Estimation of cardiovascular parameters from ECG and PPG signals

Manimegalai, P.; Jacob, Delpha; Thanushkodi, K.

doi:10.1109/nebc.2012.6207051

Cited by 10 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Reflectance type PPG sensor is designed. [11][12][13] The intensity of light received by the photodetector is sensed, amplified and filtered by the signal conditioning circuit. The output voltage signal of PPG is recorded.…”

Section: Capacitance Plethysmographmentioning

confidence: 99%

Comparative analysis of LDR and OPT 101 detectors in reflectance type PPG sensor

Daimiwal

Sundhararajan²,

Shriram

2014

2014 International Conference on Communication and Signal Processing

View full text Add to dashboard Cite

Detection of blood volume change in the skin by using Photo plethysmogram (PPG) sensor is based on the principle that hemoglobin in the blood absorbs infrared light than the other tissue. Favorable optical window is around 990nm range. The reflectance type photoplethysmographic sensor is designed using two different detectors. Objective is to compare the response of PPG sensor by using Light Dependent resistors (LDR) and OPTlOI as a detector. Signal is recorded by placing the sensor on a finger tip for wavelength ranging from visible to near IR (400 to 1000 nm) range. It is observed that the PPG signal captured using LDR is around 660 nm wavelength but for the OPTI0l response is 500 nm to 1000 nm. That is OPT 101 can be used to capture PPG in visible and infrared region. Brain mapping using optical sensor OPTI0l is preferable for the measurement of blood volume and blood flow. For source of 660 nm, LDR or OPT 101 can be used to detect the peripheral pulse. LDR is not suitable for the measurement in infrared range.

show abstract

Section: Capacitance Plethysmographmentioning

confidence: 99%

Comparative analysis of LDR and OPT 101 detectors in reflectance type PPG sensor

Daimiwal

Sundhararajan²,

Shriram

2014

2014 International Conference on Communication and Signal Processing

View full text Add to dashboard Cite

show abstract

“…However, effect of signal analysis relies on how to choose wavelet basis function. Symlets wavelet updated from daubechies wavelet, not only has biorthogonality, but also with compact support and approximate symmetry [11]. In practical application, symmetry wavelet has engendered commendable effect, therefore has more advantages in details collecting [12].…”

Section: Vehicle Mechatronics and Information Technologiesmentioning

confidence: 99%

Wavelet Based Measurement on Photoplethysmography by Smartphone Imaging

Qian

Ye³

2013

AMM

View full text Add to dashboard Cite

[Purpose] Smartphones video cameras can be used to detect the photoplethysmograph (PPG) signal.The pulse wave signal detected by smartphone always mixed mass noise because of finger moving, unevenness of pressure and outer light interference. Previous studies limit to the filtering algorithm that denoising signals, without considering characteristics information of pulse wave itself. [Method] In this paper, we propose an algorithm based on wavelet to detect qualified PPG, which captures three critical characteristic quantities through wavelet high frequency coefficient. [Results] Experiment illustrates that the detected PPG signal contain dicrotic wave, and whats more, further experiment on artery elasticity indexes indicates good robust of the algorithm. [Conclusions] Wavelet Based Measurement on Photoplethysmography by Smartphone Imaging can be used for the calculation of cardiovascular parameter such as angiosclerosis, arrhythmia, and vascular resistance.

show abstract

“…This enabled the researchers to analyze the sympathetic nerve and parasympathetic nerve activities in automatic nerve systems, thereby allowing the objective assessment of mental fatigue. In Manimegalai et al, 10 convolutional neural network technology was proposed to estimate BP using the formation characteristics of pulse waves. However, compared with public databases for disease classification data, databases that provide PPG measurement data are sparse; researchers frequently encounter the challenges of insufficient data length and the need to organize data.…”

Section: Introductionmentioning

confidence: 99%

Deep learning algorithm evaluation of hypertension classification in less photoplethysmography signals conditions

Yen

Chang

Liao

2021

Measurement and Control

View full text Add to dashboard Cite

This study used photoplethysmography signals to classify hypertensive into no hypertension, prehypertension, stage I hypertension, and stage II hypertension. There are four deep learning models are compared in the study. The difficulties in the study are how to find the optimal parameters such as kernel, kernel size, and layers in less photoplethysmographyt (PPG) training data condition. PPG signals were used to train deep residual network convolutional neural network (ResNetCNN) and bidirectional long short-term memory (BILSTM) to determine the optimal operating parameters when each dataset consisted of 2100 data points. During the experiment, the proportion of training and testing datasets was 8:2. The model demonstrated an optimal classification accuracy of 76% when the testing dataset was used.

show abstract

Estimation of cardiovascular parameters from ECG and PPG signals

Cited by 10 publications

References 8 publications

Comparative analysis of LDR and OPT 101 detectors in reflectance type PPG sensor

Comparative analysis of LDR and OPT 101 detectors in reflectance type PPG sensor

Wavelet Based Measurement on Photoplethysmography by Smartphone Imaging

Deep learning algorithm evaluation of hypertension classification in less photoplethysmography signals conditions

Contact Info

Product

Resources

About