The IRFs consist of 1057 high-quality facade images, mainly in the modernist style. In each image, the pixels were labeled into six classes, i.e., Background, Plant, Wall, Window, Door, and Fence. The multi-network cross-dataset control experiment demonstrated that the IRFs-trained classifiers segment the free facade of modern buildings more accurately than those trained with existing datasets. The formers show a significant advantage in terms of average WMIoU (0.722) and accuracy (0.837) over the latters (average WMIoU: 0.262–0.505; average accuracy: 0.364–0.662). In the future, the IRFs are also expected to be considered the baseline for the coming datasets of freely organized building facades.

6 January 2020 in Journal of Asian Architecture and Building Engineering
Verified
Journal Article
Open access
SLShuyu Liu
Shuyu Liu
GZGuangtian Zou
Guangtian Zou
SZSi Zhang
Si Zhang
Architectural innovation is important for improving the built environment. In recent years, an increasing number of architects have focused on this field. A comprehensive understanding of existing building design patterns contributes to reasonable innovation. Based on the large number of architectural cases on the internet in the big data era, this study proposes a three-stage case mining method, containing case collection, case analysis and case study, to find typical architectural cases, discover existing design patterns and create new design patterns by using cluster analysis of architectural cases. An extensive architectural design case mining system and a case clustering program are developed to assist in the case analysis. An agglomerative hierarchical clustering algorithm is applied to support the case clustering program. The example shows the complete application process and practical effect of the proposed method. With this intelligent method, architects can make more reasonable innovations in projects. The proposed typical case mining method is also expected to be useful for engineers and planners with similar needs.

4 July 2024 in Journal of Asian Architecture and Building Engineering
Verified
Journal Article
Open access
YHYuexia Hu
Yuexia Hu
WJWei Junjie
Wei Junjie
SZSi Zhang
Si Zhang
SLShuyu Liu
Shuyu Liu

2 October 2025 in Buildings
Verified
Journal Article
Open access
PDF file
SLShuyu Liu
Shuyu Liu
ZWZhihui Wang
Zhihui Wang
YHYuexia Hu
Yuexia Hu
XZXiaoyu Zhao
Xiaoyu Zhao
SZSi Zhang
Si Zhang
Semantic segmentation of building facade images has enabled a lot of intelligent support for architectural research and practice in the last decade. However, the classifiers for semantic segmentation usually predict facade elements (e.g., windows) as graphics in irregular shapes. The non-smooth edges and hard-to-define shapes impede the further use of the predicted graphics. This study proposes a method to regularize the predicted graphics following the prior knowledge of composition principles of building facades. Specifically, we define four types of boxes for each predicted graphic, namely minimum circumscribed box (MCB), maximum inscribed box (MIB), candidate box (CB), and best overlapping box (BOB). Based on these boxes, a three-stage process, consisting of denoising, BOB finding, and BOB stacking, was established to regularize the predicted graphics of facade elements into basic rectilinear polygons. To compare the proposed and existing methods of graphic regularization, an experiment was conducted based on the predicted graphics of facade elements obtained from four pixel-wise annotated building facade datasets, Irregular Facades (IRFs), CMP Facade Database, ECP Paris, and ICG Graz50. The results demonstrate that the graphics regularized by our method align more closely with real facade elements in shape and edge. Moreover, our method avoids the prevalent issue of correctness degradation observed in existing methods. Compared with the predicted graphics, the average IoU and F1-score of our method-regularized graphics respectively increase by 0.001–0.017 and 0.000–0.012 across the datasets, while those of previous method-regularized graphics decrease by 0.002–0.021 and 0.002–0.015. The regularized graphics contribute to improving the precision and depth of semantic segmentation-based applications of building facades. They are also expected to be useful for the exploration of data mining on urban images in the future.

26 May 2026 in Journal of Building Engineering
Verified
Journal Article
Closed access
HZHanxin Zhang
Hanxin Zhang
ZWZhihui Wang
Zhihui Wang
XFXinyi Fei
Xinyi Fei
SZSi Zhang
Si Zhang
SLShuyu Liu
Shuyu Liu

17 July 2026 in Sustainability
Verified
Journal Article
Open access
PDF file
SZSi Zhang
Si Zhang
XFXinyi Fei
Xinyi Fei
SLShuyu Liu
Shuyu Liu
Against the background of healthy aging, age-friendly communities, and social sustainability, community public spaces are important everyday settings for older adults’ outdoor activities and social connections. However, it remains insufficiently explained how public space environments are translated into social health benefits through specific social activities. From an environment-behavior-health perspective, this study examines Chongwen Jincheng Community in Nanjing through a concentrated sample design within a single large community. Based on 217 valid questionnaires from residents aged 60 years and above, an AMOS latent-variable structural equation model was constructed, and a standardized composite-variable Bootstrap model was used for robustness checking. The results show that the community public space environment has a significant total association with older adults’ social health. After social activities are included, the direct associations between traffic convenience, environmental comfort and safety, service facility supportiveness, and social health become non-significant, whereas multiple indirect paths through social activities remain significant, supporting a full mediation pattern in this case study. Traffic convenience is mainly linked to social health through passive and brief social interaction, environmental comfort and safety through brief and sustained social interaction, and service facility supportiveness through passive and sustained social interaction. These findings suggest that, within the cross-sectional SEM framework, the social health value of community public spaces is mainly linked to everyday encounters, weak-tie contact, brief communication, and sustained participation.