Beats Per Minute Research Articles

Real time system on chip based wearable cardiac activity monitoring sensor

In this research, a real time low power wearable cardiac activity monitoring device is introduced to display real time electrocardiography (ECG) signal and heart rate (HR). ECG records heart’s electrical activity and heart rate measures the contraction of the heart. The developed device consumes very less power as SoC used in this research has power consumption of 85 μW at 1.1V supply voltage. To measure heart rate and ECG waveform, the pre-gelled ECG electrodes are attached on the RA, LA and LL positon of the human’s body. These pre-gelled ECG electrodes attached to the ECG lead which is further connected to the ECG device. The ECG system is validated and the measured average HR of the subject was 71 to 82 beats per minute (BPM) and ECG graph was also plotted.

A solution for co-frequency and low SNR problems in heart rate estimation based on photoplethysmography signals.

In order to realize high-accuracy heart rate (HR) estimation based on photoplethysmography (PPG) under the scenes of low signal-to-noise ratio (SNR) and co-frequency caused by motion artifacts (MAs), this paper presents a novel framework integrating two-stage variational mode decomposition (VMD) denoising method, noise compensation technology, and hidden Markov model (HMM)-based tracking algorithm. The two-stage VMD denoising method is designed to separate the HR signal from MA under low SNR scene. The noise compensation technology is applied to solve the problem of co-frequency. HMM-based HR tracking method is adopted to obtain the global optimization performance of HR estimation. The effectiveness and superiority of the proposed framework in solving problems of low SNR and co-frequency associated with motion artifacts have been verified by the HR estimation experiments carried out on three public high-SNR PPG databases (ISPC, BAMI I, BAMI II) and a self-built low-SNR database (WeData). Compared with the two classical frameworks namely joint sparse spectrum reconstruction (JOSS) and convolutional neural network-long short-term memory network (CNN-LSTM), the proposed framework obtains the lowest HR estimation errors (0.94 beats per minute (BPM) and 1.81 BPM respectively) on both BAMI 2 with the highest SNR (0.40dB) and WeData with the lowest SNR (- 9.07dB). For the low-SNR database Wedata, the average absolute error (AAE) decreases by more than 21 BPM. The research result of this study provides a solution for the realization of high-accuracy PPG-based HR estimation in exercise scenarios.

Smartband for Heartbeat and Oxygen Saturation Monitoring with Critical Warning to Paramedic via IoT

There are vital signs in the human body that indicate important physiological values for the body. In the COVID-19 pandemic, some of the important vital signs that must be monitored are BPM (Beats Per Minute) and SpO2 (oxygen saturation) as indicators of whether a person is in good health or lacks oxygen to predict the early symptoms of COVID-19. The purpose of this study is to create a device on the patient's wrist that can monitor BPM and SpO2 in real-time, as well as provide notifications on smartphones and emails when the patient's condition is abnormal. The contribution of this study is to implement an IoT (Internet of Things) system using a Wi-Fi connection so that monitoring activities are not separated by distance and time. The MAX86141 sensor is used in the design of this tool to detect the BPM and SpO2 values, after which the data is processed and displayed on the ESP32 TTGO T-Display. Monitoring results are also sent to the Blynk, and if the patient's condition is abnormal, an email notification is sent. According to the tool testing results, BPM has the smallest error of 0.94 percent and the largest error of 6.48 percent, whereas SpO2 has the smallest error of 0.20 percent and the largest error of 3.23 percent. The findings of this study can be used to improve the ease and efficiency of body health monitoring activities. This has the potential to significantly improve public health service quality, particularly during the COVID-19 pandemic

Early detection model of normal and abnormal blood flow using pulse Oximetry non-invasive of pregnant heart rate

