Answers are grounded in this paper and cite their sources.
Thanks to the increase in processing power and in the number of sensors present in today's mobile devices, context-aware applications have gained a renewed interest. This paper focuses on a particular type of context, the transportation mode used by a person for carbon footprint estimation and it summarizes a method for automatically classifying different transportation modes with a smartphone. The method was evaluated with real data presenting promising results: a performance of around 94% was obtained when classifying 7 different classes with a random forest followed by a Discrete Hidden Markov Model (DHMM) filtering and accelerometer and magnetometer based features while the addition of the GPS improved the performance up to 96%.
No takes yet. Share an insight, caveat, or question.
Lorintiu et al. (2016) studied this question.
Synapse has enriched 7 closely related papers on similar clinical questions. Consider them for comparative context: