Galkin O.A.
Recognition of actions of medical workers on the basis of readings of accelerometers using a deep belief network

This paper analyzes a real set of large-volume medico-statistical data used for the recognition of actions of medical workers on the basis of accelerometer readings at definite moments of time. During the recognition process, a deep belief network was applied to unlabeled data, and then it was supervisedly learned using the error backpropagation method. The obtained results demonstrate higher recognition accuracy in comparison with basic methods. A considerable improvement in medical staff productivity is also achieved. © 2016, Springer Science+Business Media New York.

Keywords: accelerometer, deep belief network, deep neural network, Accelerometers, Deep belief networks, Error back-propagation, Large volumes, Recognition accuracy, Recognition process, Statistical datas, Unlabeled data, Deep neural networks

Cite:
Galkin O.A. (2016). Recognition of actions of medical workers on the basis of readings of accelerometers using a deep belief network. Cybernetics and Systems Analysis, 52 (6), 21-29. doi: https://doi.org/10.1007/s10559-016-9886-2 http://jnas.nbuv.gov.ua/article/UJRN-0000582972 [In Russian].