| CPC G06N 3/084 (2013.01) [G06N 3/04 (2013.01); G16H 40/67 (2018.01)] | 20 Claims |
|
1. A method, performed in a computing device, of training a machine learning neural network (MLNN) in monitoring anatomical positioning of a medical patient, the method performed in one or more processors and comprising:
receiving, in a first input layer of the MLNN, from a millimeter wave (mmWave) radar sensing device, mmWave radar point cloud data representing a plurality of spatial positions of an anatomical target associated with the medical patient during changes in successive ones of the plurality of spatial positions in association with a corresponding plurality of durations between the changes, the mmWave radar point data based upon detecting at least a range and a reflected wireless signal strength associated with the anatomical target;
receiving, in at least a second layer of the MLNN, attendant attribute data for the corresponding plurality of durations, the first and the at least a second input layers being interconnected with an output layer of the MLNN via at least one intermediate layer, the at least one intermediate layer configured in accordance with an initial matrix of weights, the first, at least a second, intermediate and output layers of the MLNN being implemented, using the one or more processors, in a memory of the computing device;
training a MLNN classifier in accordance with a classification that establishes a correlation between the mmWave radar point cloud data, the attendant attribute data and a likelihood of formation of bodily pressure ulcers (BPUs) as generated at the output layer; and
producing a trained MLNN based on increasing the correlation.
|