Neural network based radiowave monitoring of patient degenerative conditions

A computing system comprising:

• one or more processors;
• a memory storing a set of instructions, the instructions when executed in the one or more processors causing operations including:
• receiving, in a first input layer of a machine learning neural network (MLNN), from a millimeter wave (mmWave) radar sensing device, a first set of mmWave radar point cloud data representing a first gait characteristic of a subject in motion, the first gait characteristic comprising an arm swing velocity;
• receiving, in at least a second layer of the MLNN, from the mmWave radar sensing device, an at least a second set of mmWave radar point cloud data representing an at least a second gait characteristic comprising a measure of dynamic postural stability that is indicative of a degree to which the subject in motion is off-balance, 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 first, at least a second, intermediate and output layers of the MLNN being instantiated, using the one or more processors, in the memory;
• and
• training a MLNN classifier in accordance with a classifier that increases a correlation between a degenerative condition of the subject as generated at the output layer and the first and at least a second sets of mmWave point cloud data.

A computer readable non-transitory memory storing instructions, the instructions when executed in a processor causing the processor to implement operations comprising:

• receiving, in a first input layer of a machine learning neural network (MLNN), from a millimeter wave (mmWave) radar sensing device, a first set of mmWave radar point cloud data representing a first gait characteristic of a subject in motion, the first gait characteristic comprising an arm swing velocity;
• receiving, in at least a second layer of the MLNN, from the mmWave radar sensing device, an at least a second set of mmWave radar point cloud data representing an at least a second gait characteristic comprising a measure of dynamic postural stability that is indicative of a degree to which the subject in motion is off-balance, 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 first, at least a second, intermediate and output layers of the MLNN being instantiated, using the one or more processors, in a memory of a computing device;
• and
• training a MLNN classifier in accordance with a classifier that increases a correlation between a degenerative condition of the subject as generated at the output layer and the first and at least a second sets of mmWave point cloud data.