publications

2024

1. AutoCon

   Unmanned aerial vehicle-based as-built surveys of buildings

   Tianzhi He , Kaiwen Chen , Farrokh Jazizadeh , and 1 more author

   Automation in Construction, 2024

   Journal Abs Bib HTML PDF

   This is a Journal Paper

   Camera-equipped Unmanned Aerial Vehicles (UAVs) are effective tools for as-built building surveys. Through a systematic literature review, we synthesized and categorized factors affecting the quality of UAV-based reconstructed scenes and their associated performance evaluation metrics (e.g., accuracy and time efficiency). Their interrelationships were analyzed by Social Network Analysis (SNA) to identify critical factors and their impacts. We further quantitatively evaluated these factors and metrics through controlled experiments with a camera-equipped UAV and a Terrestrial Laser Scanner for an institutional building. Various flight paths, photo overlaps, and distances to the building were tested to evaluate their impact on dimensional accuracy, time efficiency, and point cloud density. We demonstrated the trade-offs between the influential factors to provide insights into parameter selection. Additionally, a data requirements schema for UAV-based as-built 3D scene reconstruction was established toward standardization of data processing practices. This study could serve as a foundation for future research and applications of UAV-based photogrammetry for building surveys.

   @article{he2024unmanned,
     title = {Unmanned aerial vehicle-based as-built surveys of buildings},
     author = {He, Tianzhi and Chen, Kaiwen and Jazizadeh, Farrokh and Reichard, Georg},
     journal = {Automation in Construction},
     volume = {161},
     pages = {105323},
     year = {2024},
     publisher = {Elsevier},
     doi = {10.1016/j.autcon.2024.105323},
   }

2023

1. JCEM

   Geographical imbalance and influential characteristics of the green building market

   Ruidong Chang , Tianzhi He , Yilong Han , and 2 more authors

   Journal of Construction Engineering and Management, 2023

   Journal Abs Bib HTML PDF

   This is a Journal Paper

   Green buildings have gained increasing momentum during the past decade, evidenced by an uptick in green building construction worldwide. To facilitate green building development, it is crucial to understand the current geographical distribution of green buildings, thereby identifying emerging markets and opportunities for future growth. However, very few studies investigated the spatial characteristics of the green building market and the factors influencing the distribution of green buildings. By examining the national green building market in the United States, we studied the spatial distribution patterns and significant influencing factors of the county-level US green building markets. Cluster mapping and hot spots of the green building markets were identified through spatial autocorrelation analysis. A spatial regression model with high performance (of 0.83) was developed to identify the significant influencing factors. We found a statistically significant clustering phenomenon of county-level US green building markets. The spatial error model reveals that three factors, namely, the number of housing units, gross domestic product, and the local green building company index, significantly influence the number of green buildings at the county level. We also found that the county-level green building market is influenced by these factors of not only the host county, but also the neighboring counties. Our findings provide a useful reference for stakeholders’ decision-making process concerning local green building market development.

   @article{chang2023geographical,
     title = {Geographical imbalance and influential characteristics of the green building market},
     author = {Chang, Ruidong and He, Tianzhi and Han, Yilong and Xue, Rui and Zhang, Wei Emma},
     journal = {Journal of Construction Engineering and Management},
     volume = {149},
     number = {10},
     pages = {04023093},
     year = {2023},
     publisher = {American Society of Civil Engineers},
     doi = {10.1061/JCEMD4.COENG-12971},
   }

2022

1. CRC

   Nudging Occupants for Energy-Saving through Voice-Based Proactive Virtual Assistants

