Recurrence Plot and Machine Learning for Signal Quality Assessment of Photoplethysmogram in Mobile Environment.

The purpose of this study was to develop a machine learning model that could accurately evaluate the quality of a photoplethysmogram based on the shape of the photoplethysmogram and the phase relevance in a pulsatile waveform without requiring complicated pre-processing. Photoplethysmograms were recorded for 76 participants (5 min for each participant). All recorded photoplethysmograms were segmented for each beat to obtain a total of 49,561 pulsatile segments. These pulsatile segments were manually labeled as 'good' and 'poor' classes and converted to a two-dimensional phase space trajectory image using a recurrence plot. The classification model was implemented using a convolutional neural network with a two-layer structure. As a result, the proposed model correctly classified 48,827 segments out of 49,561 segments and misclassified 734 segments, showing a balanced accuracy of 0.975. Sensitivity, specificity, and positive predictive values of the developed model for the test dataset with a 'poor' class classification were 0.964, 0.987, and 0.848, respectively. The area under the curve was 0.994. The convolutional neural network model with recurrence plot as input proposed in this study can be used for signal quality assessment as a generalized model with high accuracy through data expansion. It has an advantage in that it does not require complicated pre-processing or a feature detection process.

Design of Multi-Wavelength Optical Sensor Module for Depth-Dependent Photoplethysmography.

The multi-wavelength photoplethysmography sensors were introduced to measure depth-dependent blood volume based on that concept that the longer the light wavelength, the deeper the penetration depth near visible spectrum band. In this study, we propose an omnidirectional optical sensor module that can measure photoplethysmogram while using multiple wavelengths, and describe implementation detail. The developed sensor is manufactured by making a hole in a metal plate and mounting an LED therein, and it has four wavelength LEDs of blue (460 nm), green (530 nm), red (660 nm), and IR (940 nm), being arranged concentrically around a photodetector. Irradiation light intensity was measured by photoluminescent test, and photoplethymogram was measured with each wavelength simultaneously at a periphery of the human body such as fingertip, earlobe, toe, forehead, and wrist, in order to evaluate the developed sensor. As a result, the developed sensor module showed a linear increase of irradiating light intensity according to the number of LEDs increases, and pulsatile waveforms were observed at all four wavelengths in all measuring sites.

Development of a Multi-Array Pressure Sensor Module for Radial Artery Pulse Wave Measurement.

This study proposes a new structure for a pressure sensor module that can reduce errors caused by measurement position and direction in noninvasive radial artery pulse wave measurement, which is used for physiological monitoring. We have proposed a structure for a multi-array pressure sensor with a hexagonal arrangement and polydimethylsiloxane that easily fits to the structure of the radial artery, and evaluated the characteristics and pulse wave measurement of the developed sensor by finite element method simulation, a push-pull gauge test, and an actual pulse wave measurement experiment. The developed sensor has a measuring area of 17.6 × 17.6 mm2 and a modular structure with the analog front end embedded on the printed circuit board. The finite element method simulation shows that the developed sensor responds linearly to external pressure. According to the push-pull gauge test results for each channel, there were differences between the channels caused by the unit sensor characteristics and fabrication process. However, the correction formula can minimize the differences and ensure the linearity, and root-mean-squared error is 0.267 kPa in calibrated output. Although additional experiments and considerations on inter-individual differences are required, the results suggested that the proposed multiarray sensor could be used as a radial arterial pulse wave sensor.