Creating and benchmarking a new dataset for physical activity monitoring

摘要: Physical activity monitoring has recently become an important field in wearable computing research. However, there is a lack of commonly used, standard dataset and established benchmarking problems. In this work, new for physical --- recorded from 9 subjects, wearing 3 inertial measurement units heart rate monitor, performing 18 different activities created made publicly available. Moreover, 4 classification problems are benchmarked on the dataset, using data processing chain 5 classifiers. The benchmark shows difficulty tasks exposes some challenges, defined by e.g. high number personalization.