A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Proximity Detection on Construction Sites, Using Bluetooth Low Energy Beacons
Construction sites can be hazardous when workers perform their work in proximity of danger zones, which might lead to workplace fatalities. The majority of injuries and fatalities result from workers being struck by moving vehicles and entering danger zones. This paper presents a newly developed proximity detection system for estimating workers’ location using Bluetooth Low Energy (BLE) technology. The paper focuses on the development of an RSSI-distance relationship model between the transmitting and receiving beacons. Such a model is critical for the deployment of any BLE-based localization system. A set of laboratory experiments were designed and performed to develop that distance prediction model while evaluating the impact of contextual features on the model’s performance. A variety of machine learning models, as well as conventional curve-fitting methods, were evaluated for their respective suitability in the development of the RSS-distance relationship. The results show that the model with the best performance achieves an average error of 64 cm in distance prediction, through Random Forest ensemble learning. This level of accuracy is an improvement compared to the previous literature and can be considered good enough for most proximity detection use cases on construction jobsites. The impact of environmental conditions, such as the weather, availability of metal and construction equipment, on the model’s performance must be studied in future works.
Proximity Detection on Construction Sites, Using Bluetooth Low Energy Beacons
Construction sites can be hazardous when workers perform their work in proximity of danger zones, which might lead to workplace fatalities. The majority of injuries and fatalities result from workers being struck by moving vehicles and entering danger zones. This paper presents a newly developed proximity detection system for estimating workers’ location using Bluetooth Low Energy (BLE) technology. The paper focuses on the development of an RSSI-distance relationship model between the transmitting and receiving beacons. Such a model is critical for the deployment of any BLE-based localization system. A set of laboratory experiments were designed and performed to develop that distance prediction model while evaluating the impact of contextual features on the model’s performance. A variety of machine learning models, as well as conventional curve-fitting methods, were evaluated for their respective suitability in the development of the RSS-distance relationship. The results show that the model with the best performance achieves an average error of 64 cm in distance prediction, through Random Forest ensemble learning. This level of accuracy is an improvement compared to the previous literature and can be considered good enough for most proximity detection use cases on construction jobsites. The impact of environmental conditions, such as the weather, availability of metal and construction equipment, on the model’s performance must be studied in future works.
Proximity Detection on Construction Sites, Using Bluetooth Low Energy Beacons
Lecture Notes in Civil Engineering
Walbridge, Scott (editor) / Nik-Bakht, Mazdak (editor) / Ng, Kelvin Tsun Wai (editor) / Shome, Manas (editor) / Alam, M. Shahria (editor) / el Damatty, Ashraf (editor) / Lovegrove, Gordon (editor) / Mohammadali, Khazen (author) / Mazdak, Nik-Bakht (author) / Osama, Moselhi (author)
Canadian Society of Civil Engineering Annual Conference ; 2021
Proceedings of the Canadian Society of Civil Engineering Annual Conference 2021 ; Chapter: 20 ; 215-226
2022-05-18
12 pages
Article/Chapter (Book)
Electronic Resource
English
Leveraging Bluetooth Consumer Electronics as Proximity Sensors to Construction Health Hazards
| Taylor & Francis Verlag | 2013
SYSTEMS AND METHODS FOR IMPLEMENTING A PROXIMITY LOCK USING BLUETOOTH LOW ENERGY
| European Patent Office | 2017
SYSTEMS AND METHODS FOR IMPLEMENTING A PROXIMITY LOCK USING BLUETOOTH LOW ENERGY
| European Patent Office | 2017
SYSTEMS AND METHODS FOR IMPLEMENTING A PROXIMITY LOCK USING BLUETOOTH LOW ENERGY
| European Patent Office | 2019