Pulse rate estimation based on facial videos:an evaluation and optimization of the classical methods using both self-constructed and public datasets

Pulse rate is one of the important characteristics of traditional Chinese medicine pulse diagnosis,and it is of great significance for determining the nature of cold and heat in diseases.The prediction of pulse rate based on facial video is an exciting research field for getting palpation information by observation diagnosis.However,most studies focus on optimizing the algorithm based on a small sample of participants without systematically investigating multiple influencing factors.A total of 209 participants and 2,435 facial videos,based on our self-constructed Multi-Scene Sign Dataset and the public datasets,were used to perform a multi-level and multi-factor comprehensive comparison.The effects of different datasets,blood volume pulse signal extraction algorithms,region of interests,time windows,color spaces,pulse rate calculation methods,and video recording scenes were analyzed.Furthermore,we proposed a blood volume pulse signal quality optimization strategy based on the inverse Fourier transform and an improvement strategy for pulse rate estimation based on signal-to-noise ratio threshold sliding.We found that the effects of video estimation of pulse rate in the Multi-Scene Sign Dataset and Pulse Rate Detection Dataset were better than in other datasets.Compared with Fast independent component analysis and Single Channel algorithms,chrominance-based method and plane-orthogonal-to-skin algorithms have a more vital anti-interference ability and higher robustness.The performances of the five-organs fusion area and the full-face area were better than that of single sub-regions,and the fewer motion artifacts and better lighting can improve the precision of pulse rate estimation.

Integration of 1H-NMR-Based Metabolomics Approach with Traditional Chinese Pulse Diagnosis to Evaluate the Qi-Enhancing Activity of Herbal Tea

Human metabolism is intricately linked to an individual’s health status. Regardless of living habits, it will be reflected in the metabolic characteristics of urine. The utilization of the 1H NMR-based metabolomics method has enabled examine the metabolomic changes in urine under various physiology conditions, providing valuable insights into metabolites. In this particular study, volunteers were divided into two groups based on the strength of their spleen pulses, using the pulse diagnosis method employed in traditional Chinese medicine. Subsequently, their urine samples were analyzed, revealing notable variances in urea, creatinine, citric acid, succinic acid, trimethylamine-N-oxide (TMAO), alanine, hippuric acid, and glycine between the two groups. Interestingly, individuals with weak spleen pulses showed significant improvements after consuming herbal tea. Furthermore, we conducted LC-MS analysis on herbal tea and performed adenosine triphosphate (ATP) activity tests on the C2C12 mouse skeletal muscle cell line. The results indicated that within a reasonable concentration range, exposure to herbal tea led to an increase in the mitochondrial ATP production capacity of C2C12 cells. These findings shed light on the relationship between traditional Chinese medicine pulse diagnosis and urine metabolites, highlighting their potential as non-invasive and straightforward health assessment indicators. They can aid in the preliminary determination of necessary dietary and lifestyle changes to enhance overall bodily health.

A correlation between pulse diagnosis of human body and health monitoring of structures

The concept of health monitoring is a key aspect of the field of medicine that has been practiced for a long time. A commonly used diagnostic and health monitoring practice is pulse diagnosis, which can be traced back approximately five thousand years in the recorded history of China. With advances in the development of modern technology, the concept of health monitoring of a variety of engineering structures in several applications has begun to attract widespread attention. Of particular interest in this study is the health monitoring of civil structures. It seem natural, and even beneficial, that these two health-monitoring methods, one as applies to the human body and the other to civil structures, should be analyzed and compared. In this paper, the basic concepts and theories of the two monitoring methods are first discussed. Similarities are then summarized and commented upon. It is hoped that this correlation analysis may help provide structural engineers with some insights into the intrinsic concept of using pulse diagnosis in human health monitoring, which may of be some benefit in the development of modern structural health monitoring methods.

Wrist blood flow signal-based computerized pulse diagnosis using spatial and spectrum features

ABSTRACT Current computerized pulse diagnosis is mainly based on pressure and photoelectric signal. Considering the richness and complication of pulse diagnosis information, it is valuable to explore the feasibility of novel types of signal and to develop appropriate feature representation for diagnosis. In this paper, we present a study on computerized pulse diagnosis based on blood flow velocity signal. First, the blood flow velocity signal is collected using Doppler ultrasound device and preprocessed. Then, by locating the fiducial points, we extract the spatial features of blood flow velocity signal, and further present a Hilbert-Huang transform-based method for spectrum feature extraction. Finally, support vector machine is applied for computerized pulse diagnosis. Experiment results show that the proposed method is effective and promising in distinguishing healthy people from patients with cho- lecystitis or nephritis.

