VB

V. Bhatt

info

Please Note

2 records found

Developing a System for Indoor Temperature Prediction Using OGC, IFC Semantics and XGBoost

Master thesis (2025) - V. Bhatt, A. Rafiee, J. Schembri
Buildings require increasing attention to indoor environmental conditions, while installing sensors in every room is costly and impractical. This thesis develops an interoperable system for predicting indoor temperature in uninstrumented building spaces by integrating Building Information Modeling (BIM), Internet of Things (IoT) sensor data, and machine learning through open standards. IFC-based building geometry and semantics are combined with sensor observations managed through the OGC SensorThings API and FROST, while an XGBoost regression model is used to predict indoor temperature. The developed workflow successfully links spatial building information with time-series sensor data and extracts features such as room volume, window area, orientation, and solar inflow. The model identified solar inflow, external temperature, and room volume as the most influential predictors and demonstrated stable performance across rooms, indicating potential for predicting conditions in non-instrumented spaces. The standards-based architecture also enabled efficient data retrieval and integration of additional environmental parameters such as CO2 and noise. Despite limitations related to data availability, sensor coverage and seasonal variation, the study demonstrates the feasibility of a scalable framework for data-driven building performance analysis and provides a foundation for interoperable digital twins and future environmental monitoring and decision support.
...

Synthesis project report

The declining availability of practical hours for medical anatomical education has prompted Enatom to develop a digital anatomical platform, utilizing the open-source WebGL-based point cloud renderer Potree. This platform, which employs detailed point cloud scans of anatomical structures, aims to offer a dynamic and interactive educational experience. Although Enatom's focus is not directly on geomatics, the techniques employed in this project have strong parallels with those used in geomatics, thereby enabling a symbiotic exchange of expertise. This interdisciplinary approach enhances the development of Enatom’s digital platform, with the potential to contribute to the field of geomatics. To address existing user experience challenges, this project has added a lasso-selection tool tailored for Potree, advanced annotation capabilities, and methods for sensitive data anonymization within the point cloud. The project's outcomes will be available in an open-source format at https://github.com/GEO1101-Synthesis-Group4/Selection-Annotation-Repo. This project exemplifies the versatile application of geomatics expertise beyond its traditional scope, demonstrating its potential in enhancing diverse domains such as medical education. ...