The heart is an important organ in humans as an identification of early examinations in pregnant women carried out by doctors to determine normal and abnormal pregnancies in the fetus. Heart rate or BPM (beats per minute) is a parameter that indicates the condition of a person's heart. The normal human heart rate ranges from 60-100 beats per minute. In pumping blood throughout the body, the heart then holds it back after being cleaned by the lungs and this is closely related to the level of oxygen flowing in the bloodstream. Humans need sufficient oxygen levels in the body to survive. One of the vital monitoring tools for oxygen levels in the human body is pulse oximetry. Pulse oximetry is usually in units or rooms with high and rapid action cases such as the ICU. From these problems, it is necessary to make a research on a diagnostic instrument model for early detection of normal and abnormal blood flow using non-invasive pulse oximetry, a case study of the heart rate of pregnant women which can be identified early through the max 30100 sensor reading in the form of detecting the heart rate and oximeter, then processed by Arduino uno R3 where arduino uno processes data in the form of heart rate and oxymeter readings so that it can be displayed via a 16x2 LCD, the output is the identification of the value of the heart rate and oximeter input so that the normal and abnormal heart rate conditions are known. The purpose of this study is to detect early pregnant women and fetuses with normal or abnormal blood flow using non-invasive pulse oximetry in which case studies are implemented on the heartbeat of pregnant women. The method used in this study uses the hardware programming method by starting with project planning, research, part testing, mechanical design, electrical design, software design, functional test, integration, overall testing and optimization. The measurement results from the MAX30100 sensor are processed on Arduino UNO R3 and displayed on the LCD screen. The system as a whole can work with energy supply from the power supply. After measuring with a comparator that has been calibrated, the average error value of the measurement is 3.32 %.

Intelligent music accompaniment system based on discrete wavelet transform

Instrument players usually play music with an unstable tempo. However, most of the robotic accompaniment systems are designed with a fixed beat. They can’t adjust their tempo to players’ tempo automatically. Therefore, we propose an adaptive accompaniment system for a soloist that can follow the tempo of a guitar player. The system includes a sound signal receiving element, an audio processing module, a robotic drumming system, and an information display device. The guitar signal is processed with the discrete wavelet transform, audio feature extraction, and peak detection to estimate the tempo of a piece of music, also known as the Beats Per Minute (BPM). In this research, the Daubechies Wavelet (db) is used for signal extraction and reconstruction. The experimental results validate wavelet five (db5) was the effective signal processing method. At the same time, the pedals are also designed to allow the guitarist to change the combination of bass drum and snare drum according to the performance needs. In the research, the guitar signal can be efficiently processed by Discrete Wavelet Transform and then control the drum to follow the guitarist’s tempo.

Early prediction of clinical scores for left ventricular reverse remodeling using extreme gradient random forest, boosting, and logistic regression algorithm representations.

ObjectiveAt present, there is no early prediction model of left ventricular reverse remodeling (LVRR) for people who are in cardiac arrest with an ejection fraction (EF) of ≤35% at first diagnosis; thus, the purpose of this article is to provide a supplement to existing research.Materials and methodsA total of 109 patients suffering from heart attack with an EF of ≤35% at first diagnosis were involved in this single-center research study. LVRR was defined as an absolute increase in left ventricular ejection fraction (LVEF) from ≥10% to a final value of >35%, with analysis features including demographic characteristics, diseases, biochemical data, echocardiography, and drug therapy. Extreme gradient boosting (XGBoost), random forest, and logistic regression algorithm models were used to distinguish between LVRR and non-LVRR cases and to obtain the most important features.ResultsThere were 47 cases (42%) of LVRR in patients suffering from heart failure with an EF of ≤35% at first diagnosis after optimal drug therapy. General statistical analysis and machine learning methods were combined to exclude a number of significant feature groups. The median duration of disease in the LVRR group was significantly lower than that in the non-LVRR group (7 vs. 48 months); the mean values of creatine kinase (CK) and MB isoenzyme of creatine kinase (CK-MB) in the LVRR group were lower than those in the non-LVRR group (80.11 vs. 94.23 U/L; 2.61 vs. 2.99 ng/ml; 27.19 vs. 28.54 mm). Moreover, AUC values for our feature combinations ranged from 97 to 94% and to 87% when using the XGBoost, random forest, and logistic regression techniques, respectively. The ablation test revealed that beats per minute (BPM) and disease duration had a greater impact on the model’s ability to accurately forecast outcomes.ConclusionShorter disease duration, slightly lower CK and CK-MB levels, slightly smaller right and left ventricular and left atrial dimensions, and lower mean heart rates were found to be most strongly predictive of LVRR development (BPM).

