Skip to content

Index

Denoise Task API

The objective of denoising is to remove noise and artifacts from physiological signals while preserving the underlying signal information. The dominant noise sources include baseline wander (BW), muscle noise (EMG), electrode movement artifacts (EM), and powerline interference (PLI). For physiological signals such as ECG and PPG, removing the artifacts is difficult due to the non-stationary nature of the noise and overlapping frequency bands with the signal. While traditional signal processing techniques such as filtering and wavelet denoising have been used to remove noise, deep learning models have shown great promise in enhanced denoising.

Classes:

Classes

DenoiseTask

heartKIT Denoise Task

Functions

train staticmethod 
train(params: HKTaskParams)

Train model for denoise task

Parameters:

Source code in heartkit/tasks/denoise/__init__.py 
26
27
28
29
30
31
32
33
@staticmethod
def train(params: HKTaskParams):
    """Train model for denoise task

    Args:
        params (HKTaskParams): Task parameters
    """
    train(params)
evaluate staticmethod 
evaluate(params: HKTaskParams)

Evaluate denoise model

Parameters:

Source code in heartkit/tasks/denoise/__init__.py 
35
36
37
38
39
40
41
42
@staticmethod
def evaluate(params: HKTaskParams):
    """Evaluate denoise model

    Args:
        params (HKTaskParams): Task parameters
    """
    evaluate(params)
export staticmethod 
export(params: HKTaskParams)

Export denoise model

Parameters:

Source code in heartkit/tasks/denoise/__init__.py 
44
45
46
47
48
49
50
51
@staticmethod
def export(params: HKTaskParams):
    """Export denoise model

    Args:
        params (HKTaskParams): Task parameters
    """
    export(params)
demo staticmethod 
demo(params: HKTaskParams)

Run denoise demo.

Parameters:

Source code in heartkit/tasks/denoise/__init__.py 
53
54
55
56
57
58
59
60
@staticmethod
def demo(params: HKTaskParams):
    """Run denoise demo.

    Args:
        params (HKTaskParams): Task parameters
    """
    demo(params)