Real-time Heart Rate Monitoring Research Articles

Lightweight and interpretable convolutional neural network for real-time heart rate monitoring using low-cost video camera under realistic conditions

Recent research has shown that a person's heart rate (HR) can be estimated using video data through remote photoplethysmography (rPPG). However, this approach is faced with various challenges, including the inability to prepare training data that encompasses all realistic conditions, the impact of complex inference models on reasoning speed, and the lack of interpretability that hinders medical and healthcare applications. To tackle these issues, a lightweight and interpretable convolutional neural network is proposed for real-time HR monitoring using a low-cost video camera under realistic conditions. The Mediapipe framework is leveraged to construct a facial detection and tracking pipeline that is robust to head movements and illumination changes. Empirical mode decomposition (EMD) is then combined with a channel-wise attention-based convolutional neural network (CNN) for HR inference. Additionally, a temporal long-term peak merge method is proposed as a post-processing step to further enhance the accuracy of the neural network inference. The results of linear regression and Bland-Altman analysis demonstrate consistency between the estimated HR values and the ground truth. Moreover, experimental outcomes show no significant difference in the inference times of the proposed method running with or without a GPU, with a reasoning speed on mobile CPU remaining within 100 ms, ensuring real-time HR monitoring. Furthermore, this study provides pioneering empirical evidence to open the black box of neural networks in HR monitoring using rPPG signals.

Abnormal heart rate detection through real-time heart monitoring application

Health monitoring that requires doctors and patients at the healthcare center may not be practical during the coronavirus disease 2019 (COVID-19) pandemic. Alternatively, mobile health (mHealth) should be embraced to minimize contact between patients and healthcare personnel. This research aims to enhance the detection of abnormal heart rate (HR) detection by developing a real-time heart rate monitoring (RTHM) application. Sixteen healthy adults participated in a physical real-time HR monitoring testbed. Participants HR was measured for three minutes resting and three minutes performing moderate-intensity physical activity. The results were compared with the polar beat app. Additionally, the energy consumption, the time taken to receive an alarm message, and an acceptance test were analyzed. The app is acceptably accurate, the mean absolute percentage error less than 2%. The response time to receive the alarm message is 30 seconds on average, which is under an acceptable range of medical standards. Moreover, the app is power efficient, 477 mW on average. Participants show a positive attitude towards using RTHM. RTHM is expected to provide a more plausible tool for monitoring the heart towards enhancing abnormal HR detection by promoting patient-oriented healthcare and minimizing sudden deaths due to heart failure.

Abnormal heart rate detection through real-time heart monitoring application

Health monitoring that requires doctors and patients at the healthcare center may not be practical during the coronavirus disease 2019 (COVID-19) pandemic. Alternatively, mobile health (mHealth) should be embraced to minimize contact between patients and healthcare personnel. This research aims to enhance the detection of abnormal heart rate (HR) detection by developing a real-time heart rate monitoring (RTHM) application. Sixteen healthy adults participated in a physical real-time HR monitoring testbed. Participants HR was measured for three minutes resting and three minutes performing moderate-intensity physical activity. The results were compared with the polar beat app. Additionally, the energy consumption, the time taken to receive an alarm message, and an acceptance test were analyzed. The app is acceptably accurate, the mean absolute percentage error less than 2%. The response time to receive the alarm message is 30 seconds on average, which is under an acceptable range of medical standards. Moreover, the app is power efficient, 477 mW on average. Participants show a positive attitude towards using RTHM. RTHM is expected to provide a more plausible tool for monitoring the heart towards enhancing abnormal HR detection by promoting patient-oriented healthcare and minimizing sudden deaths due to heart failure.

An improved real-time detection algorithm based on frequency interpolation

Real-time monitoring of heart rate (HR), i.e., extraction of heart rate variability (HRV), plays an important role in diagnosis and prevention of cardiovascular diseases. Compared with traditional contact monitoring devices, the use of continuous wave (CW) Doppler radar to monitor HRV does not require contact and is not sensitive to light and temperature, which makes it more and more popular. To monitor the HRV based on CW Doppler radar, the time window must be shortened to less than 5 s, which will lead to the spectrum leakage and degrade the measurement accuracy of HRV. To solve this problem, a custom CW Doppler radar has been developed in an integrated fashion on a single PCB, whose transmitting frequency and power of the radar are 24 GHz and 3 dBm, respectively. Furthermore, four frequency interpolation algorithms are introduced to compare their extraction accuracy. Experiments are performed on three subjects, and results show that the Quinn algorithm can obtain best HRV extraction results compared with other algorithms. Specially, the average HRV extraction error is 3.61% using the Quinn algorithm.