An Effective Photoplethysmography Heart Rate Estimation Framework Integrating Two-Level Denoising Method and Heart Rate Tracking Algorithm Guided by Finite State Machine

In order to achieve accurate heart rate (HR) estimation in complex scenes, this paper presents an effective photoplethysmography (PPG) HR estimation framework integrating two-level denoising method and HR tracking algorithm guided by finite state machine (FSM). Aiming at solving the problems of low signal-to-noise ratio and co-frequency (the noise frequency is close to the HR frequency) caused by motion artifacts, the two-level denoising method consisting of the cascaded adaptive filtering and the differential denoising guided by FSM are designed to remove motion-related noises in PPG signals. In order to solve the problem of HR tracking error caused by poor wrist contact, the HR tracking algorithm guided by FSM is proposed to obtain the global optimization capability. The results of HR estimation experiments conducted on the IEEE Signal Processing Cup database and the WeData database created by ourselves show that the proposed framework can effectively cope with the problems of low signal-to-noise ratio and co-frequency. Even if tracking errors occur due to poor wristband contact, the proposed HR tracking algorithm guided by FSM can correct them in time when the HR component appears again. The average absolute error of HR estimation on the two databases are 1.76 BPM (beats per minute) and 2.77 BPM, respectively, which is more accurate compared to other algorithms.

A deep learning approach to estimate pulse rate by remote photoplethysmography

Objective. This study proposes a U-net shaped Deep Neural Network (DNN) model to extract remote photoplethysmography (rPPG) signals from skin color signals to estimate Pulse Rate (PR). Approach. Three input window sizes are used in the DNN: 256 samples (5.12 s), 512 samples (10.24 s), and 1024 (20.48 s). A data augmentation algorithm based on interpolation is also used here to artificially increase the number of training samples. Main results. The proposed model outperformed a prior-knowledge rPPG method by using input signals with window of 256 and 512 samples. Also, it was found that the data augmentation procedure only increased the performance for the window of 1024 samples. The trained model achieved a Mean Absolute Error (MAE) of 3.97 Beats per Minute (BPM) and Root Mean Squared Error (RMSE) of 6.47 BPM, for the 256 samples window, and MAE of 3.00 BPM and RMSE of 5.45 BPM for the window of 512 samples. On the other hand, the prior-knowledge rPPG method got a MAE of 8.04 BPM and RMSE of 16.63 BPM for the window of 256 samples, and MAE of 3.49 BPM and RMSE of 7.92 BPM for the window of 512 samples. For the longest window (1024 samples), the concordance of the predicted PRs from the DNNs and the true PRs was higher when applying the data augmentation procedure. Significance. These results demonstrate a big potential of this technique for PR estimation, showing that the DNN proposed here may generate reliable rPPG signals even with short window lengths (5.12 s and 10.24 s), suggesting that it needs less data for a faster rPPG measurement and PR estimation.

Inappropriate sinus tachycardia: an examination of existing definitions.

Inappropriate sinus tachycardia (IST) is a syndrome characterized by an elevated sinus rate unassociated with known physiological, pathological, or pharmacological causes. Despite published consensus documents, IST definitions appear to vary in the literature. In this study, we reviewed IST publications to evaluate IST definition variability and ascertain the degree to which consensus definitions are being adopted. English-language articles in PubMed, Ovid MEDLINE, Ovid Embase, and Google Scholar published from 1 January 1970 to 1 June 2021 with the title terms 'inappropriate sinus tachycardia,' 'non-paroxysmal sinus tachycardia,' or 'permanent sinus tachycardia' were searched. In each, the IST definition used, qualifying characteristics, and publications cited to support each definition were recorded. We identified 138 publications meeting the search criteria. Inappropriate sinus tachycardia definitions were provided in 114 of 138 articles (83%). A majority of definitions (92/114, 81%) used distinct heart rate (HR) thresholds. Among these, the most common threshold was ≥100 beats per minute (BPM) (75/92, 82%), mainly measured at rest (54/92, 59%). Most definitions (47/92, 51%) included a second criterion to qualify for IST; these were most often an HR threshold of 90 BPM measured over 24 h by ambulatory electrocardiogram (37/47, 79%). Diagnosis of exclusion was a common criterion (75/92, 82%) but symptom status was not (41/92, 45%). The 2015 Heart Rhythm Society IST consensus was commonly cited but adopted in only 37% of definitions published after 2015. Inappropriate sinus tachycardia definitions in current literature are inconsistent, and professional society consensus IST definitions have, to date, had limited impact.

