Systems, apparatuses and methods for sensing fetal activity

1. A computer-implemented method, comprising:

receiving, by at least one computer processor executing specific programmable instructions configured for the method, a plurality of Phonocardiogram (PCG) signals data inputs from a plurality of acoustic sensors;

digital signal filtering, by the at least one computer processor, utilizing a plurality of bandpass filters, the plurality of PCG signals data inputs to form a plurality of filtered PCG outputs, wherein the plurality of bandpass filters comprises a L number of bandpass filters, wherein each bandpass filter outputs a K number of filtered PCG outputs;

wavelet denoising, by the at least one computer processor, a first subset of filtered PCG outputs of the plurality of filtered PCG outputs to form a M number of denoised filtered PCG outputs, wherein M is equal to L multiply by K, wherein the wavelet denoising comprises:

deconstructing, by the at least one computer processor, each filtered PCG output to generate a plurality of transform coefficients, by irrelatively passing each filtered PCG output through a succession of low and high pass filters,

identifying, by the at least one computer processor, a subset of heartbeat-carrying transform coefficients from the plurality of transform coefficients, and

reconstructing, by the at least one computer processor, the subset of heartbeat-carrying transform coefficients to form the M number of denoised filtered PCG outputs;

transforming, by the at least one computer processor, utilizing an Independent-Component-Analysis (ICA), a second subset of filtered PCG outputs of the plurality of filtered PCG outputs to form the M number of filtered ICA transforms;

transforming, by the at least one computer processor, utilizing the Independent-Component-Analysis (ICA), a first portion of the second subset of denoised filtered PCG outputs to form the M number of denoised filtered ICA transforms;

compiling, by the at least one computer processor, a S number of a plurality of detection heartbeat (DH) inputs, comprising:

i) the M number of filtered PCG outputs,

ii) the M number of the denoised filtered PCG outputs,

iii) the M number of the filtered ICA transforms, and

iv) the M number of the denoised filtered ICA transforms;

detecting, by the at least one computer processor, beat locations of beats in each of DH inputs;

calculating, by the at least one computer processor, a confidence score that describes a probability that the beats in each DH input of the plurality of DH inputs represent actual heartbeats and not a noise;

dividing, by the at least one computer processor, the plurality of DH inputs into at least two groups:

i) a first group of DH inputs containing fetal heartbeats,

ii) a second group of DH inputs containing maternal heartbeats;

selecting, by the at least one computer processor, from the first group of DH inputs, at least one particular fetal DH input that contains the fetal heartbeat based on a first confidence score of the at least one particular fetal DH input; and

selecting, by the at least one computer processor, from the second group of DH inputs, at least one particular maternal DH input that contains the maternal heartbeat, based on a second confidence score of the at least one particular maternal DH input.

2. The computer-implemented method of claim 1 , wherein K is equal to a number of the plurality of acoustic sensors, and L is equal to 6.

3. The computer-implemented method of claim 1 , wherein each filter of the plurality of bandpass filters has a bandwidth of 10-100 Hz and a frequency range of 5-110 HZ.

4. The computer-implemented method of claim 1 , wherein the detecting of the beat locations of the beats in each of DH inputs, comprising:

calculating, by the at least one computer processor, a predetermined transform filter;

iteratively repeating, by the at least one computer processor, based on a predetermined average window length of the predetermined transform filter:

identifying, in each DH input, a subset of peaks having a predetermined shape and a predetermined size, and

selecting a group of peaks from the subset of peaks, wherein the group of peaks has the smallest variance measure;

calculating, by the at least one computer processor, initial locations of the beats.

5. The computer-implemented method of claim 1 , wherein the calculating the confidence score, comprising:

generating, by the at least one computer processor, a beat-by-beat heartbeat graph for each DH input based on the beat locations.

6. The computer-implemented method of claim 1 , wherein the dividing the plurality of DH inputs into the first group of DH inputs containing fetal heartbeats and the second group of DH inputs containing maternal heartbeats, comprising:

clustering, by the at least one computer processor, the beats of each DH input according to each beat value; and

assigning, by the at least one computer processor, a particular DH input having a higher average beat rate into the first group of DH inputs containing fetal heartbeats.