Standardized motion detection and real time heart rate monitoring of aerobics training based on convolution neural network

In order to make the teaching and training of aerobics more standardized, it is necessary to use scientific means to detect and monitor the movement standardization in teaching and training and the change of human heart rate in the training process, but at present, there are some difficulties in both detection and monitoring, Therefore, this paper proposes to use the advantages of convolutional neural network to solve the current aerobics teaching problems of motion detection and heart rate monitoring. In the process of operation, the complete aerobics video needs to be divided into several different images, the standardized action image background needs to be eliminated, and then the visual error caused by the difficult action image needs to be corrected. On the premise of image processing, the convolutional neural network is used to pre train the image, and the skeleton map of the human body is constructed in the computer. In the process of practical operation, the use of convolutional neural network for heart rate monitoring has many advantages. It can not only save the time of contact with the human body, but also integrate various information of the time dimension, reducing a lot of computing steps, saving a lot of computing resources for practical work, and promoting the improvement of system output signal quality to a certain extent. The result of the experiment also proves that the convolutional neural network can improve the accuracy of students' movement detection and heart rate change monitoring in aerobics teaching and training.

Self-Filtered NIR Photodetectors Based on Silicon Micro-Holes Array for Stable Heart Rate Monitoring

Here, we presented a novel near-infrared (NIR) photodetectors based on Si micro-holes array/graphene (SiMHs/Gr) Schottky barrier diode (SBD) for monitoring heart rate. The SBD exhibited a unique self-filtered NIR response in a range from 900 nm to 1160 nm with a responsivity of 122 mA/W at zero bias voltage. Moreover, our device possessed an ultrahigh signal to noise ratio (SNR) of more than <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$10^{{5}}$ </tex-math></inline-formula> between visible and NIR light. The presented self-filtered NIR photodetector was used as a non-contact transmission-type photoplethysmography sensor for real-time heart rate monitoring. Due to the suppression of disturbances caused by ambient light, our device performed more accurate heart rate monitoring than those extracted from commercial broadband photodetectors.

Validation of Wearable Device Consisting of a Smart Shirt with Built-In Bioelectrodes and a Wireless Transmitter for Heart Rate Monitoring in Light to Moderate Physical Work

Real-time monitoring of heart rate is useful for monitoring workers. Wearable heart rate monitors worn on the upper body are less susceptible to artefacts caused by arm and wrist movements than popular wristband-type sensors using the photoplethysmography method. Therefore, they are considered suitable for stable and accurate measurement for various movements. In this study, we conducted an experiment to verify the accuracy of our developed and commercially available wearable heart rate monitor consisting of a smart shirt with bioelectrodes and a transmitter, assuming a real-world work environment with physical loads. An exercise protocol was designed to light to moderate intensity according to international standards because no standard exercise protocol for the validation simulating these works has been reported. This protocol includes worker-specific movements such as applying external vibration and lifting and lowering loads. In the experiment, we simultaneously measured the instantaneous heart rate with the above wearable device and a Holter monitor as a reference to evaluate mean absolute percentage error (MAPE). The MAPE was 0.92% or less for all exercise protocols conducted. This value indicates that the accuracy of the wearable device is high enough for use in real-world cases of physical load in light to moderate intensity tasks such as those in our experimental protocol. In addition, the experimental protocol and measurement data devised in this study can be used as a benchmark for other wearable heart rate monitors for use for similar purposes.

Effect Of Flexi-bar Exercise Intervention On Cognitive Function Of Middle-aged And Elderly Women