The Comparison of Type of Music Tempo on Cardiopulmonary Function During Exercise

Purpose: The study aimed to examine the effects of beats per minute (BPM) on the cardiopulmonary functions of adult men during exercise and to provide reference materials for future physical therapy studies of the respiratory system.
 Methods: This study recruited 18 healthy male adults who agreed to participate in this study and had no cardiopulmonary problems. The participants conducted a total of five experiments with no music, 30 BPM, 130 BPM, 180 BPM, and 230 BPM, and music education was conducted regarding the music experience before the experiment. The experiment was conducted twice a week for a total of 3 weeks, and one-way analysis of variance was used to compare the mean differences in VO₂max, time, respiratory rate (RR), metabolic equivalents (METs), and peak time between each BPM.
 Results: For each BPM, the VO2max, time, RR, METs, and peak time showed significant differences. With 180 BPM, the VO₂max, time, RR, METs, and peak time were high. For each BPM, the VO₂max, time, RR, METs, and peak time showed significant differences. With 180 BPM, the VO₂max, time, RR, METs, and peak time were high.
 Conclusion: The results of this study show that the most effective BPM for cardiopulmonary functions is 180 BPM, and 180 BPM will enable to perform exercises more efficiently.

1036-P: The Association between Maternal Gestational Weight Gain and Autonomic Nervous System Is Disturbed in GDM: Results from Two-Year-Old Children

Objective: The intrauterine environment is known to affect the offspring's long-term risk for obesity and diabetes. Previous data show that maternal metabolism and gestational weight gain (GWG) are associated with autonomic nervous system (ANS) function in fetuses in utero, which can be assessed with heart rate variability (HRV) . We have now examined whether this association is also present in 2-year-old children and addressed the impact of gestational diabetes (GDM) . Research Design and Methods: We examined children of participants of the ongoing PREG study (NCT04270578) who had a 5-point 75g oral glucose tolerance test during pregnancy. To assess HRV, a 10-minute ECG was recorded in the offspring. We analyzed time domain (beats per minute (BPM) , Root Mean Square of successive differences (RMSSD)) , Standard Deviation of RR-Intervals (SDNN) and frequency domain parameters (low frequency (LF) , high frequency (HF) and LF/HF) of HRV. Results: We examined 67 children (33 girls, 34 boys, age 25.3±1.6 months) . During pregnancy, 30 of their mothers had GDM, which was treated according to national guidelines. There were no differences between groups in birth weight, weight at age 2, and body fat. We observed statistically significant associations of GWG with heart rate, RMSSD, SDNN, HF power, and HF/LF, indicating a lower parasympathetic tone in children of mothers with low GWG. This association was attenuated in GDM-exposed children. ANS function correlated with body weight and body fat only in children from normoglycemic pregnancies (NGT) . Conclusion: We found an impact of maternal GWG on offspring ANS function, which was missing in the presence of treated GDM. The balance of the ANS was related to offspring body composition only in children from NGT pregnancies. Our results point towards a critical impact of maternal weight gain during pregnancy on the developing ANS with longstanding consequences for body composition. Disclosure L.Fritsche: None. H.Preissl: None. M.Heni: Advisory Panel; Boehringer Ingelheim International GmbH, Research Support; Boehringer Ingelheim International GmbH, Sanofi, Speaker's Bureau; Amryt Pharma Plc, Boehringer Ingelheim International GmbH, Novo Nordisk. J.Hartkopf: None. J.Hummel: None. D.Löffler: None. H.Häring: None. A.Peter: None. A.L.Birkenfeld: None. R.Wagner: Advisory Panel; Akcea Therapeutics, Daiichi Sankyo, Sanofi-Aventis Deutschland GmbH, Speaker's Bureau; Lilly, Novo Nordisk, Sanofi-Aventis Deutschland GmbH. A.Fritsche: Advisory Panel; Boehringer Ingelheim International GmbH, Novo Nordisk, Sanofi-Aventis Deutschland GmbH. Funding The PREG study is supported in part by a grant from the Federal Ministry of Education and Research (BMBF) (01GI0925) to the German Center for Diabetes Research (DZD) and by grant from the Deutsche Diabetes Stiftung (380/02/16) to LF

