On the Generality of Codebook Approach for Sensor-Based Human Activity Recognition

• DOI: 10.3390/electronics6020044
• Publication Date: 2017-06-01T14:36:36Z
• Authors: Kimiaki Shirahama; Marcin Grzegorzek
• Keywords: Generality; Feature (linguistics); Activity Recognition; Sequence (biology); Similarity (geometry)

With the recent spread of mobile devices equipped with different sensors, it is possible to continuously recognise and monitor activities in daily life. This sensor-based human activity recognition formulated as sequence classification categorise sequences sensor values into appropriate classes. One crucial problem how model features that can precisely represent characteristics each lead accurate recognition. It laborious and/or difficult hand-craft such based on prior knowledge manual investigation about data. To overcome this, we focus a feature learning approach extracts useful from large amount In particular, adopt simple but effective one, called codebook approach, which groups numerous subsequences collected clusters. Each cluster centre codeword represents statistically distinctive subsequence. Then, encoded expressing distribution codewords. The extensive experiments tasks for physical, mental eye-based validate effectiveness, generality usability approach.