Knowledge Graphs for Cataloging and Making Sense of Smart City Data
Name
Kaspar Kadalipp
Abstract
Modern buildings and cities are equipped with a large number of devices with sensors that generate data. However, this data is often stored in a technical format that is more convenient for the sensors, making it difficult for humans to understand. This thesis deals with the challenge of interpreting the complex data generated by the numerous sensors, using the Tartu Cumulocity IoT platform dataset as a case study. To get an overview of the available data and identify issues with analyzing it further, the dataset was visualized as a simplified knowledge graph. In addition, a hierarchical topic model was created to capture the nuances of various smart city domains from the dataset.
Graduation Thesis language
English
Graduation Thesis type
Master - Computer Science
Supervisor(s)
Pelle Jakovits
Defence year
2024