Microcontroller based RR-Interval measurement using PPG signals for Heart Rate Variability based biometric application

Abstract

Heart Rate Variability (HRV) is a natural property of heart rate. Medical science since last two decades has been viewing at it as a diagnostic and prognostic tool. This study is intended towards harnessing the HRV property of heart for person identification. The highest peak in the ECG signal as well as PPG signal as seen in Figure 1, is known as the R-peak, while the time duration between two adjacent R-peak is known as RR-Interval. RR-Intervals are the only requirement for HRV analysis.Traditionally it is measured from an Electrocardiography (ECG) signals, but we used photoplethysmography (PPG) based pulse sensor and in-house designed microcontroller based RR-Interval measurement system. PPG sensors come in two basic types, one uses transmission and the other one makes use of reflection. We have tested the hardware with both transmission and reflection type sensors. This article is intended to document the performance analysis of both types of PPG sensors. And also present results of biometric identification based on RR-Intervals collected at the fingertips. Classification is done using KNN classifier.

Biometric Systems Utilising Health Data from Wearable Devices

“…This is one of the long-term studes that established: (1) the feasibility of using PPG signals in biometric authentication based on features, such as wave angles, area and inflection point and (2) different physical and mental conditions might cause failure in the authentication as they introduce irregularities or abnormalities in the heart rate. Similar work [3] used PPG signals for HRV based biometric application where the authors designed a physical component to measure the RR-intervals, i.e., the time duration between two adjacent R-peaks of the signal. In this case, the RR-intervals were used as a feature to perform the NN classification.…”

Machine Learning Classification for Assessing the Degree of Stenosis and Blood Flow Volume at Arteriovenous Fistulas of Hemodialysis Patients Using a New Photoplethysmography Sensor Device

“…The k-nearest neighbors (kNN) is a popular non-parametric supervised learning method used for classification or pattern recognition. It is reported to reveal promising results in PPG sensor applications in biometrics identification [24] and in detecting obstructive sleep apnea [25]. The basic concept of kNN is to classify the testing data by training data with the k nearest Euclidean distance.…”

HRV based Human Heart Disease predaction and classification using Maching Learning

“…Resting is useful for healthcare disease prevention. Among HR sensing methods, photoplethysmography (PPG) is known as a simple and non-invasive method, which illuminates the skin by a light emitting diode (LED) and measures the intensity of the light changed by the blood volume pulses (BVPs) under the skin by a photo detector (PD) [14].…”

“…We indicated a heart disease (abnormal) by 1 and healthy (normal) by 0.For purpose of this research; the multi-class classification problem is changed to binary classification problem [17]. Machine learning algorithms are investigated for assessing and predicting the severity of heart failure by artificial neural networks (ANN), Support vector machine (SVM), classification, Logistic regression [14].…”