Period Segmentation for Wrist Pulse Signal Based on Adaptive Cascade Thresholding and Machine Learning

Abstract

Wrist pulse signal has been regarded as a physical health indicator for a long history in Traditional Chinese Medicine (TCM). The quantized pulse diagnosis by using the signal processing and pattern recognition technology is introduced to take over the traditional subjective judgments in recent years, and it's attracting more and more attention. However, the previous researches with pulse preprocessing mainly concentrate on the denoising and baseline wander correction procedure. The evaluation criterion isn't associated with the feature analysis, and the performance with shape classification doesn't give any contributions to the pulse diagnosis. Moreover, the signals are processed in a simulated environment by adding disturbance manually. In this paper, we propose a period segmentation method based on adaptive cascade thresholding and machine learning for extracting the information within single period. It's a novel preprocessing stage and the pulse data collected in real conditions for practical usage is analyzed. The experiments show that our method is significant in the pulse preprocessing stage and improves the accuracy for the disease classification between healthy subjects and diabetes.

Analysis of the Radial Pulse Wave and its Clinical Applications: A Survey

“…Combining with the method of empirical mode decomposition, Xu et al proposed an adaptive wavelet threshold denoising method and showed that when the SNR was low, the denoising performance of this method was better than the traditional wavelet threshold denoising method [32]. Wang et al proposed a method based on adaptive cascade thresholding to remove the disturbance intervals and showed that an adaptive cascade threshold method could be used to obtain a stable pulse wave [33]. The above studies show that after removing interference, relatively smooth radial pulse waves can be obtained, which is beneficial to analyze the its characteristics.…”

“…The period segmentation refers to dividing a long-term waveform signal into several single-period signals according to the cardiac cycle. In the period segmentation, Wang et al accomplished it through detecting the lowest valley value as the segmentation point using the adaptive sliding window [33]. Hu et al utilized Hilbert transform to find the peak point which could be regarded as the marker of periodic segmentation [35].…”

“…It is difficult to accurately extract the waveform features and describe the morphological changes. To obtain a corruption-free and more stable radial signal, the waveform preprocessing can not only reduce the interference components [28][29][30][31][32][33], but should also analyze the morphology of radial pulse waves over a long period [34][35][36][37][38]. The purpose of feature extraction is to analyze the information represented by radial pulse waves.…”

A New Measure of Pulse Rate Variability and Detection of Atrial Fibrillation Based on Improved Time Synchronous Averaging

“…That is to say, we can select the less interfered periods from a pulse wave series with poor quality to complete TSA, rather than discarding the whole series (Figure 1). Similar algorithms have been applied to single-period pulse waveform extraction [14,15]. However, in existing applications, the pulse wave signal is assumed to be a strict periodic signal, and the starting point or the highest point of the waveform is used as the fiducial point for synchronization without discussing the basis of these steps.…”

Machine Learning–Based Signal Quality Evaluation of Single-Period Radial Artery Pulse Waves: Model Development and Validation

“…This similarity is not the only important criterion for classifying pulse segments. Wang and Lu [ 10 ] utilized a k-nearest neighbor (KNN) classifier based on manual label data to measure the quality of the segmented single periods. However, the details and accuracy of the classifier were not shown.…”