SYSTEM AND METHOD OF IDENTIFICATION OF THE HEART VALVE SIGNALS
A system for identifying heart valve signals includes a non-invasive sensor unit for capturing electrical signals and composite vibration objects, a memory containing computer instructions, and one or more processors coupled to the memory, where the one or more processors are configured to perform the steps of separating a plurality of individual heart vibration events from the composite vibration objects by using at least one among bin-wise clustering and permutation alignment, or non-negative matrix factorization, or deep belief networks and tagging the plurality of individual heart vibration events using at least one among principal component analysis, Gabor filtering, generalized cross correlation, phase transform, smoothed coherent transformation, Roth correlation or band filtering.
1 . A system for identifying heart valve signals, comprising:
a non-invasive sensor unit for capturing electrical signals and composite vibration objects;
a memory containing computer instructions; and
one or more processors coupled to the memory, an execution of the computer instructions by the one or more processors causing the one or more processors to perform operations comprising:
separating a plurality of individual heart vibration events from the composite vibration objects by using at least one among bin-wise clustering and permutation alignment, or non-negative matrix factorization, or deep belief networks; and
tagging the plurality of individual heart vibration events using at least one among principal component analysis, Gabor filtering, generalized cross correlation, phase transform, smoothed coherent transformation, Roth correlation or band filtering.
2 . The system of claim 1 , wherein the non-invasive sensor unit comprises at least one or more sensors using a tri-axial accelerometer configured for placement on different points of a torso.
3 . The system of claim 1 , wherein the system uses one or more among spectral information, relations among channels, and relations among events in a form of relative times of occurrence of heart valve events.
4 . The system of claim 1 , wherein the non-invasive sensor unit provides sensor signals that are filtered, cross correlated, and peak detected to provide an estimate of a delay
5 . The system of claim 1 , further comprising a sensor for performing an electrocardiogram and wherein the non-invasive sensor unit comprises at least one sensor for sensing a heart valve opening.
6 . The system of claim 1 , wherein a permutation alignment is used for source separation.
7 . The system of claim 1 , wherein the system uses Gabor analysis on source separated signals and then source tags the source separated signals.
8 . The system of claim 1 , wherein the processor is configured to perform Gabor analysis on source separated signals using a finite Gabor dictionary of fixed frequencies and with variable phase delay.
9 . The system of claim 1 , wherein the system comprises a Gabor dictionary that serves as a basis representation of the source signals, an optimization algorithm that determines a delay to minimize reconstruction error, and collection and organization of features extracted from the optimization algorithm.
10 . The system for measuring cardiac time intervals of claim 1 , wherein the non-invasive sensor unit comprises at least one sensor for sensing vibrations corresponding to a heart valve opening.
11 . The system for measuring cardiac time intervals of claim 1 , wherein a number of vibration sensors in the non-invasive sensor unit is less than the number of the separated vibration sources.
12 . The system of claim 1 , wherein the processor uses Principal Component Analysis (PCA) to find timing information and delay between channels and to determine which source is associated with which heart valve signal event.
13 . The system of claim 1 , wherein the marking of individual valve events comprises at least the marking of one or more among a Mitral valve opening (MO), Aortic valve opening (AO), Tricuspid valve opening (TO), or Pulmonary valve opening (PO).
15 . The system of claim 1 , wherein the system uses a feature extraction algorithm based on multichannel Gabor basis decomposition using matching pursuit, and a second algorithm that uses eigen-decomposition of a covariance matrix extracted from the source signals to obtain a cross correlation function between channels.
16 . A sensor array device, comprising:
a wearable device configured to capture an electrocardiogram signal synchronized with composite vibration objects from at least one accelerometer and further configured to communicate with a wireless node;
wherein the at least one accelerometer is configured for capturing the composite vibration objects;
an electrode for sensing the electrocardiogram signal; and
one or more processors configured for:
separating a plurality of individual heart vibration events from the composite vibration objects by using at least one among bin-wise clustering and permutation alignment, or non-negative matrix factorization, or deep belief networks; and
tagging the plurality of individual heart vibration events using at least one among principal component analysis, Gabor filtering, generalized cross correlation, phase transform, smoothed coherent transformation, Roth correlation or band filtering.
17 . The sensor array device of claim 16 , wherein the at least one accelerometer are configurable for measuring a lower frequency range vibration signal and a higher frequency range vibration signal.
18 . The sensor array device of claim 16 , wherein the processor is operatively coupled to the at least one accelerometer, the processor further being configured for:
identifying the plurality of individual heart vibration events from the composite vibration objects;
transmitting the composite vibration signals or the plurality of individual heart vibration events to a remote device; and
marking and presenting individual valve events from the plurality of individual heart vibration events with respect to the electrocardiogram signal.
19 . The sensor array device of claim 16 , wherein the one or more processors are configured to uses Gabor analysis on source separated signals.
20 . The sensor array device of claim 16 , wherein the sensor array device is portable and captures synchronized sensor data to a memory and wherein the processor is configurable in the process of separating the plurality of individual heart vibration events from the composite vibration objects into separate vibration sources and further identifying the individual heart vibration events among at least one of a mitral valve opening, a tricuspid valve opening, an aortic valve opening, or a pulmonary valve opening.