To address the problem of large reconstruction errors in 3D pulse signals caused by excessively small out-of-plane displacement of the contact membrane in the existing traditional Chinese medicine fingertip tactile binocular vision detection technology, this study proposes a 3D pulse image detection method based on subtle motion magnification technology and explores its application in pulse pattern recognition. Firstly, a 3D pulse image detection system based on binocular vision to obtain pulse image signals is developed as experimental data. Then, the phase motion video magnification algorithm is used to amplify the original signals, and the amplified signals are reconstructed in three dimensions to obtain 3D pulse signals. On this basis, nine features are extracted from the 3D pulse signals and features selection is performed using a two-sample Kolmogorov-Smirnov test. Finally, machine learning algorithms such as decision trees and random forests are used to identify the five types of pulse conditions: deep pulse, intermittent pulse, flooding pulse, slippery pulse, and rapid pulse. The experimental results show that compared to the methods without subtle motion magnification technology, the proposed method significantly improves waveform clarity, amplitude stability, and periodic regularity. Meanwhile, the average accuracy in pulse pattern recognition reaches 96.29%±0.26%.
Algorithms ; Imaging, Three-Dimensional/methods* ; Pattern Recognition, Automated ; Medicine, Chinese Traditional ; Motion ; Humans ; Pulse ; Signal Processing, Computer-Assisted ; Machine Learning

PPG(photoplethysmography)holds significant application value in wearable and intelligent health devices.However,during the acquisition process,PPG signals can generate motion artifacts due to inevitable coupling motion,which diminishes signal quality.In response to the challenge of real-time detection of motion artifacts in PPG signals,this study analyzed the generation and significant features of PPG signal interference.Seven features were extracted from the pulse interval data,and those exhibiting notable changes were filtered using the dual-sample Kolmogorov-Smirnov test.The real-time detection of motion artifacts in PPG signals was ultimately based on decision trees.In the experimental phase,PPG signal data from 20 college students were collected to formulate the experimental dataset.The experimental results demonstrate that the proposed method achieves an average accuracy of(94.07±1.14)%,outperforming commonly used motion artifact detection algorithms in terms of accuracy and real-time performance.

In order to quantitatively analyze the morphology and period of pulse signals, a time-space analytical modeling and quantitative analysis method for pulse signals were proposed. Firstly, according to the production mechanism of the pulse signal, the pulse space-time analytical model was built after integrating the period and baseline of pulse signal into the analytical model, and the model mathematical expression and its 12 parameters were obtained for pulse wave quantification. Then, the model parameters estimation process based on the actual pulse signal was presented, and the optimization method, constraints and boundary conditions in parameter estimation were given. The spatial-temporal analytical modeling method was applied to the pulse waves of healthy subjects from the international standard physiological signal sub-database Fantasia of the PhysioNet in open-source, and we derived some changes in heartbeat rhythm and hemodynamic generated by aging and gender difference from the analytical models. The model parameters were employed as the input of some machine learning methods, e.g. random forest and probabilistic neural network, to classify the pulse waves by age and gender, and the results showed that random forest has the best classification performance with Kappa coefficients over 98%. Therefore, the space-time analytical modeling method proposed in this study can effectively quantify and analyze the pulse signal, which provides a theoretical basis and technical framework for some related applications based on pulse signals.

In order to improve the storage and transmission efficiency of dynamic photoplethysmography (PPG) signals in the detection process and reduce the redundancy of signals, the modified adaptive matching pursuit (MAMP) algorithm was proposed according to the sparsity of the PPG signal. The proposed algorithm which is based on reconstruction method of sparse adaptive matching pursuit (SAMP), could improve the accuracy of the sparsity estimation of signals by using both variable step size and the double threshold conditions. After experiments on the simulated and the actual PPG signals, the results show that the modified algorithm could estimate the sparsity of signals accurately and quickly, and had good anti-noise performance. Contrasting with SAMP and orthogonal matching pursuit (OMP), the reconstruction speed of the algorithm was faster and the accuracy was high.
Algorithms ; Humans ; Image Processing, Computer-Assisted ; Photoplethysmography