Classification research of TCM pulse conditions based on multi-label voice analysis

Objective:To explore the feasibility of remotely obtaining complex information on traditional Chinese medicine(TCM)pulse conditions through voice signals.Methods: We used multi-label pulse conditions as the entry point and modeled and analyzed TCM pulse diagnosis by combining voice analysis and machine learning.Audio features were extracted from voice recordings in the TCM pulse condition dataset.The obtained features were combined with information from tongue and facial diagnoses.A multi-label pulse condition voice classification DNN model was built using 10-fold cross-validation,and the modeling methods were validated using publicly available datasets.Results: The analysis showed that the proposed method achieved an accuracy of 92.59%on the public dataset.The accuracies of the three single-label pulse manifestation models in the test set were 94.27%,96.35%,and 95.39%.The absolute accuracy of the multi-label model was 92.74%.Conclusion: Voice data analysis may serve as a remote adjunct to the TCM diagnostic method for pulse condition assessment.

Analysis on pulse features of coronary heart disease patients with or without a history of ischemic stroke

Objective To evaluate the capability of wrist pulse analysis in distinguishing three physiolog-ical and pathological conditions:healthy individuals,coronary heart disease(CHD)patients without a history of ischemic stroke,and CHD patients with a history of ischemic stroke.Methods Study participants were recruited from Shuguang East Hospital,Yueyang Hospital of Integrated Traditional Chinese and Western Medicine,and Shanghai Municipal Hospital of Traditional Chinese Medicine,affiliated with Shanghai University of Traditional Chinese Medicine,from April 15 to September 15,2021.They were categorized into three groups:healthy controls(Group 1),CHD patients without a history of ischemic stroke(Group 2),and CHD patients with a history of ischemic stroke(Group 3).The wrist pulse signals of the study participants were non-invasively collected using a pulse diagnosis instrument.The linear time-domain features and nonlinear time-series multiscale entropy(MSE)features of the pulse signals were extracted using time-domain analysis and the MSE methods,which were subsequently compared between groups.Based on these extracted features,a recognition model was developed using a random forest(RF)algorithm.The classification performance of the models was evaluated using metrics,including accuracy,precision,recall,and F1-score derived from confusion matrix as well as the area under the receiver operating characteristics(ROC)curve(AUC).Results A total of 189 participants were enrolled,with 63 in Group 1,61 in Group 2,and 65 in Group 3.Compared with Group 1,Group 2 showed significant increases in pulse features H2/H1,H3/H1,W1,W2,and W2/T,and decreased in MSE_(1)-MSE7(P<0.05),while Group 3 showed significant increases in pulse features T5/T4,T,H1/T1,W1,W2,AS,and Ad,and de-creased in MSE_(1)-MSE_(20)(P<0.05).Compared with Group 2,Group 3 demonstrated notable increases in H1/T1 and As(P<0.05).The RF model achieved precision of 80.00%,61.54%,and 61.54%,recall of 74.29%,60.00%,and 68.97%,F1-scores of 70.04%,60.76%,and 65.04%,and AUC values of 0.92,0.74,and 0.81 for Groups 1,2,and 3,respectively.The overall accuracy was 67.69%,with micro-average AUC of 0.83 and macro-average AUC of 0.82.Conclusion Differences in pulse features reflect variations in arterial compliance,peripheral resistance,cardiac afterload,and pulse signal complexity among healthy individuals,CHD patients without a history of ischemic stroke,and those with such a history.The developed pulse-based recognition model holds the potential in distinguishing between these three groups,offering a novel diagnostic reference for clinical practice.