BACKGROUND:Aerobic training (AT) can improve the ability of working memory and inhibitory control of healthy elderly. Flexi-Bar vibration exercise, as a special form of exercise has been confirmed to have a positive effect on the cognition. This study aimed to evaluate whether Flexi-Bar exercise can be used as an effective intervention to delay the decline of cognitive function caused by aging and its potential mechanism. METHODS:A total of 30 middle-aged and elderly sedentary women (aged 55.47 ± 5.45 years) were randomly divided into the intervention group and the control group. Mini-mental State Examination (MMSE) and international physical activity questionnaire (iPAQ) were administered at baseline before randomization. The ability of inhibitory control was assessed via the Stroop task before and after the whole intervention. Functional near-infrared spectroscopy (fNIRS) was used to measure the oxygenated hemoglobin (O2Hb) concentrations in the prefrontal area. The intervention group was given the Flexi-Bar exercise intervention 3 days/week for 8 weeks with an intensity of 50 ~ 65% HRmax for 1 hour/day, and the real-time heart rate monitoring was carried out during the intervention. The control group only maintained normal daily life. RESULT:(1) Compared with the control group, O2Hb in the left ventral dorsolateral prefrontal lobe in the exercise group significantly increased (p < 0.05, t = 2.46). (2) Compared with the pre-test of EX group, the brain-derived nerve growth factor (BDNF) in the intervention group significantly increased after the intervention (p < 0.05, t = 2.304), but there was no significant difference in the control group (p > 0.05). (3) In terms of epigenetic miRNA, a total of 165 differentially expressed miRNAs were screened between the intervention group and the control group, of which 60 miRNAs were related to the cognitive function. In the intervention group, 4 miRNAs positively correlated with cognitive decline were down-regulated (all p < 0.01). The down-regulation of miR-126-5p and miR-21-5p was negatively correlated with the expression of BDNF. CONCLUSION:These findings supported our hypothesis by demonstration of a beneficial effect of Flexi-Bar exercise that can improve the cognitive function of middle-aged and elderly people.

Research on noncontact heart rate detection based on face tracking and BVP signal extraction

The noncontact heart rate detection technology is very suitable for daily health monitoring due to its advantages of no contact with the human body, simple operation, and low cost. However, this technique is susceptible to ambient light variation interference and motion artifacts. In addition, most of the existing HR (real-time heart rate monitoring) detection studies based on remote photoplethysmography only focus on illumination variation interference or motion artifacts, and few studies consider both illumination variation interference and motion artifacts. First, a nonparametric skin color segmentation model and support vector machine (SVM) are used in the Cb and Cr components of the YCbCr color space to construct a joint skin color segmentation model specific to the current video sequence, to remove the skin-like background in the video frame in a coarse-to-fine manner. Subsequently, the CamShift algorithm color histogram is constructed within the Cr component and face tracking is performed. It should be noted that the use of SVM to build a skin color segmentation model is based on the following three considerations: first, the skin color segmentation algorithm based on SVM has a relatively fast running speed. Second, considering skin color and background sample information at the same time will help to improve the accuracy of skin color segmentation. Third, SVM can enhance the generalization ability of the learning machine according to the principle of structural risk minimization, which makes the skin color segmentation model based only on video standard frames can also play a better role in the segmentation of subsequent video frames. The experimental results show that the proposed algorithm has higher accuracy for noncontact heart rate detection than the original algorithm; compared with the tracking algorithm in recent years, it has good tracking accuracy and obvious speed advantage.

Continuous time series analysis on the effects of induced running fatigue on leg symmetry using kinematics and kinetic variables: Implications for knee joint injury during a countermovement jump.

This study investigates the symmetry change in joint angle and joint moment of knee joints following a Running-Induced Fatigue counter movement Jump. Twelve amateur runners volunteered to participate in the study. A prolonged running protocol was used to induce fatigue. Joint angle and moment were recorded during the push and flexion phase of the CMJ before and immediately after fatigue. Borg scale (RPE>17) and real-time heart rate monitoring (HR>90%HRmax) were used to confirm running fatigue. Symmetry function (SF) was used to assess the symmetry of the knee Angle and moment variation parameters over the entire push-off and landing phases based on time series analysis. Paired sample t-test was used to examine changes in SF before and after acute fatigue. The Angle and moment of the knee are asymmetrical in all planes (SF > 0.05), with SF ranging from 5 to 130% in angle and 5–110% in moment. There was a significant increase in knee joint angle asymmetry in the horizontal plane during the push-off and landing stage following the prolonged - Running Protocol implementation. These increases in asymmetry are mainly caused by excessive external rotation of the dominant knee joint. These findings indicate that fatigue-induced changes during CMJ may progress knee movement pattern asymmetry in the horizontal plane.

