资源
分享此页:
列印
列印
香港专上院校所提供之论文/研究刊物
| 院校 | 题目 | 类型 | 日期 | 作者 | 摘要 | 网页 |
|---|---|---|---|---|---|---|
| HKU | The Investigation on the Usage of Building Information Modeling (BIM) in Hong Kong | Thesis | 04/2014 | POON Ho Yu | -- | N.A. |
| HKUST | Transfer learning enhanced AR spatial registration for facility maintenance management | Journal | 02/2020 | Chen, K., Yang, J., Cheng, J.C.P., Chen, W., and Li, C.T. | Augmented reality (AR), which requires a spatial registration technique, has proved to greatly improve the efficiency of facility maintenance management (FMM) activities. Being one of the most promising techniques for indoor localization, Wi-Fi fingerprinting has been widely used for AR spatial registration. However, localization accuracy of Wi-Fi fingerprinting decreases over time due to dynamics of environmental factors. Readings from different mobile devices can also affect the accuracy negatively. In this paper, a transfer learning technique named transferable CNN-LSTM is proposed for improving the robustness of Wi-Fi fingerprinting while implementing AR in FMM activities. Convolutional neural network (CNN), embedded with long short term memory (LSTM) networks, is utilized to predict the location of unlabeled fingerprints. Multiple kernel variant of maximum mean discrepancy (MK-MMD) is adopted to reduce the distribution difference between the source domain and the target domain, so that the location of the newly collected unlabeled fingerprints can be predicted accurately. As shown in the experimental validation, the transferable CNN-LSTM can achieve an accuracy of 97.1% in short-term (without significant environmental changes) spatial registration, 87.8% in long-term (with significant environmental changes) spatial registration, and around 90% in multi-device spatial registration, indicating a higher accuracy and better robustness over other conventional approaches. | 连结 |
| HKUST | Trends and opportunities of BIM-GIS integration in the architecture, engineering and construction industry: A review from a spatio-temporal statistical perspective | Journal | 12/2017 | Song, Y., Wang, X., Tan, Y., Wu, P., Sutrisna, M., Cheng, J.C.P., et al. | The integration of building information modelling (BIM) and geographic information system (GIS) in construction management is a new and fast developing trend in recent years, from research to industrial practice. BIM has advantages on rich geometric and semantic information through the building life cycle, while GIS is a broad field covering geovisualization-based decision making and geospatial modelling. However, most current studies of BIM-GIS integration focus on the integration techniques but lack theories and methods for further data analysis and mathematic modelling. This paper reviews the applications and discusses future trends of BIM-GIS integration in the architecture, engineering and construction (AEC) industry based on the studies of 96 high-quality research articles from a spatio-temporal statistical perspective. The analysis of these applications helps reveal the evolution progress of BIM-GIS integration. Results show that the utilization of BIM-GIS integration in the AEC industry requires systematic theories beyond integration technologies and deep applications of mathematical modeling methods, including spatio-temporal statistical modeling in GIS and 4D/nD BIM simulation and management. Opportunities of BIM-GIS integration are outlined as three hypotheses in the AEC industry for future research on the in-depth integration of BIM and GIS. BIM-GIS integration hypotheses enable more comprehensive applications through the life cycle of AEC projects. | 连结 |