Finding Points-of-Interest (PoIs) from Life-logging and Location Trace Data

In this paper, we perform an analytical study on finding Points-of-Interest (PoIs) from life-logging and location trace data. The dataset is collected from thirty subjects in the real-world environment using our smartphone-based life-logging system. We adopt density-based DBSCAN clustering algorithm to extract PoIs from location traces, and apply statistical analysis to decide optimal clustering parameters empirically. By verifying the correlation and strength of association between the clustering result and place labels, we conclude that it is possible to infer the semantic label of the place from the accumulated life-logging and location data.