HASC2011corpus: towards the common ground of human activity recognition
Proceedings of the 13th international conference on Ubiquitous computing
On the feasibility of user de-anonymization from shared mobile sensor data
Proceedings of the Third International Workshop on Sensing Applications on Mobile Phones
The Journal of Machine Learning Research
Personal and Ubiquitous Computing
Hi-index | 0.00 |
In this paper, we show a large-scale activity gathering system with mobile sensor devices such as smart phones and accelerometers. We gathered over 35,000 activity data points from more than 200 people over approximately 13 months. We describe the design rationale of the system, and analyze the gathered data through statistics, clustering, and application of an existing activity recognition method. Our results show that there is a challenging field for activity recognition in larger-scale activity data.