WITHDRAWN: Computational efficient wearable sensor network health monitoring system for sports athletics using IoT

Abstract The rapid development and growth in the Internet of Things (IoT) area offer great potential in the healthcare sector. Currently, wireless technology, fitness trackers, and body sensors in the sports field have a major impact on living efficiency and health system reliability. Wearable devices have become increasingly interested in measuring physiological factors, promoting health, and improving adherence to the practice in different populations from elite athletes to patients. In this paper, fog assisted Computational efficient Wearable sensor networks (FCE-WSN) has been proposed in health monitoring systems for sports athletic using IoT. The wearable device for the continuous real-time monitoring of heart rate, respiratory frequency, and movement cadence during physical activity has been analyzed. Besides, the sensor collected data is uploaded to the IoT-connection system Ethernet module, and the Authorized Individual accesses the data via the internet to track the athletics health. Moreover, the wearable device's analytical model and its use illustrate how computing resources' costs can be minimized while preserving health requests for access to medical information stored in a fog and cloud distribution setting. Our assessment system depends on a queue and can estimate the minimum computing resources needed to achieve the Service Level Agreement (SLA) (both fog and cloud nodes). The experimental results show that the proposed method is user-friendly, reliable, and economical to use regularly.

An IoMT system for health monitoring in athletes

Continuous health monitoring in real-time has become essential to improve people's quality of life through medical prescription or personal control. Our goal is to develop a wearable IoMT device with real-time monitoring of heart rate and breathing patterns while an athlete performs physical exercise at high-intensity intervals. The wearable IoMT device incorporates vital signs sensors to record and display information in a mobile application, allowing users to track their health and receive an alert if the data exceeds normal parameters.

SWIR Photodetection and Visualization Realized by Incorporating an Organic SWIR Sensitive Bulk Heterojunction.

Short‐wavelength infrared (SWIR) photodetection and visualization has profound impacts on different applications. In this work, a large‐area organic SWIR photodetector (PD) that is sensitive to SWIR light over a wavelength range from 1000 to 1600 nm and a SWIR visualization device that is capable of upconverting SWIR to visible light are developed. The organic SWIR PD, comprising an organic SWIR sensitive blend of a near‐infrared polymer and a nonfullerene n‐type small molecule SWIR dye, demonstrates an excellent capability for real‐time heart rate monitoring, offering an attractive opportunity for portable and wearable healthcare gadgets. The SWIR‐to‐visible upconversion device is also demonstrated by monolithic integration of an organic SWIR PD and a perovskite light‐emitting diode, converting SWIR (1050 nm) to visible light (516 nm). The most important attribute of the SWIR visualizing device is its solution fabrication capability for large‐area SWIR detection and visualization at a low cost. The results are very encouraging, revealing the exciting large‐area SWIR photodetection and visualization for a plethora of applications in environmental pollution, surveillance, bioimaging, medical, automotive, food, and wellness monitoring.

Is Continuous Heart Rate Monitoring of Livestock a Dream or Is It Realistic? A Review.

For all homoeothermic living organisms, heart rate (HR) is a core variable to control the metabolic energy production in the body, which is crucial to realize essential bodily functions. Consequently, HR monitoring is becoming increasingly important in research of farm animals, not only for production efficiency, but also for animal welfare. Real-time HR monitoring for humans has become feasible though there are still shortcomings for continuously accurate measuring. This paper is an effort to estimate whether it is realistic to get a continuous HR sensor for livestock that can be used for long term monitoring. The review provides the reported techniques to monitor HR of living organisms by emphasizing their principles, advantages, and drawbacks. Various properties and capabilities of these techniques are compared to check the potential to transfer the mostly adequate sensor technology of humans to livestock in term of application. Based upon this review, we conclude that the photoplethysmographic (PPG) technique seems feasible for implementation in livestock. Therefore, we present the contributions to overcome challenges to evolve to better solutions. Our study indicates that it is realistic today to develop a PPG sensor able to be integrated into an ear tag for mid-sized and larger farm animals for continuously and accurately monitoring their HRs.

Heart Rate Monitoring with Smart Wearables using Edge Computing

Heart is a vital component of every human health. The development of wearables and its sensor enables the possibility of easy-to-use real-time monitoring. The goal of this study is to improve an IoT monitoring system by enabling real-time heart rate monitoring and analysis, also to assess the use of PPG sensors in smart wearables compared to other clinical-tested heart rate sensors. The PPG sensor will be used to record heart rate data of the user physically. The measurements are then sent to the application for pre-processing. The application can then transmit the pre-processed measurements to the cloud server for monitoring or further analysis, i.e. to assess the health of users’ heart. The measurement comparison with measurement collected by a BCG sensor is carried out in this paper. While neither are standard for heart rate measurements, the findings of the evaluation show that the PPG sensor achieves quite similar input data and assessment results during awake stages. The Fitbit sensor tested often underestimates, with sometimes delayed or doesn’t detect a sudden increase in heart rate during sleeping.

