Clustering based transfer detection with fuzzy activity recognition from smart-phone GPS trajectories

This paper introduces an adaptive clustering-based transfer detection framework. Existing transfer detection algorithms are based on a walking-based approach. But in a walking-based approach it is difficult to set a deterministic walking threshold. However during transfer people generally move slowly or wait for a while and thus the spatio-temporal points are located close to each other and tend to form clusters. To mitigate such problems an adaptive density-based fuzzy approach is proposed for detecting transfers and activities performed during transfers.