Identity Recognition in Sanitary Facilities Using Invisible Electrocardiography.

This article proposes a new method of identity recognition in sanitary facilities based on electrocardiography (ECG) signals. Our team previously proposed a novel approach of invisible ECG at the thighs using polymeric electrodes, leading to the creation of a proof-of-concept system integrated into a toilet seat. In this work, a biometrics pipeline was devised, which tested four different classifiers, varying the population from 2 to 17 subjects and simulating a residential environment. However, for this approach to be industrially viable, further optimization is required, particularly regarding electrode materials that are compatible with industrial processes. As such, we also explore the use of a conductive silicone material as electrodes, aiming at the industrial-scale production of a toilet seat capable of recording ECG data, without the need for body-worn devices. A desirable aspect when using such a system is matching the recorded data with the monitored user, ideally using a minimal sensor set, further reinforcing the relevance of user identification through ECG signals collected at the thighs. Our approach was evaluated against a reference device for a population of 17 healthy and pathological individuals, covering a wide age range (24–70 years). With the silicone composite, we were able to acquire signals in 100% of the sessions, with a mean heart rate deviation between a reference system and our experimental device of 2.82 ± 1.99 beats per minute (BPM). In terms of ECG waveform morphology, the best cases showed a Pearson correlation coefficient of 0.91 ± 0.06. For biometric detection, the best classifier was the Binary Convolutional Neural Network (BCNN), with an accuracy of 100% for a population of up to four individuals.

The IoT Based Exercise Cycle

The "IOT Based Exercise Cycle" project combines a variety of technologies, including computer hardware and software, to provide bikers with a new modern home exercise solution that immerses them in their surroundings. As a result, a cyclist can monitor some of the most significant training data online via a web page, including speed, distance covered by the rider, heart rate, and oxygen level during exercise. Additionally, depending on the amount of peddling, a cyclist can view flashing pictures on a web page. This cycle is linked to the cyclist's heart rate and temperature, allowing him or her to keep track of their BPM (Heart Beats Per Minute) and body temperature. The system consists of both hardware and software components. Hardware is in charge of gathering, measuring, processing, and transmitting data from sensors. A server contains a Front-End Web page that displays and controls data for cyclists on the software side. Finally, there is a web page that displays all of the parameters that the rider can use to track his or her route.

Heartbeat Rate Monitoring System by Pulse Technique

Abstract: It’s a non-contact method to measure someone’s heart rate, as we will calculate it using simple webcam or even phone’s camera. It will ease to care about your health as we are heading towards an age where everyone is concerned about their health and elevated or abnormal heart rate that can be fatal or serious at least so having a machine that measure your heartbeat is rather expensive and our goal is to use our current resources to measure one’s heartrate without additional cost. Keywords: PPG (Photoplethysmogram), HR (Heart rate), BPM (Beats per minute), HB (Heart beat)