The value of pulse wave velocity in the diagnosis of coronary heart disease

Objective: Using receiver operating characteristics (ROC) curve to evaluate the value of pulse wave velocity (PWV) in the diagnosis of coronary heart disease (CHD). Methods: By using coronary angiography as golden diagnostic standard of CHD, 218 patients were divided into both CHD group (n=121) and non-CHD group (n = 97). All these patients received PWV test. The efficacy of PWV of each artery segments in the diagnosis of CHD was evaluated by ROC curve. The sensitivity and specificity were calculated with the golden diagnostic standard of CHD. Results:The PWV of right carotid to femoral artery (Rc-f), left carotid to femoral artery (Lc-f), right radial to carotid artery (Rc-r), left radial to carotid artery (Lc-r) in CHD group were significantly higher than that of non-CHD group (9. 31±1. 75 vs 7.60±1.59, P<0. 01; 9. 02±1.71 vs 7. 52±1.50, P<0. 01; 8. 69±1. 37 vs 8. 00±1. 27, P<0. 01; 8.52±1. 03 vs 8. 03±1. 2, P<0. 01 respectively). However, the PWV of both right and left femoral to ankle artery (Rf-a and Lf-a) had no significant differences between the two groups. We then compared the area under curve (AUC) of each ROC(AUCROC) of PWV of Rc-f, Lc-f Rc-r and Lc-r to evaluate their diagnostic efficacy for CHD. We found that AUCROC of Rc-f PWV was the biggest (AUCROC = 0. 818), at the peak point of its ROC curve, the PWV was 8. 32 m/s. PWV>8. 32 m/s of Rc-f could predict the presence of CHD with a sensitivity of 79% and specificity of 77%. Conclusion: The PWV of Rc-f, Lc-f, Rc-r, Lc-r are significantly higher in CHD group than that in non-CHD group, and PWV of Rc-f is the most accurate in the detection of CHD. The PWV>8. 32 m/s of RC-F is a valuable predictor of CHD.

A new interpretation of TCM pulse diagnosis based on quantum physical model of the human body

Following the quantum theory-based physical model of the human body,a new interpretation of the traditional Chinese medicine(TCM)principle of"Cunkou reads viscera"is presented.Then,a Gaussian pulse wave model as a solution to the Schrodinger equation is shown to accurately describe 19 different pulse shapes,and to quantitatively capture the degree of YinYang attributes of 13 pulse shapes.Furthermore,the model suggests using pulse depth and strength as leading-order quantity and pulse shape as first-order quantity,to characterize the hierarchical resonance between the human body and the environment.The future pulse informatics will focus on determining an individual’s unique quantum human equilibrium state,and diagnose its health state according to the pulse deviation from its equilibrium state,to truly achieve the high level of TCM:"knowing the normal state and reaching the change".

Nonlinear Response Analysis for Insulation Diagnosis of Water-tree Aged 10 kV XLPE Cable Using Pulse Voltage

The diagnosis of water trees of cable insulation is of great importance as the water-treeing is a primary cause of aging breakdown for the middle voltage cables. In this paper, it is described how the water-tree-aged 10 kV XLPE cables were diagnosed. The cables were subjected to electrical stress of 5.9 kV/mm and a thermal load cycle in a curved water-filled tube for 3, 6 and 12 months of aging in accor- dance with the accelerated water-tree test method. The aged cables were used as the samples for water-tree diagnosis. First, the water-tree degraded cable, was charged by a DC voltage, and then the cable was grounded while a pulse voltage was applied to it for releasing the space charge trapped in the water trees. The amount of the space charge, which corresponds to the deterioration degree of the water trees, was calculated. The effects of DC voltage amplitude, pulse voltage repetition rate and aging conditions on the amount of the space charge were studied. Obtained results show that the amount of the space charge has a positive correlation with the applied DC voltage and the ag- ing time of the cables, and that a peak value of space charge appears with the increase of the pulse voltage repetition rate. An optimum pulse voltage repetition rate under which the space charge can be released rapidly is obtained. Furthermore, the releasing mechanism of space charge by the pulse voltage is discussed. Accumulated results show that the presented method has a high resolution for the diagnosis of water tree degradation degree and is expected to be applied in practice in future.

MODELING AND ANALYSIS OF HUMAN PULSE

Pulse diagnosis is a special method of diagnosing patient’s disease.Amathematical model of the pulse is presented in this paper.The feature parameters ofthe sphygmogram are extracted based on the signal model.The discrimination andprincipal analysis are employed to identify the pulses.The results are matching withthose of traditional methods.

