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%.
Transportation mode recognition based on smartphone embedded sensors for carbon footprint estimation
2016-11-01
517044 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
British Library Online Contents | 2019
|Individual trip mode recognition based on smartphone GPS positioning data
British Library Conference Proceedings | 2022
|