NAS-HR:Neural architecture search for heart rate estimation from face videos

Background In anticipation of its great potential application to natural human-computer interaction and health monitoring,heart-rate(HR)estimation based on remote photoplethysmography has recently attracted increasing research attention.Whereas the recent deep-learning-based HR estimation methods have achieved promising performance,their computational costs remain high,particularly in mobile-computing scenarios.Methods We propose a neural architecture search approach for HR estimation to automatically search a lightweight network that can achieve even higher accuracy than a complex network while reducing the computational cost.First,we define the regions of interests based on face landmarks and then extract the raw temporal pulse signals from the R,G,and B channels in each ROI.Then,pulse-related signals are extracted using a plane-orthogonal-to-skin algorithm,which are combined with the R and G channel signals to create a spatial-temporal map.Finally,a differentiable architecture search approach is used for the network-structure search.Results Compared with the state-of-the-art methods on the public-domain VIPL-HR and PURE databases,our method achieves better HR estimation performance in terms of several evaluation metrics while requiring a much lower computational cost1.

Multiscale Entropy under the Inverse Gaussian Distribution： Analytical Results

The multiscale entropy （MSE） reveals the intrinsic multiple scales in the complexity of physical and physiological signals, which are usually featured by heavy-tailed distributions. However, most research results are pure experimental search. Recently, Costa et al. have made the first attempt to present the theoretical basis of MSE, but it only supports the Gaussian distribution [Phys Rev. E 71 （2005） 021906]. We present the theoretical basis of MSE under the inverse Gaussian distribution, a typical model for physiological, physical and financial data sets. The analysis allows for uncorrelated inverse Gaussian process and 1/f noise with the multivariate inverse Gaussian distribution, and then provides a reliable foundation for the potential applications of MSE to explore complev nhwical and Dhwical time series.

Stimulation and Control of Homeostasis

Healthy homeostasis is a principal driving force of the dynamic equilibrium of living organisms. The dynamical basis of homeostasis is the complex and interconnected feedback mechanisms, which are fundamentally governed by the nervous system, mainly the balance of the sympathetic and parasympathetic controlling actions. The balancing regulation is well presented in the heart’s sinus node and can be measured by the time-domain heart-rate variation (HRV) of its frequency domain to analyze the constitutional frequencies of the variation. This last is a fluctuation that shows 1/f time fractal arrangement (f is the composing frequency). The time-fractal arrangement could depend on the structural fractal of the His-Purkinje system of the heart and personally modify the HRV. The cancers gradually destroy the homeostatic harmony, starting locally and finishing systemically. The controlling activity of vagus-nerve changes the HRV or the power density spectrum of the signal fluctuations in malignant development, presenting an appropriate control of the cancerous processes. The modified spectrum by a non-invasive radiofrequency treatment could arrest the tumor growth. An appropriate modulation could support the homeostatic control and force reconstructing of the broken complexity.

Antenatal Noninvasive Fetal Electrocardiography:A Literature Review

Fetal heart rate(FHR)monitoring is one of the central parts of obstetric care.Ultrasound-based technologies such as cardiotocography(CTG)remain the most common method for FHR monitoring.The CTG’s limitations,including subjective interpretation,high interobserver variability,and the need for skilled professionals,led to the development of computerized CTG(cCTG).While cCTG demonstrated advantages,its superiority over visual interpretation remains inconclusive.This has prompted the exploration of alternatives like noninvasive fetal electrocardiography(NIFECG).This review explores the landscape of antenatal FHR monitoring and the need for remote FHR monitoring in a patient-centered care model.Additionally,FHR monitoring needs to evolve from the traditional approach to incorporate artificial intelligence and machine learning.The review underscores the importance of aligning fetal monitoring with modern healthcare,leveraging artificial intelligence algorithms for accurate assessments,and enhancing patient engagement.The physiology of FHR variability(FHRV)is explained emphasizing its significance in assessing fetal well-being.Other measures of FHRV and their relevance are described.It delves into the promising realm of NIFECG,detailing its history and recent technological advancements.The potential advantages of NIFECG are objective FHR assessment,beat-to-beat variability,patient comfort,remote prolonged use,and less signal loss with increased maternal body mass index.Despite its promise,challenges such as signal loss must be addressed.The clinical application of NIFECG,its correlation with cCTG measures,and ongoing technological advancements are discussed.In conclusion,this review explores the evolution of antenatal FHR monitoring,emphasizing the potential of NIFECG in providing reliable,home-based monitoring solutions.Future research directions are outlined,urging longitudinal studies and evidence generation to establish NIFECG’s role in enhancing fetal well-being assessments during pregnancy.

