BIM-AIoT data for indoor environment monitoring

The dataset includes BIM-IoT integration data such as Revit model, images, and IoT time-series data. The abstract is as follows: Automatic indoor environmental quality (IEQ) monitoring plays a pivotal role in the management of green building operations. Traditional monitoring methods that integrate Building Information Modeling (BIM) and the Internet of Things (IoT) are unable to perform automatic detection. This study addresses the limitation by introducing a BIM-AIoT based ‘LabMonitor’ approach for real-time IEQ monitoring and prediction. To enhance the accuracy of detecting occupants’ comfort, a convolutional neural network (CNN) based YOLOv8 model is utilized. The effectiveness of the proposed approach is validated in an engineering laboratory within a university setting. Results demonstrated that the BIM-AIoT based ‘LabMonitor’ approach achieves a high mean average precision (mAP) of 0.939 in real-time indoor comfort level detection tasks. This work provides a scalable and interoperable solution for smart engineering laboratory management, addressing key challenges in multimodal data fusion and automatic real-time monitoring.