A new principle of pulse detection based on terahertz wave plethysmography

This study presents findings in the terahertz (THz) frequency spectrum for non-contact cardiac sensing applications. Cardiac pulse information is simultaneously extracted using THz waves based on the established principles in electronics and optics. The first fundamental principle is micro-Doppler motion effect. This motion based method, primarily using coherent phase information from the radar receiver, has been widely exploited in microwave frequency bands and has recently found popularity in millimeter waves (mmWave) for breathe rate and heart rate detection. The second fundamental principle is reflectance based optical measurement using infrared or visible light. The variation in the light reflection is proportional to the volumetric change of the heart, often referred as photoplethysmography (PPG). Herein, we introduce the concept of terahertz-wave-plethysmography (TPG), which detects blood volume changes in the upper dermis tissue layer by measuring the reflectance of THz waves, similar to the existing remote PPG (rPPG) principle. The TPG principle is justified by scientific deduction, electromagnetic wave simulations and carefully designed experimental demonstrations. Additionally, pulse measurements from various peripheral body parts of interest (BOI), palm, inner elbow, temple, fingertip and forehead, are demonstrated using a wideband THz sensing system developed by the Terahertz Electronics Lab at Arizona State University, Tempe. Among the BOIs under test, it is found that the measurements from forehead BOI gives the best accuracy with mean heart rate (HR) estimation error 1.51 beats per minute (BPM) and standard deviation 1.08 BPM. The results validate the feasibility of TPG for direct pulse monitoring. A comparative study on pulse sensitivity is conducted between TPG and rPPG. The results indicate that the TPG contains more pulsatile information from the forehead BOI than that in the rPPG signals in regular office lighting condition and thus generate better heart rate estimation statistic in the form of empirical cumulative distribution function of HR estimation error. Last but not least, TPG penetrability test for covered skin is demonstrated using two types of garment materials commonly used in daily life.

PyVHR: a Python framework for remote photoplethysmography.

Remote photoplethysmography (rPPG) aspires to automatically estimate heart rate (HR) variability from videos in realistic environments. A number of effective methods relying on data-driven, model-based and statistical approaches have emerged in the past two decades. They exhibit increasing ability to estimate the blood volume pulse (BVP) signal upon which BPMs (Beats per Minute) can be estimated. Furthermore, learning-based rPPG methods have been recently proposed. The present pyVHR framework represents a multi-stage pipeline covering the whole process for extracting and analyzing HR fluctuations. It is designed for both theoretical studies and practical applications in contexts where wearable sensors are inconvenient to use. Namely, pyVHR supports either the development, assessment and statistical analysis of novel rPPG methods, either traditional or learning-based, or simply the sound comparison of well-established methods on multiple datasets. It is built up on accelerated Python libraries for video and signal processing as well as equipped with parallel/accelerated ad-hoc procedures paving the way to online processing on a GPU. The whole accelerated process can be safely run in real-time for 30 fps HD videos with an average speedup of around 5. This paper is shaped in the form of a gentle tutorial presentation of the framework.

Sensorimotor and working memory systems jointly support development of perceptual rhythm processing.

We studied the role of sensorimotor and working memory systems in supporting development of perceptual rhythm processing with 119 participants aged 7-12years. Children were assessed for their abilities in sensorimotor synchronization (SMS; beat tapping), auditory working memory (AWM; digit span), and rhythm discrimination (RD; same/different judgment on a pair of musical rhythm sequences). Multiple regression analysis revealed that children's RD performance was independently predicted by higher beat tapping consistency and greater digit span score, with all other demographic variables (age, sex, socioeconomic status, music training) controlled. The association between RD and SMS was more robust in the slower tempos (60 and 100 beats-per-minute (BPM)) than faster ones (120 and 180BPM). Critically, the relation of SMS to RD was moderated by age in that RD performance was predicted by beat tapping consistency in younger children (age: 7-9 years), but not in older children (age: 10-12years). AWM was the only predictor of RD in older children. Together, the current findings demonstrate that the sensorimotor and working memory systems jointly support RD processing during middle-to-late childhood and that the degree of association between the two systems and perceptual rhythm processing is shifted before entering into early adolescence.

Safety and Efficacy of External Nasal Dilator Strips with N95 Respirator Masks by Emergency Department Personnel.

