Real Time Heart Rate Variability Measurement Based on Photoplethysmography Signal Using Smart Phone Application
Abstract
The role of real-time health monitoring systems is to manage patient health and chronic diseases by applying sensor-based technologies to health management. This study aims to design an effective smartphone-based system to measure real-time heart rate variability (HRV) by means of photoplethysmography (PPG) signals, addressing the drawbacks of motion artifacts, physiological differences, computational limitations, and overestimation errors currently associated with other techniques.
Methods/Analysis
Within the proposed system, the fingertip videos are recorded with a smartphone camera, and the PPGs are extracted by analyzing the red, green, and blue (RGB) channels. Preprocessing techniques are used to process the red channel intensity, and signal enhancement is performed by bandpass filtering and fast Fourier transform (FFT). Systolic peaks are detected using peak picking, classification, and HRV estimation is done by using adaptive RGB thresholding and moving variance methods.
Findings
The designed system is capable of measuring heart rate and HRV in real time with better accuracy. The experimental findings prove that the method suggested has a high probability of performance with a low error (~5.97%) rate as compared to a conventional pulse oximeter. The comparison made on the basis of mean, standard deviation and power spectral density (PSD) indicates consistency and validity in the estimation of HRV.
Novelty/Improvement
The proposed model presents a low-complexity real-time HRV monitoring approach on a smartphone that does not require any further hardware. Strong peak detection, adaptive thresholding, and RGB-based PPG extraction are integrated to make it robust and computationally efficient and applicable to real-life applications in healthcare. Nevertheless, measurements of HRV in real-time by smartphone-based PPG signals are associated with a number of limitations such as motion artifacts, changes in illumination, device-specific variations in RGB signals, and signal acquisition noise. This paper aims to solve these problems by proposing an efficient framework that uses adaptive RGB thresholding, motion artifact reduction, and strong signal processing methods. The significant contribution of the work is that it developed a real-time, low-calculation, and device-independent system of monitoring HRV on a smartphone platform, which guarantees a better accuracy and reliability in the practical conditions.
© 2026 S. T. Veerabhadrappa, G. C. Suguna, A. C. Savitha, Ravi Kumar, N. Smitha, published by International Journal on Smart Sensing and Intelligent Systems
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.