FYPs/Thesis/Journal from Higher Education Institutions in Hong Kong


Below Information is provided by the Higher Insitutions signed MoU with CIC.



Date: From


Institution Title Type Date Author(s) Abstract Link
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. Link
HKUST Developing efficient mechanisms for BIM-to-AR/VR data transfer Journal 06/2020 Chen, K., Chen, W., Wang, Q., and Cheng, J.C.P. Augmented reality/virtual reality (AR/VR) has been increasingly adopted to enhance visualization of building information modeling (BIM) models. However, there is a lack of mechanisms for efficient data transfer from BIM to AR/VR. On one hand, most semantic information is lost while importing BIM models into AR/VR engines. On the other hand, huge and complicated BIM models can increase the time for model transfer, increase the computation work load while rendering, and reduce the fluency when using AR/VR applications. Therefore, this paper aims to develop efficient mechanisms for BIM-to-AR/VR data transfer to better utilize the information of BIM. In this paper, an ontology-based approach is proposed to transfer semantic information of BIM. Building components in geometric models are classified according to their features and simplified with different polygon reduction methods. As shown in the experimental validation, the proposed mechanisms have the capability to efficiently transfer semantic information of BIM to AR/VR, greatly reduce the number of triangles for geometric models while maximizing the consistency of the overall shape, and improve the framerate in corresponding AR/VR applications. N.A.
HKUST A semi-automated approach to generate 4D/5D BIM models for evaluating different offshore oil and gas platform decommissioning options Journal 07/2017 Cheng, J.C.P., Tan, Y., Song, Y., Liu, X., and Wang, X. Background
Offshore oil and gas platforms generally have a lifetime of 30 to 40 years, and platform decommissioning is a major issue because many of the existing offshore oil and gas platforms are reaching the end of their service life. There are many possible options for decommissioning offshore oil and gas platforms, and each decommissioning option can be implemented using different methods and technologies. Therefore, it is necessary to have a clear understanding and in-depth evaluation of each decommissioning option before commencing platform decommissioning. 4D and 5D building information modeling (BIM) has been commonly used in the building industry to analyze constructability and to evaluate different construction or demolition plans. However, application of BIM in the oil and gas industry, especially for the platform decommissioning process, is still limited.
This paper suggests and demonstrates the application of 4D and 5D BIM technology to simulate various methodologies to realize various selected offshore platform decommissioning options, thereby visualizing and evaluating different options, considering both the time and resources required for decommissioning process. One hundred and seventy-seven offshore platform decommissioning options are summarized in this paper. A new approach to create multiple 4D/5D BIM models in a semi-automated manner for evaluating various scenario options of OOGP decommissioning was proposed to reduce the model creation time as current way of 4D/5D BIM model creation for each OOGP decommissioning option is time consuming.

In the proposed approach, an OOGP BIM model relationship database that contains possible 4D/5D BIM model relationships (i.e. schedules for different decommissioning methods) for different parts of an OOGP was generated. Different OOGP decommissioning options can be simulated and visualized with 4D/5D BIM models created by automatically matching schedules, resources, cost information and 3D BIM models. This paper also presents an illustrative example of the proposed approach, which simulates and evaluates two decommissioning options of a fixed jacket platform, namely Rig-to-Reef and Removal-to-Shore. As compared to the traditional approach of 4D/5D BIM model generation, the proposed semi-automated approach reduces the model generation time by 58.8% in the illustrative example.

The proposed approach of semi-automated 4D/5D BIM model creation can help understand the implication of different decommissioning options as well as applied methods, detecting potential lifting clashes, and reducing 4D/5D BIM model creation time, leading to better planning and execution for the decommissioning of offshore oil and gas platforms. In addition, with the proposed semi-automated approach, the 4D/5D BIM model can be generated in a more efficient manner.
HKUST Social BIMCloud: A distributed cloud-based BIM platform for object-based lifecycle information exchange Journal 03/2015 Das, M., Cheng, J.C.P., and Kumar, S. Background
The architecture, engineering and construction (AEC) industry lacks a framework for capturing, managing, and exchanging project, product, and social information over the lifecycle of a building. The current tools have various limitations, such as lack of interoperability, slow to transfer huge building model files, and possibility of data inconsistency.

In this paper, we present a cloud-based BIM server framework namely Social BIMCloud that facilitates BIM information exchange through dynamic merging and splitting of building models. The data model of Social BIMCloud is based on but not limited to IFC. The data model of Social BIMCloud was further extended to accommodate social interactions, by studying the formal modes of communication in the AEC industry. An object-based approach to capture and manage social interactions in AEC projects through a BIM-based visual user interface was also developed and demonstrated.

Social BIMCloud addresses the issues of inefficient data transfer speed and data inconsistency in a distributed environment by facilitating the storage and partial exchange of integrated nD BIM models. Data interoperability is facilitated through open BIM standards such as IFC and direct integration with construction software. High performance, scalability, fault tolerance, and cost effectiveness are facilitated through data partitioning, data replication strategies, multi-node structures, and pay-per-use tariff systems, respectively, through a cloud-based NoSQL database.

The Social BIMCloud framework helps to develop and exchange BIM models, which are rich in project information such as social interactions, cost, and energy analyses. This framework improves the communication efficiency between project participants, leading to better designs and less rework. The information captured by this framework could also be useful to determine important metrics such as industry trends, relationships among project participants, and user requirements.
HKUST BIM-Based Daylighting and Energy Analysis on UG Hall 7 of HKUST Report 06/2016 Tianzhu QIN
Huan HE
BIM is a three-dimensional digital based model or technology with various project-related information inside. It is widely used in modern building industry. As buildings are consuming so much energy today, building energy save has become an important part of a project’s optimization. To achieve the purpose of saving and controlling a building's energy consumption by BIM related software prediction and adjustment and control is a simple and effective strategy.

This project aims to make energy-saving analyzes of STUDENT HALL 7 of HKUST, the main study method is: Revit 3D model—Green Building Studio energy analysis—solar panel analysis—PVGIS analysis—ECOTECT environmental analysis. Firstly obtained the three-dimensional model of Hall 7 through REVIT, and then send the model to Autodesk Green Building Studio to make energy consumption analysis, than make solar panel analysis of the building to find the energy save of panels, afterwards use PVGIS to check if the saving ratio is rational. What’s more, we also import the REVIT into ECOTECT to make further analysis.
HKUST As-built BIM Model Verification Through Field Inspection and Laser Scanning: A Comparative Study Report 06/2020 HUANG, Cong
ZHOU Haoran
BIM model is a prerequisite for the Operation and Maintenance (O&M) of sustainable buildings. Only after having a reliable BIM model can start O&M related work, such as space management and energy management, all these works needs to confirm the accuracy of the BIM model. In this project, the author conducted a verify of the BIM model to ensure that the model was correct before the O&M work started.
This project first compared various survey methods, and based on their advantages and disadvantages, chose the laser scanning method and manual survey method for experiments. Then using two selected methods to do site surveying for HUKUST parking lot and LTK to SENG Commons. And the end, given survey recommendations for different types of as-built model verification based on the survey result.