A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Health monitoring of historic buildings using machine learning in real-time internet of things (IoT)
In this paper, structural health monitoring (SHM) is used to detect the damage level for the historic building. The damaged level is defined based on the support vector machine (SVM) algorithm to extract the damage feature. Physical checks allow us to detect any damage or structural degeneration. Supervised training machine learning (ML) is used as a tool to examine accelerometer data to ascertain the condition of structures following an occurrence. The three training models, the SVM, the random forest linear classification, and the k-nearest neighbor (KNN) model are tested and compared to classify data. The data obtained from structural health monitoring, teams of responders, and investigators can be used to manage the most vulnerable structures. The accuracy of the SVM algorithm was found up to 94% accurate and precise, at a high level. The internet of things (IoT) architecture is also introduced with SVM learning algorithms for early warning. The proposed system makes use of an SHM system to identify seismic events or accelerations. The IoT system SHM uses real data from the structure, allowing for online damage identification and ongoing monitoring. A dashboard is used to represent the monitoring data and the damage level.
Health monitoring of historic buildings using machine learning in real-time internet of things (IoT)
In this paper, structural health monitoring (SHM) is used to detect the damage level for the historic building. The damaged level is defined based on the support vector machine (SVM) algorithm to extract the damage feature. Physical checks allow us to detect any damage or structural degeneration. Supervised training machine learning (ML) is used as a tool to examine accelerometer data to ascertain the condition of structures following an occurrence. The three training models, the SVM, the random forest linear classification, and the k-nearest neighbor (KNN) model are tested and compared to classify data. The data obtained from structural health monitoring, teams of responders, and investigators can be used to manage the most vulnerable structures. The accuracy of the SVM algorithm was found up to 94% accurate and precise, at a high level. The internet of things (IoT) architecture is also introduced with SVM learning algorithms for early warning. The proposed system makes use of an SHM system to identify seismic events or accelerations. The IoT system SHM uses real data from the structure, allowing for online damage identification and ongoing monitoring. A dashboard is used to represent the monitoring data and the damage level.
Health monitoring of historic buildings using machine learning in real-time internet of things (IoT)
Eldeib, Ahmed H. (author) / Abdelsalam, Ahmed Mohamed (author) / Shehata, Ahmed M. (author) / Ali, Hesham Sayed Kamel (author) / Fouad, Sara (author)
2023-11-01
Indonesian Journal of Electrical Engineering and Computer Science; Vol 32, No 2: November 2023; 725-733 ; 2502-4760 ; 2502-4752 ; 10.11591/ijeecs.v32.i2
Article (Journal)
Electronic Resource
English
Real-Time Health Monitoring of Historic Buildings with Wireless Sensor Networks
| British Library Conference Proceedings | 2009
Online Contents | 1995
| Springer Verlag | 2020
British Library Online Contents | 1993
Internet of things enabled real time water quality monitoring system
| Springer Verlag | 2016