In order to reduce the impact of various noise in pulse signal, the quality estimation and filtering algorithms based on cyclostationarity are proposed to reprocess pulse signal. First, A quality evaluation index of pulse signal which named quality factor is defined by cyclic spectrum to describe the quality variation of the pulse signal affected by noise; Second, a cyclic correlation matched filter (CCMF) is designed to remove noise. The simulation of pulse signal is produced by ourselves and noise signal is provided by MIT-BIH physiological database are used to test the function of proposed method, and then the method is applied to the actual pulse signal. The results show that the quality factor can accurately reflect the quality of the pulse signal and the CCMF can effectively remove noise from pulse signal.
Algorithms ; Databases, Factual ; Heart Rate ; Humans

In order to derive dynamic pulse rate variability (DPRV) signal from dynamic pulse signal in real time, a method for extracting DPRV signal was proposed and a portable mobile monitoring system was designed. The system consists of a front end for collecting and wireless sending pulse signal and a mobile terminal. The proposed method is employed to extract DPRV from dynamic pulse signal in mobile terminal, and the DPRV signal is analyzed both in the time domain and the frequency domain and also with non-linear method in real time. The results show that the proposed method can accurately derive DPRV signal in real time, the system can be used for processing and analyzing DPRV signal in real time.
Electrocardiography ; Heart Rate ; Monitoring, Physiologic ; Signal Processing, Computer-Assisted

Pulse signal contains a wealth of biological and pathological information. However, it is susceptible to the influence of various factors which results in poor signal quality, and causes the device to generate false alarms. First the pulse signals are processing into discrete symbols, and then compare the test signal with the pulse template by using Dynamic Time Warping (DTW) to get the threshold for which can be used to find the interference segment of the test signal. By analyzing the DTW distance of the pulse signal, we can get the interference degree of the signal, then the quality level of the plus signal can be defined by the relationship between the interference degree and quality of the signal. The 1 055 group pulse signals provided by MIMIC II physiological database are used to train and test the signal quality assessment algorithms, and compared with other existing algorithms. The results show that the algorithms can accurately detect interference segments in pulse signal and reflect the quality of it.
Algorithms ; Heart Rate ; Humans ; Pulse ; Signal Processing, Computer-Assisted

In order to reduce the impact of various noise in pulse signal, the quality estimation and filtering algorithms based on cyclostationarity are proposed to reprocess pulse signal. First, A quality evaluation index of pulse signal which named quality factor is defined by cyclic spectrum to describe the quality variation of the pulse signal affected by noise;Second, a cyclic correlation matched filter (CCMF) is designed to remove noise. The simulation of pulse signal is produced by ourselves and noise signal is provided by MIT-BIH physiological database are used to test the function of proposed method, and then the method is applied to the actual pulse signal. The results show that the quality factor can accurately reflect the quality of the pulse signal and the CCMF can effectively remove noise from pulse signal.

Pulse signal contains a wealth of biological and pathological information. However, it is susceptible to the influence of various factors which results in poor signal quality, and causes the device to generate false alarms. First the pulse signals are processing into discrete symbols, and then compare the test signal with the pulse template by using Dynamic Time Warping (DTW) to get the threshold for which can be used to find the interference segment of the test signal. By analyzing the DTW distance of the pulse signal, we can get the interference degree of the signal, then the quality level of the plus signal can be defined by the relationship between the interference degree and quality of the signal. The 1 055 group pulse signals provided by MIMICⅡphysiological database are used to train and test the signal quality assessment algorithms, and compared with other existing algorithms. The results show that the algorithms can accurately detect interference segments in pulse signal and reflect the quality of it.

In order to derive dynamic pulse rate variability (DPRV) signal from dynamic pulse signal in real time, a method for extracting DPRV signal was proposed and a portable mobile monitoring system was designed. The system consists of a front end for colecting and wireless sending pulse signal and a mobile terminal. The proposed method is employed to extract DPRV from dynamic pulse signal in mobile terminal, and the DPRV signal is analyzed both in the time domain and the frequency domain and also with non-linear method in real time. The results show that the proposed method can accurately derive DPRV signal in real time, the system can be used for processing and analyzing DPRV signal in real time.