Classification of a signal in a time domain
Methods, systems, and computer-readable and executable instructions are provided for classifying an electrocardiogram (ECG) signal. Classifying an ECG signal can include analyzing the ECG signal using a stream of pulses generated by a sampler, extracting cardiac pulse features from a timing of the stream of pulses, and classifying the ECG signal based on the extracted cardiac pulse feature.
1. A non-transitory computer-readable medium comprising instructions for causing a programmable processor to:
pre-process an electrocardiogram (ECG) recording;
transform each heartbeat cycle within the ECG recording into pulse data using an Integrate and Fire (IF) sampler;
separate the pulse data within each transformed heartbeat cycle into a time-based bin;
concatenate the binned pulse data with a particular time interval; and
classify an ECG signal of the ECG recording based on the concatenation.
2. The non-transitory computer readable medium of claim 1 , wherein the instructions are further cause the programmable processor to concatenate the binned pulse data with an RR interval from the ECG recording.
3. The non-transitory computer readable medium of claim 1 , wherein the instructions further cause the programmable processor to:
create a feature vector which serves as an input to a linear discriminant function; and
monitor cardiac functions utilizing the linear discriminant function as a linear discriminant classifier.
4. The non-transitory computer readable medium of claim 1 , wherein the instructions that cause the programmable processor to preprocess the ECG recording further cause the programmable processor to remove a baseline wander and noise from the ECG recording.
5. A computer-implemented method for classifying an electrocardiogram (ECG) signal, comprising:
pre-processing an electrocardiogram (ECG) recording;
transforming each heartbeat cycle within the ECG recording into pulse data using an Integrate and Fire (IF) sampler;
separating the pulse data within each transformed heartbeat cycle into a time-based bin;
concatenating the binned pulse data with a pan icular time interval; and
classifying, via the computer, an ECG signal of the ECG recording based on the concatenation.
6. The method of claim 5 , further comprising concatenating the binned pulse data with an RR interval from the ECG recording.
7. The method of claim 5 , further comprising:
creating a feature vector which serves as an input to a linear discriminant function; and
monitoring cardiac functions utilizing the linear discriminant function as a linear discriminant classifier.
8. The method of claim 5 , wherein preprocessing the ECG recording further comprises removing a baseline wander and noise from the ECG recording.
9. A system for classifying an electrocardiogram (ECG) signal, comprising:
a memory resource; and
a processing resource coupled to the memory resource, the processing resource configured to:
pre-process an electrocardiogram (ECG) recording;
transform each heartbeat cycle within the ECG recording into pulse data using an Integrate and Fire (IF) sampler;
separate the pulse data within each transformed heartbeat cycle into a time-based bin;
concatenate the binned pulse data with a particular time interval; and
classify an ECG signal of the ECG recording based on the concatenation.
10. The system of claim 9 , wherein the processing resource is further coupled to the memory resource to concatenate the binned pulse data with an RR interval from the ECG recording.
11. The system of claim 9 , wherein the processing resource is further coupled to the memory resource to:
create a feature vector which serves as an input to a linear discriminant function; and
monitor cardiac functions utilizing the linear discriminant function as a linear discriminant classifier.
12. The non-transitory computer readable medium of claim 9 , wherein the processing resource coupled to the memory resource to preprocess the ECG recording is further coupled to the memory resource to remove a baseline wander and noise from the ECG recording.