7. A specifically programmed computer system, comprising:

at least one specialized computer machine, comprising:

a non-transient memory, electronically storing particular computer executable program code; and

at least one computer processor which, when executing the particular program code, becomes a specifically programmed computing processor that is configured to at least perform the following operations:

receiving a plurality of Phonocardiogram (PCG) signals data inputs from a plurality of acoustic sensors;

digital signal filtering, utilizing a plurality of bandpass filters, the plurality of PCG signals data inputs to form a plurality of filtered PCG outputs, wherein the plurality of bandpass filters comprises a L number of bandpass filters, wherein each bandpass filter outputs a K number of filtered PCG outputs;

wavelet denoising a first subset of filtered PCG outputs of the plurality of filtered PCG outputs to form a M number of denoised filtered PCG outputs, wherein M is equal to L multiply by K, wherein the wavelet denoising comprises:

deconstructing each filtered PCG output to generate a plurality of transform coefficients, by irrelatively passing each filtered PCG output through a succession of low and high pass filters,

identifying a subset of heartbeat-carrying transform coefficients from the plurality of transform coefficients, and

reconstructing the subset of heartbeat-carrying transform coefficients to form the M number of denoised filtered PCG outputs;

transforming, utilizing an Independent-Component-Analysis (ICA), a second subset of filtered PCG outputs of the plurality of filtered PCG outputs to form the M number of filtered ICA transforms;

transforming, utilizing the Independent-Component-Analysis (ICA), a first portion of the second subset of denoised filtered PCG outputs to form the M number of denoised filtered ICA transforms;

compiling a S number of a plurality of detection heartbeat (DH) inputs, comprising:

i) the M number of filtered PCG outputs,

ii) the M number of denoised filtered PCG outputs,

iii) the M number of filtered ICA transforms, and

iv) the M number of denoised filtered ICA transforms;

detecting beat locations of beats in each of DH inputs;

calculating a confidence score that describes a probability that the beats in each DH input of the plurality of DH inputs represent actual heartbeats and not a noise;

dividing the plurality of DH inputs into at least two groups:

i) a first group of DH inputs containing fetal heartbeats,

ii) a second group of DH inputs containing maternal heartbeats;

selecting, from the first group of DH inputs, at least one particular fetal DH input that contains the fetal heartbeat based on a first confidence score of the at least one particular fetal DH input; and

selecting, from the second group of DH inputs, at least one particular maternal DH input that contains the maternal heartbeat, based on a second confidence score of the at least one particular maternal DH input.

8. The specifically programmed computer system of claim 7 , wherein K is equal to a number of the plurality of acoustic sensors, and L is equal to 6.

9. The specifically programmed computer system of claim 7 , wherein each filter of the plurality of bandpass filters has a bandwidth of 10-100 Hz and a frequency range of 5-110 HZ.

10. The specifically programmed computer system of claim 7 , wherein the detecting of the beat locations of the beats in each of DH inputs, comprising:

calculating a predetermined transform filter;

iteratively repeating, based on a predetermined average window length of the predetermined transform filter:

identifying, in each DH input, a subset of peaks having a predetermined shape and a predetermined size, and

selecting a group of peaks from the subset of peaks, wherein the group of peaks has the smallest variance measure;

calculating initial locations of the beats.

11. The specifically programmed computer system of claim 7 , wherein the calculating the confidence score, comprising:

generating a beat-by-beat heartbeat graph for each DH input based on the beat locations.

12. The specifically programmed computer system of claim 7 , wherein the dividing the plurality of DH inputs into the first group of DH inputs containing fetal heartbeats and the second group of DH inputs containing maternal heartbeats, comprising:

clustering the beats of each DH input according to each beat value; and

assigning a particular DH input having a higher average beat rate into the first group of DH inputs containing fetal heartbeats.