Spectroscopic diagnosis of plasma in atmospheric pressure negative pulsed gas-liquid discharge with nozzle-cylinder electrode

The plasma characteristics of a gas-liquid phase discharge reactor were investigated by optical and electrical methods.The nozzle-cylinder electrode in the discharge reactor was supplied witha negative nanosecond pulsed generator.The optical emission spectrum diagnosis revealed that OH（A2∑＋ → X2Π,306–309 nm）,N32（CΠ→B3Πg,337 nm）,O（3p5p→3s-5s-0,777.2 nm）and O（3p3p→3s3s0,844.6 nm）were produced in the discharge plasma channels.The electron temperature（Te）was calculated from the emission relative intensity ratio between the atomic O 777.2 nm and 844.6 nm,and it increased with the applied voltage and the pulsed frequency and fell within the range of 0.5–0.8 e V.The gas temperature（Tg）that was measured by Lifbase was in a range from 400 K to 600 K.

Comparative study of pulsed breakdown processes and mechanisms in self-triggered four-electrode pre-ionized switches

This work investigates the pulsed breakdown processes and mechanisms of self-triggered preionized switches with a four-electrode structure in nitrogen through intensified charge coupled device photographs.The diameter of the trigger plane hole mainly determines the switch’s electric field distribution.Two configurations with minimum and maximum trigger plane holes are adopted for comparison.In the switch with a minimum trigger plane hole,the maximum electric field distributes at the surfaces of the main electrodes.Although charged particles in the triggering spark channel cannot drift out,homogeneous discharges can be stimulated from both the cathode and anode surfaces through ultraviolet illumination.Two sub-gaps are likely to break down simultaneously.In the switch with a maximum trigger plane hole,the maximum electric field locates near the trigger electrodes.Discharges in both sub-gaps initiate from the trigger electrodes in the form of a positive or negative streamer.Due to the lower breakdown voltage and electric field threshold for discharge initiation,the cathode side sub-gap breaks down first.The analysis of two extreme examples can be referenced in the future design and improvement of self-triggered four-electrode switches with different trigger electrode structures.

Micro-piezoelectric pulse diagnoser and frequency domain analysis of human pulse signals

Background:The theory of pulse diagnosis is to assess the physiological condition of the human body using radial pulse.However,pulses can vary markedly from person to person.Further,pulse diagnosis is difficult to learn and requires one-on-one teaching.Methods:To address this problem,we built a home-made pulse diagnoser and measured human pulses for studying the standardization of pulse diagnosis.Our pulse diagnoser was composed of a piezoelectric transducer,differential amplifier,data acquisition instrument,and a Matlab analysis program.The measured pulses were converted into electronic signals by a piezoelectric transducer and saved on a computer.The digitalized data were then refined and analyzed by fast Fourier transform for frequency analysis.Simulations were performed to assess the factors that affected the pulse,including phase shifts of reflected pulse waves (generate sub-peaks in pulses),inconsistent heart rates (deform pulse waves),the vessel stiffness (alter harmonic frequencies of the pulses),and the wave amplitudes (determined by the pulse strength).Results:By comparing a published report and our simulation findings,we characterized the pulse types and the effects of various factors,and then applied the findings to study actual pulses in patients.Three types of pulses were determined from the frequency spectrumchoppy pulse (Se mai) without apparent harmonic peaks,the harmonic frequencies of wiry pulse (Xian mai) that are non-integer multiples of the fundamental frequency,and surging pulse (Hong mai) that exhibit strong amplitudes in the spectrum of frequency.A normal pulse and a slippery pulse were differentiated by a phase shift,but not by assessing the frequency spectrum.Conclusion:These findings confirm that frequency domain analysis can avoid ambiguity arising in assessing the three types of pulses in the time domain.Further studies of other pulses in the frequency domain are required to develop a precise electronic pulse diagnoser.

Automated Pulse-Based Diagnosis: Role of TIM Diagnostic Features

Emanated from the idea of reinvestigating ancient medical system of Ayurveda—Traditional Indian Medicine (TIM), our recent study had shown significant applications of analysis of arterial pulse waveforms for non-invasive diagnosis of cardiovascular functions. Here we present results of further investigations analyzing the relation of pulse-characteristics with some clinical and pathological parameters and other features that are of diagnostic importance in Ayurveda.

