2018/03/06 by Maarten Bieshaar, Bieshaar, Maarten
Computer Science · Social Sciences · #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #Context-Aware Activity Recognition Systems #FOS: Computer and information sciences #Human Mobility and Location-Based Analysis #Human-Computer Interaction (cs.HC) #Innovative Human-Technology Interaction #User Authentication and Security Systems
paper · pdf · doi:10.48550/arxiv.1803.02097
openalex publication_date 2018/03/06 · openalex created_date 2022/10/01 · openalex updated_date 2026/07/28
This article describes an approach to detect the wearing location of smart\ndevices worn by pedestrians and cyclists. The detection, which is based solely\non the sensors of the smart devices, is important context-information which can\nbe used to parametrize subsequent algorithms, e.g. for dead reckoning or\nintention detection to improve the safety of vulnerable road users. The wearing\nlocation recognition can in terms of Organic Computing (OC) be seen as a step\ntowards self-awareness and self-adaptation. For the wearing location detection\na two-stage process is presented. It is subdivided into moving detection\nfollowed by the wearing location classification. Finally, the approach is\nevaluated on a real world dataset consisting of pedestrians and cyclists.\n