On-body device position awareness plays an important role in providing smartphone-based services with high levels of usability and quality. Traditionally, the problem assumed that the positions that were supported by the system were fixed at the time of design. Thus, if a user stores his/her terminal into an unsupported position, the system forcibly classifies it into one of the supported positions. In contrast, we propose a framework to discover new positions that are not initially supported by the system, which adds them as recognition targets via labeling by a user and re-training on-the-fly. In this article, we focus on a component of identifying a set of samples that are derived from a single storing position, which we call new position candidate identification. Clustering is applied as a key component to prepare a reliable dataset for re-training and to reduce the user’s burden of labeling. Specifically, density-based spatial clustering of applications with noise (DBSCAN) is employed because it does not require the number of clusters in advance. We propose a method of finding an optimal value of a main parameter, Eps-neighborhood (eps), which affects the accuracy of the resultant clusters. Simulation-based experiments show that the proposed method performs as if the number of new positions were known in advance. Furthermore, we clarify the timing of performing the new position candidate identification process, in which we propose criteria for qualifying a cluster as the one comprising a new position.
New Position Candidate Identification via Clustering toward an Extensible On-Body Smartphone Localization System