Investigation on the automatic parameters extraction of pulse signals based on wavelet transform

This paper analyses a key problem in the quantification of pulse diagnosis. Due to the subjectivity and fuzziness of pulse diagnosis,quantitative methods are needed. To extract the parameters of pulse signals,the prerequisite is to detect the corners of pulse signals correctly. Up to now,the pulse parameters are mostly acquired by marking the pulse corners manually,which is an obstacle to modernize pulse diagnosis. Therefore,a new automatic parameters extraction approach for pulse signals using wavelet transform is presented. The results testified that the method we proposed is feasible and effective and can detect corners of pulse signals accurately,which can be expected to facilitate the modernization of pulse diagnosis.

A model for automatic identification of human pulse signals

This paper presents a quantitative method for automatic identification of human pulse signals. The idea is to start with the extraction of characteristic parameters and then to construct the recognition model based on Bayesian networks. To identify depth, frequency and rhythm, several parameters are proposed. To distinguish the strength and shape, which cannot be represented by one or several parameters and are hard to recognize, the main time-domain feature parameters are computed based on the feature points of the pulse signal. Then the extracted parameters are taken as the input and five models for automatic pulse signal identification are constructed based on Bayesian networks. Experimental results demonstrate that the method is feasible and effective in recognizing depth, frequency, rhythm, strength and shape of pulse signals, which can be expected to facilitate the modernization of pulse diagnosis.

Artificial intelligence meets traditional Chinese medicine: a bridge to opening the magic box of sphygmopalpation for pulse pattern recognition

Artificial intelligence(AI) aims to mimic human cognitive functions and execute intellectual activities like that performed by humans dealing with an uncertain environment. The rapid development of AI technology provides powerful tools to analyze massive amounts of data, facilitating physicians to make better clinical decisions or even replace human judgment in healthcare.Advanced AI technology also creates novel opportunities for exploring the scientific basis of traditional Chinese medicine(TCM) and developing the standardization and digitization of TCM pulse diagnostic methodology. In the present study, we review and discuss the potential application of AI technology in TCM pulse diagnosis. The major contents include the following aspects:(1) a brief introduction of the general concepts and knowledge of TCM pulse diagnosis or palpation,(2) landmark developments in AI technology and the applications of common AI deep learning algorithms in medical practice,(3) the current progress of AI technology in TCM pulse diagnosis,(4) challenges and perspectives of AI technology in TCM pulse diagnosis. In conclusion, the pairing of TCM with modern AI technology will bring novel insights into understanding the scientific principles underlying TCM pulse diagnosis and creating opportunities for the development of AI deep learning technology for the standardization and digitalization of TCM pulse diagnosis.

Doctors’Dilemma in Auspicious Pulse Diagnosis Represented in Ming-Qing Fiction

Auspicious pulse diagnosis/pregnancy diagnosis in traditional Chinese medicine involves such issues as medical skills,narrative skills,family decency,and ethics.It is an excellent case for the exploration of ethical dilemmas in traditional Chinese medical practice.The early classical medical texts such as Su Wen(Basic Questions)and Ling Shu Jing(Spiritual Pivot Canon)provide a principle-based ethical guide for doctor-patient communication,while popular fiction such as Hong Lou Meng(A Dream of Red Mansions),Yu Mu Xing Xin Bian(Stories:Entertain to Enlighten),and Feng Yue Meng(Courtesans and Opium)in the Ming and Qing dynasties present literary examples for solving ethical dilemmas.This article will analyze these texts from three perspectives.First,the doctors in the text were subject to gender order and other delicate etiquette and customs,therefore were unable to make the diagnosis without embarrassing the patients and jeopardizing family decency.Second,the narrator tends to attribute pregnancy misdiagnosis to three reasons:incomplete patient information,doctors’poor narrative competence,and doctors’corrupted medical ethics.Finally,the Ming-Qing fiction proposes three methods to solve this moral dilemma:clear pulse reading,tactful speech,and taboo challenging.This discussion of moral dilemmas in pregnancy diagnosis in traditional Chinese medical practice can be used as a reference for the localization of narrative medicine.

