Inertial Measurement Unit (IMU) sensors have been used in mobile devices such as smartwatches lately. The data acquired can be used in sports analytics. A recent study shows how this technology may be used to analyse ballroom dance figures.
A single Samsung Gear Live smart watch per dancing couple was sufficient to successfully classify movement segments from the International Standard Waltz. Seven different machine learning strategies were compared, and it was shown that neural networks approach outperforms random forests technique. The accuracy was further improved by using the fact that the transitions between figures are memoryless and determining which figure transitions are possible according to the rules of waltz. The maximal improved accuracy was 92.31%. The technology suggested by this paper can be used by judges and dancers themselves whether or not they are dancing the figures correctly.
Inertial Measurement Unit (IMU) sensors are being increasingly used to detect human gestures and movements. Using a single IMU sensor, whole body movement recognition remains a hard problem because movements may not be adequately captured by the sensor. In this paper, we present a whole body movement detection study using a single smart watch in the context of ballroom dancing. Deep learning representations are used to classify well-defined sequences of movements, called figures. Those representations are found to outperform ensembles of random forests and hidden Markov models. The classification accuracy of 85.95 % was improved to 92.31 % by modeling a dance as a first-order Markov chain of figures and correcting estimates of the immediately preceding figure.