Cardiac autonomic function in patients with myasthenia gravis:analysis of the heart-rate variability in the time-domain

Aim:Myasthenia gravis(MG)is a neuromuscular transmission disorder caused by acetylcholine receptor autoantibodies.Cardiac autonomic dysfunctions were rarely reported in patients with MG.Functional cardiac abnormalities were variable and reported in patients at severe stages of the disease and with thymoma.We investigated cardiac functions in patients with MG using Ambulatory 24‑h electrocardiographic Holter‑Monitoring.Methods:This study included 20 patients with MG with a mean age of 28.45±8.89 years and duration of illness of 3.52±1.15 years.The standard Holter reports include data for heart‑rate,ventricular ectopies(VEs),supraventricular ectopies(SVEs),heart-rate variability(HRV),ST,QT,atrial fibrillation and T‑wave alternans.Results:VEs,SVEs and ST‑T changes were reported in 55%,40%and 20%of patients respectively.Compared with healthy subjects(n=20),HRV components including SDNN,SDANN,SDNN Index,RMS‑SD and pNN50(P=0.001 for all)were reduced in patients indicating sympathetic and parasympathetic autonomic dysfunctions.HRV abnormalities were reported in 30-60%of patients.No significant correlations were identified between SDNN,RMS‑SD,pNN50,and duration of illness.Conclusion:Depressed HRV may be an early manifestation of autonomic neuropathy in patients with MG even in milder stages of the disease.This information is useful in rating disease progression and the efficacy of therapeutic interventions.

Paying less but harvesting more:the effect of unconscious acceptance in regulating frustrating emotion

Previous studies indicate that emotion regulation may occur unconsciously, without the cost of cognitive effort, while conscious acceptance may enhance negative experiences despite having potential long-term health benefits. Thus, it is important to overcome this weakness to boost the efficacy of the acceptance strategy in negative emotion regulation. As unconscious regulation occurs with little cost of cognitive resources, the current study hypothesizes that unconscious acceptance regulates the emotional consequence of negative events more effectively than does conscious acceptance. Subjects were randomly assigned to conscious acceptance, unconscious acceptance and no-regulation conditions. A frustrating arithmetic task was used to induce negative emotion. Emotional experiences were assessed on the Positive Affect and Negative Affect Scale while emotion-related physiological activation was assessed by heart-rate reactivity. Results showed that conscious acceptance had a significant negative affective consequence, which was absent during unconscious acceptance. That is, unconscious acceptance was linked with little reduction of positive affect during the experience of frustration, while this reduction was prominent in the control and conscious acceptance groups. Instructed, conscious acceptance resulted in a greater reduction of positive affect than found for the control group. In addition, both conscious and unconscious acceptance strategies significantly decreased emotion-related heart-rate activity(to a similar extent) in comparison with the control condition. Moreover, heart-rate reactivity was positively correlated with negative affect and negatively correlated with positive affect during the frustration phase relative to the baseline phase, in both the control and unconscious acceptance groups. Thus, unconscious acceptance not only reduces emotion-related physiological activity but also better protects mood stability compared with conscious acceptance. This suggests that the clinical practice of acceptance therapy may need to consider using the unconscious priming of an accepting attitude, instead of intentionally instructing people to implement such a strategy, to boost the efficacy of acceptance in emotion regulation.