Kick-scooters detection in sensor-based transportation mode classification methods⁎⁎This work was part of the project CAPTIMOVE funded by the IDEX of University Grenoble Alpes (call for projects "Initiatives de Recherche Strategiques (IRS)") (ANR-15-IDEX-02). This work was also supported by the Erench National Research Agency in the framework of the Investissements d’avenir program (ANR-10-AIRT-05). The sponsors had no involvement in the design of the study, the collection, analysis and interpretation of data, and in writing the manuscript. This work further forms part of a broader translational and interdisciplinary research program, GaitAlps.The graphical content used in this paper was designed by macrovector / Ereepik and Flaticon.com.

In this work we present a novel classification model that can detect kick-scooters from inertial and pressure sensors. The detection is performed with kick-scooters being trained with other activities and transportation modes including still, walking, biking, taking bus and tramway. Results show that kick-scooters can be precisely detected up to 99% for three different sensor placements: on-foot, waist-attached and in the trouser’s pocket. Thus, this paper provides a first contribution where kick-scooters can be classified and studied for further applications such as mobility behavior analysis and navigation.