Codebook approach for sensor-based human activity recognition
Kimiaki Shirahama, Lukas Köping, Marcin Grzegorzek · 2016
One crucial problem in sensor-based human activity recognition is how to model features that can precisely represent characteristics of a sequence of sensor values. For this, we study a codebook approach that represents the sequence as a distribution of characteristic subsequences. The extensive experiments on different recognition tasks for physical, mental and eye-based activities validate the effectiveness, generality and usability of the codebook approach, where only a few intuitive parameters need to be tuned.