A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Measuring distance using ultra-wideband radio technology enhanced by extreme gradient boosting decision tree (XGBoost)
Abstract Measuring distance is critical for safety and quality in construction and operation of engineering structures. This paper proposes a framework to utilize cost-effective and robust ultra-wideband radio technology for wireless sensing of distance, presents a machine learning method based on extreme gradient boosting decision tree, and incorporates error mitigation methods to improve the measurement accuracy. In-situ measurement of distance for a highway bridge in operation was conducted to evaluate the performance of the proposed methods which demonstrated a sub-millimeter accuracy of distance measurement. The proposed methods show desired accuracy, cost-effectiveness, and robustness to the environment, and reveal a tradeoff between the accuracy and frequency of distance measurement. The tradeoff can be used to optimize the sensing system and signal processing program to satisfy the requirements in different applications. This study is expected to advance the capability of measuring distance in various automation processes for construction and operation of engineering structures.
Highlights A cost-effective wireless distance measurement method is presented using ultra-wideband radio. A machine learning technique is used to increase the measurement accuracy to sub-mm level. Tradeoff between sampling frequency and accuracy can be used to reconfigure the system. Laboratory and field tests are used to evaluate the performance of the proposed method.
Measuring distance using ultra-wideband radio technology enhanced by extreme gradient boosting decision tree (XGBoost)
Abstract Measuring distance is critical for safety and quality in construction and operation of engineering structures. This paper proposes a framework to utilize cost-effective and robust ultra-wideband radio technology for wireless sensing of distance, presents a machine learning method based on extreme gradient boosting decision tree, and incorporates error mitigation methods to improve the measurement accuracy. In-situ measurement of distance for a highway bridge in operation was conducted to evaluate the performance of the proposed methods which demonstrated a sub-millimeter accuracy of distance measurement. The proposed methods show desired accuracy, cost-effectiveness, and robustness to the environment, and reveal a tradeoff between the accuracy and frequency of distance measurement. The tradeoff can be used to optimize the sensing system and signal processing program to satisfy the requirements in different applications. This study is expected to advance the capability of measuring distance in various automation processes for construction and operation of engineering structures.
Highlights A cost-effective wireless distance measurement method is presented using ultra-wideband radio. A machine learning technique is used to increase the measurement accuracy to sub-mm level. Tradeoff between sampling frequency and accuracy can be used to reconfigure the system. Laboratory and field tests are used to evaluate the performance of the proposed method.
Measuring distance using ultra-wideband radio technology enhanced by extreme gradient boosting decision tree (XGBoost)
Liu, Yiming (author) / Liu, Lin (author) / Yang, Liu (author) / Hao, Li (author) / Bao, Yi (author)
2021-03-16
Article (Journal)
Electronic Resource
English
Using extreme gradient boosting (XGBoost) machine learning to predict construction cost overruns
| Taylor & Francis Verlag | 2024
| DOAJ | 2022