The Ability to Visually Recognize Facial Emotions during the Initial Stages of Alzheimer’s

Background: Alzheimer’s sufferers (AS) are unable to visually recognize facial emotions (VRFE). However, we do not know the kind of emotions involved, the timeline for the onset of this loss of ability to recognize facial emotional expressions during the natural course of this disease and the existence of any correlation with other comorbid cognitive disorders. For that reason, the authors aimed to determine whether a deficit in facial emotion recognition is present at the onset of Alzheimer disease, distinctly and concurrently with the onset of cognitive impairment or is it a prodromal syndrome of Alzheimer’s Disease before the onset of cognitive decline and what emotions are involved. A secondary aim was to investigate relationships between facial emotion recognition and cognitive performance on various parameters. Method: Single Blind Case-control study. Setting in Memory clinic. Participants: 12 patients, (AS) and 12 control subjects (CS) were enrolled. Measurements: Quantitative information about the ability for facial emotion recognition was obtained from Method of Analysis and Research on the Integration of Emotions (MARIE). The Mini Mental Status Examination (MMSE), the Picture Naming, the Mattis Dementia Rating Scale (DRS), and the Grober & Buschke Free and Cued Selective Reminding Test (FCSRT) tests were used to measure cognitive impairment. Results: We note that the AS have a problem with the visual recognition of facial emotions with existence of a higher threshold for visual recognition. The AS is less sensitive to the visual recognition cues of facial emotions. AS is unable to distinguish anger from fear. It would be a possible explanation for some acts of aggressiveness seen in the clinical and home setting demonstrated by “AS with behavioral disturbance”. The anger-fear series was found to be the first affected in the course of Alzheimer’s. The appearance of the curve is sigmoid for the control group and linear for the Alzheimer’s patients with a cognitive distortion when the VRFE is represented graphically with percentage of correct recognition plotted on the “y” axis and the selected images presented as stimulus with measures of density of emotion plotted on the “x” axis. In both groups, it is intuitively and theoretically expected that correct recognition will be directly proportional to the density of represented emotion in the stimulus image. This hypothesis is true for CS but not so for AS. The MARIE (see below) processing of emotions seems to be strengthened by the optimal cognitive functions showing the hypothesis applies to CS but not uniformly in AS. This anomaly in the AS is evidenced by the decline of the cognitive functions contributing to abovementioned “linearization” in the graphic representation. There is a direct positive correlation between the results of MARIE and the performance on cognitive tests. Conclusion: The administration of a combination of DRS, FCSRT, and MARIE to patients screened for possibly emerging Alzheimer’s could provide a more detailed and specific approach to make a definitive early diagnosis of Alzheimer’s. The Alzheimer’s patients found it difficult to distinguish between anger and fear.

Covid-19 Diagnosis by Artificial Intelligence Based on Vibraimage Measurement of Behavioral Parameters

The hypothesis of behavioral parameters dependence measured from person’s head movements in quasi-stationary state on COVID-19 disease is discussed. Method for determining the dependence of vestibular-emotional reflex parameters on COVID-19, various diseases and pathologies are proposed. Micro-movements of a head for representatives of the control group (with a confirmed absence of COVID-19 disease) and a group of patients with a confirmed diagnosis of COVID-19 were studied using vibraimage technology. Parameters and criteria for the diagnosis of COVID-19 for training artificial intelligence (AI) on the control group and the patient group are proposed. 3-layer (one hidden layer) feedforward neural network (40 + 20 + 1 sigmoid neurons) was developed for AI training. AI was firstly trained on the primary sample of patients and a control group. Study of a random sample of people with trained AI was carried out and the possibility of detecting COVID-19 using the proposed method was proved a week before the onset of clinical symptoms of the disease. Number of COVID-19 diagnostic parameters was increased to 26 and AI was trained on a sample of 536 measurements, 268 patient measurement results and 268 measurement results in the control group. The achieved diagnostic accuracy was more than 99%, 4 errors per 536 measurements (2 false positive and 2 false negative), specificity 99.25% and sensitivity 99.25%. The issues of improving the accuracy and reliability of the proposed method for diagnosing COVID-19 are discussed. Further ways to improve the characteristics and applicability of the proposed method of diagnosis and self-diagnosis of COVID-19 are outlined.