The Mobile Sensing Platform: An Embedded Activity Recognition System
IEEE Pervasive Computing
Activity Recognition for Everyday Life on Mobile Phones
UAHCI '09 Proceedings of the 5th International on ConferenceUniversal Access in Human-Computer Interaction. Part II: Intelligent and Ubiquitous Interaction Environments
Location and activity recognition using ewatch: a wearable sensor platform
Ambient Intelligence in Everyday Life
Identification of postural transitions using a waist-located inertial sensor
IWANN'13 Proceedings of the 12th international conference on Artificial Neural Networks: advences in computational intelligence - Volume Part II
Hi-index | 0.00 |
Sufficient physical activity is required for everybody, especially for elderly people. Monitoring of physical activity is possible in daily life by using mobile sensors such as acceleration sensors. The recognition of periodic activity types like walking, cycling, car driving etc. is easy to perform. However, the identification of transitions between physical activities is difficult, because those events are nonrecurring and unique. The estimation about the share of standing or sitting during work is interesting for the design of the modern workplace. Human ergonomics demand for a limitation of standing work; this may even be enforced by the legal protection of working mothers to improve the working condition. The recognition of standing and sitting is furthermore useful within the home living area design. Hereby a detection of staying, sitting and walking supports the assessment of the activities of daily life. This paper addresses the methodology of mobile physical activity recognition of transitions between sitting and standing by using only one three-dimensional acceleration sensor. The recognition is performed by using a synthetic kernel signal and a correlation of the measurement signal. For the evaluation, a detection application has been developed which uses the build-in sensors of a standard mobile phone. The evaluation included 12 subjects and the result shows that mobile recognition of activity transitions is possible.