Time sequence signal efficient denoising and high-precision reconstruction modeling method and system

Abstract

The invention provides a time sequence signal efficient denoising and high-precision reconstruction modeling method and system. The method comprises: carrying out data preprocessing on original pulsewave signals; selecting a preset signal duration, and dividing the pulse wave signals after data preprocessing into a prediction set, a training set and a test set; selecting a convolutional neural network as a basic model of the deep convolutional noise reduction auto-encoder, and obtaining a deep convolutional noise reduction auto-encoder model according to a signal denoising requirement; inputting the training set into a deep convolution noise reduction auto-encoder model for training, and optimizing and selecting parameters of the deep convolution noise reduction auto-encoder model by using the regularization parameters and the test set to obtain an optimal deep learning model; and inputting the noisy pulse wave signal prediction set into the optimal deep learning model to obtain deepstructure features, performing signal reconstruction and denoising processing, and evaluating model performance. According to the method, denoising and reconstruction of the pulse wave signals are effectively carried out, and a new thought is provided for filtering same-frequency noise interference in the pulse wave signals.

Description

technical field [0001] The present invention relates to the field of signal denoising and machine learning, in particular, to a time series signal denoising and reconstruction modeling method and system, more specifically, to a time series signal efficient denoising and high precision reconstruction Modeling methods and systems. Background technique [0002] Photoplethysmography is an important medical method for wearable devices to monitor human health, and it is of great significance for the detection and timely treatment of cardiovascular diseases. With the rapid development of optoelectronic technology, wearable devices are also widely used in clinical and physical exercise. However, due to the portability of its equipment, the pulse wave signal is extremely susceptible to noise pollution in actual scenarios, which will increase the inaccuracy of the extraction of characteristic parameters such as heart rate and breathing rate and the complexity of further disease diagn...

AI Technical Summary

Problems solved by technology

Singular value decomposition is a matrix analysis method, which uses signal resampling to perform matrix decomposition and selects appropriate singular values ​​to reconstruct the signal, but the operation process is more complicated, and motion artifacts close to the pulse wave frequency cannot be eliminated

Adaptive filter is a commonly used filter in the signal processing process, and it has also achieved good results in the denoising of time series signals, but this type of filter is too sensitive to the adjustment of parameters, so it is very unstable

The wavelet transform algorithm is the most widely used algorithm in traditional signal denoising processing. The soft threshold decomposed by the wavelet coefficient can effectively filter out the myoelectric interference and baseline drift components in the pulse wave signal. Noise, whose frequency range happens to overlap with that of the pulse wave signal, makes it difficult for traditional signal processing methods to work

Images