INTRODUCTIONThe coronavirus disease 2019 (COVID-19) pandemic has prompted increased use of personal protective equipment (PPE) to maintain the health and safety of caregivers. This study was conducted in 2020 to evaluate the safety and efficacy of external nasal dilator strips (ENDS) coupled with N95 respirators in a sample of community hospital emergency department personnel.METHODSAfter obtaining written consent, the authors tested participants’ response to exercise (i.e., walking up 10 flights of stairs) while wearing an N95 respirator, both with and without an ENDS. The authors measured participants’ heart rate and respiratory effort responses over four minutes following their exercise trial. A convenience sample of these personnel also repeated their respirator fit testing while wearing an ENDS with the N95 style they had previously been fitted for.RESULTSA total of N = 50 participants were enrolled. Peak heart rate while wearing an ENDS was 125 beats per minute (BPM) with the ENDS versus 130 BPM without (p = 0.21). The Borg Exertion Score while wearing an ENDS peaked at 13 with the ENDS versus 14 without (p = 0.08). However, when subjects were surveyed before and after the trial upon whether they would consider using an ENDS beneath their N95 using a scale of 1-5, their interest in this significantly increased (p = 0.004). Four of the 13 (31%) participants who completed repeated fit testing while wearing the ENDS beneath their N95 respirator failed the repeat testing.CONCLUSIONSThese results first suggest that a sizable proportion of ED personnel may fail N95 fit testing while wearing an ENDS beneath the N95 mask for which they had been previously fitted. Although providers’ subjective interest in use of ENDS increased, these results also demonstrate that use of an ENDS beneath an N95 respirator may not significantly increase exercise tolerance.

1-Dimentional Convolutional Neural Network based Heart Rate Estimation Using Photoplethysmogram Signals

Recently, as the importance of healthcare has increased, researches are being conducted to measure health status in real time. Heart Rate (HR) measurement is one of the important health conditions that measure heart beat rates. HR measurement can be performed using Photoplethysmogram (PPG) or Electrocardiogram (ECG) signals. Since the PPG or ECG signals are different from people to people, conventional HR estimator occasionally results in large errors. To develop a reliable HR estimator, an HR estimation technique using PPG is proposed in this paper, based on a deep learning technique. The proposed HR estimation technique has the following key features. We develop a new artificial neural network which is 1-Dimensional Convolutional Neural Network (1D-CNN) composed of ten convolutional layers and two fully connected layers. To assess the estimation performance, cross validation is used. The training and verification of the proposed 1D-CNN technique are performed on Python 3.7.5 with Keras 2.0 library. The proposed HR estimation technique performs training and verification using field PPG data. Overfitting is prevented by increasing the limited training data by data augmentation. In training, the loss function is the Mean Square Error (MSE), which is commonly used in regression problems. In the verification, the error between the predicted HR and the actual HR is compared using Mean Absolute Error (MAE). As a result of the final performance verification through cross validation, the proposed technique shows an MAE of 1.23 Beats Per Minute (BPM). This results indicate that the proposed technique enables quick and accurate HR estimation with only PPG signals. Therefore, if this technique is applied to medical and wearable devices, the proposed technique can replace the existing HR monitors.

Data-Driven Computer Choreography Based on Kinect and 3D Technology

As a form of artistic expression, dance accompanied by music enriches the cultural life of human beings and stimulates the creative enthusiasm of the public. Choreography is usually done by professional choreographers. It is highly professional and time-consuming. The development of technology is changing the way of artistic creation. The development of motion capture technology and artificial intelligence makes computer-based automatic choreography possible. This paper proposes a method of music choreography based on deep learning. First, we use Kinect to extract and filter actions and get actions with high authenticity and continuity. Then, based on the constant Q transformation, the overall note density and beats per minute (BPM) of the target music are extracted, and preliminary matching is performed with features such as action speed and spatiality, and then, the local features of the music and action segments based on rhythm and intensity are matched. The experimental results show that the method proposed in this paper can effectively synthesize dance movements. The speed and other characteristics of each movement segment in the synthesis result are very uniform, and the overall choreography is more aesthetic.