   Tianzhi He , and Farrokh Jazizadeh

   In Construction Research Congress 2022 , 2022

   Conference Abs Bib HTML PDF

   This is a Conference Paper

   With the advancement of the Internet of Things (IoT) technologies, smart homes have promoted human-building interaction and sustainability in occupants’ daily life. The rise of voice-based AI-powered virtual assistants has brought new potentials to provide occupants with a convenient and intuitive interface to interact with smart homes. Aiming at enhancing the human-building bi-directional communication, voice-based proactive virtual assistants integrated with smart home ecosystems—that is, Smart Home Assistants (SHAs)—were investigated in this study. A comprehensive data collection was conducted through an online experiment, in which 307 valid questionnaire responses with participants’ demographic background information and their feedback to proactive SHAs were collected. Occupants’ perception of the proactive SHAs was evaluated among different groups of users with various demographic backgrounds. Five occupants’ socio-demographic background features were identified to have a significant impact on their acceptance level to the energy-saving suggestions by proactive SHAs, including gender, age, education level, employment status, and the number of occupants in a residence. By utilizing these demographic features, ensemble learning models can predict occupants’ perception of proactive SHAs with good performance (accuracy in the range of 0.69–0.75). Findings in this study will provide a valuable reference for academic researchers and industry practitioners in the development of personalized proactive smart home systems for human-building interaction.

   @inproceedings{he2022nudging,
     title = {Nudging Occupants for Energy-Saving through Voice-Based Proactive Virtual Assistants},
     author = {He, Tianzhi and Jazizadeh, Farrokh},
     booktitle = {Construction Research Congress 2022},
     pages = {402--411},
     year = {2022},
     doi = {10.1061/9780784483961.043},
   }

2021

1. I3CE

   Proactive Smart Home Assistants for Automation—User Characteristic-Based Preference Prediction with Machine Learning Techniques

   Tianzhi He , and Farrokh Jazizadeh

   In Computing in Civil Engineering 2021 , 2021

   Conference Abs Bib HTML PDF

   This is a Conference Paper

   AI-powered smart homes bring high-quality intelligent services to occupants with digital virtual assistants. Through interactions with occupants, the smart home assistants (SHAs) can develop occupants’ profiles using a number of personal characteristic features for tailored and smart interactions. Based on these profiles, smart home systems can proactively offer automation services while conserving occupants’ comfort and convenience. In this study, we have sought to investigate characteristic features that affect occupants’ perception of the proactive concept, as well as their preferences for modes of interactions through an application of automation for energy efficiency management. Upon a data collection through an online experiment on campus, 58 valid responses with personal characteristic features were utilized to develop predictive machine learning models. These models can predict participants’ general attitude towards proactive SHAs, as well as their preferences for interaction modes with good performance (accuracy between 0.67 and 0.82 and F-score between 0.66 and 0.74). Various features were identified to have considerable significance, including personal beliefs of taking actions and energy expenses, as well as environmental protection values. The findings of this study provide an insight into the design of learning processes for virtual assistants in smart home ecosystems and the effect of the individual characteristics on the users’ preferences for interactions with SHAs.

   @incollection{he2021proactive,
     title = {Proactive Smart Home Assistants for Automation—User Characteristic-Based Preference Prediction with Machine Learning Techniques},
     author = {He, Tianzhi and Jazizadeh, Farrokh},
     booktitle = {Computing in Civil Engineering 2021},
     pages = {271--278},
     year = {2021},
     doi = {10.1061/9780784483893.034},
   }

2020

1. CRC

   Exploring the Development Trends and Characteristics of the US Green Building Market

   Tianzhi He , Ruidong Chang , Yilong Han , and 1 more author

   In Construction Research Congress 2020 , 2020

   Conference Abs Bib HTML PDF

   This is a Conference Paper

   The AEC industry has witnessed an increasing growth in the green building market in the past decade and continues to expect its promising future. While most of the prior research on the green building market was conducted based on the survey data at the project level, how the corporate dimension develops is still lacking. To fill the gap, this research attempted to explore the characteristics of the U.S. green building market from a corporate perspective both quantitatively and qualitatively. We first collected data of 223 top/representative green building contractors in the U.S. identified by the Engineering News-Record over the past decade, and explored the development trend. The 223 organizations were further categorized into three different groups with distinct characteristics and corporate strategy using k-means clustering. This research provided practitioners and academics with a holistic understanding of the U.S. green building market, as well as contributed to the development of green building corporation management strategy.

   @inproceedings{he2020exploring,
     title = {Exploring the Development Trends and Characteristics of the US Green Building Market},
     author = {He, Tianzhi and Chang, Ruidong and Han, Yilong and Yang, Ziyi},
     booktitle = {Construction Research Congress 2020},
     pages = {914--923},
     year = {2020},
     organization = {American Society of Civil Engineers Reston, VA},
     doi = {10.1061/9780784482858.098},
   }