A Proof-of-Concept 70 nA ECG Processor for Real-Time R-Wave and NN50 Detection

Unobtrusive health monitoring applications necessitate accurate, real-time, and energy-efficient computation of health-related parameters. Two important parameters for cardiovascular and cardiac autonomic health assessment are heart rate (HR) and heart rate variability (HRV). In this paper, an energy-efficient mixed-signal processor ASIC for real-time monitoring of HR and NN50, a well-established HRV score for parasympathetic activity assessment, is presented. The proposed ASIC, designed in a 0.5 μm CMOS technology, detects R-waves of ECG signals and compares successive R-R intervals to identify the NN50 events in real-time. Post-layout simulation results using ECG signals of four recordings from the MIT-BIH arrhythmia database are compared with DSP calculations on MATLAB. Based on simulation results, the processor detects R-waves with an average accuracy of 99.1%, and NN50 events with average sensitivity and positive predictive values of 94.7% and 96.9%, respectively. The processor consumes 70 nA when supplied by ±1.6 V.

How do I track Cardiac Rehabilitation in my patient with ischemic heart disease using Strava

Abstract Cardiac rehabilitation is a program which reduces morbidity and mortality in patients with ischemic heart disease. However only some European centers provide these programs for patients diagnosed with cardiac ischemia. Therefore home-based programs were developed for cardiac rehabilitation. Strava is a social network developed to track activities of running and cycling both in athletes and individuals searching for recreation and sport activities. In our work we present an approach based on Strava tracking to improve the quality of cardiac rehabilitation. Real-time monitoring of heart rate, steps per minute and speed during recreational or competitive activities can be used to increase physical capacity in individuals with ischemic heart disease. Key words: cardiac rehabilitation, Strava, ischemic heart disease, home-based,

A Flexible Wireless Sensor Patch for Real-Time Monitoring of Heart Rate and Body Temperature

A Flexible Wireless Sensor Patch for Real-Time Monitoring of Heart Rate and Body Temperature

Heart rate measures from the Apple Watch, Fitbit Charge HR 2, and electrocardiogram across different exercise intensities

ABSTRACTThis study compared heart rate (HR) measurements for the Fitbit Charge HR 2 (Fitbit) and the Apple Watch devices with HR measurements for electrocardiogram (ECG). Thirty young adults (15/15 females/males, age 23.5 ± 3.0 years) completed the Bruce Protocol. HR measurements were recorded from the ECG and both devices every minute. Average HR for each participant was calculated for very light, light, moderate, vigorous and very vigorous intensities based on ECG-measured HR. A concordance correlation coefficient (CCC) was calculated to examine the strength of the relationship between ECG measured HR and HR measured by each device. Relative error rates (RER) were also calculated to indicate the difference between each device and ECG. An equivalence test was conducted to examine the equivalence of HRs measured by devices and ECG. The Apple Watch showed lower RER (2.4–5.1%) compared with the Fitbit (3.9–13.5%) for all exercise intensities. For both devices, the strongest relationship with ECG-measured HR was found for very light PA with very high CCC (>.90) and equivalence. The strength of the relationship declined as exercise intensity increased for both devices. These findings indicate that the accuracy of real-time HR monitoring by the Apple Watch and Fitbit Charge HR2 is reduced as exercise intensity increases.

A Pilot Study on Real-time Monitoring of Heart Rate and Movement Speed in Middle-distance Race of Physical Education Classes

In Chinese universities, students need to participate in the middle-distance-race. Normally, female students are required to participate in the race of 800 meters, while male students are required to participate in the race of 1000 meters. However, it is difficult for teachers to grasp the real time information of students during the race. And there is a lack of timely communications between the teachers and students. Focusing on this issue, this study, with the use of POLAR heart rate sensor and other modern information technologies, expands the original function of the sensor to achieve a concurrent operation of detecting heart rates and automatically measuring the movement speed. The researchers have successfully designed a micro system to monitor the process of middle-distance race. Moreover, the study also engages in a preliminary experiment verification so as to provide object and effective reference and basis for the middle-distance race physical education teaching in universities.