System and method for processing human related data including physiological signals to make context aware decisions with distributed machine learning at edge and cloud

An edge computing device for processing human related data to make personalized and context aware decisions with distributed machine learning at one or more of an edge device and a cloud server, the edge computing device comprising:

• a memory storing computer executable instructions;
• and
• a processor configured to fetch executable instruction and receive signals and parameters of a neural network model from the memory and execute the instructions modeling feedforward path, loss function and backpropagation and use execution results as an input to a next layer of the neural network model, the processor further configured to:
• receive one or more signals comprising a first signal, a second signal and a third signal obtained in real time from sensing a patient's physiological signal from one or more sensory devices or derive one or more of the first, second and third signals and features from the one or more received signals;
• run a first correlation function on the first signal and the second signal to generate a first correlation pattern;
• determine a lag time between the first signal and the second signal;
• run a second correlation function on the second signal and the third signal to generate a second correlation pattern;
• derive states of at least one of first and second long short term memory (LSTM) neural networks of the neural network model based on 1) at least one of the first and second correlation patterns and/or 2) at least one of the first, second and third signals;
• and
• map the patient to a stage of a medical condition based on the derived states of the at least one of the first and second LSTM neural networks.

A method of processing human related data to make personalized and context aware decisions with distributed machine learning at one or more of an edge computing device and a cloud server, the method comprising:

• receiving, at a processor of the edge computing device, one or more signals comprising a first signal, a second signal and a third signal obtained in real time from sensing a patient's physiological signal from one or more sensory devices or deriving, at the processor, one or more of the first, second and third signals from the one or more received signals;
• running, at the processor, a first correlation function on the first signal and the second signal to generate a first correlation pattern;
• determining, at the processor, a lag time between the first signal and the second signal;
• running, at the processor, a second correlation function on the second signal and the third signal to generate a second correlation pattern;
• deriving states of at least one of first and second long short term memory (LSTM) neural networks based on 1) at least one of the first and second correlation patterns and/or 2) at least one of the first, second and third signals;
• mapping, at the processor, the patient to a stage of a medical condition based on the derived states of the at least one of the first and second LSTM neural networks;
• and
• combining states of different LSTMs and mapping them to a state of the medical condition by feeding them to a decision making neural network layer.