Applicability of DBSCAN in Identifying the Candidates of New Positions in On-Body Smartphone Localization Problem

Position recognition contributes to the provision of useful and reliable smartphone-based services. Existing on-body localization approaches for smartphone deal with predetermined positions. We have proposed a framework for detecting new positions at the usage stage and expanding the target for recognition. In this paper, we present a preliminary experiment on the design of a component to identify new position candidates using density-based spatial clustering of applications with noise (DBSCAN) clustering.