RESUMO
Several studies have been proposed to estimate blood pressure (BP) with cuffless devices using only a Photoplethysmograph (PPG) sensor on the basis of the physiological knowledge that the PPG changes depend on the state of the cardiovascular system. In these studies, machine learning algorithms were used to extract various features from the wave height and the elapsed time from the rising point of the pulse wave to feature points have been used to estimate the BP. However, the accuracy is still not adequate to be used as medical equipment because their features cannot express fully information of the pulse waveform which changes according to the BP. And, no other effective knowledge about the pulse waveform for estimating BP has been found yet. Therefore, in this study, we focus on the autoencoder which can extract complex features and can add new features of the pulse waveform for estimating the BP. By using autoencoder, we extracted 100 features from the coupling signal of the pulse wave and from its first-order differentiation and second-order differentiation. The result of examination with 1363 test subjects show that the correlation coefficients and the standard deviation of the difference between the measured BP and the estimated BP got improved from R = 0.67, SD = 13.97 without autoencoder to R = 0.78, SD = 11.86 with autoencoder.
Assuntos
Fotopletismografia , Análise de Onda de Pulso , Pressão Sanguínea , Determinação da Pressão Arterial , Frequência CardíacaRESUMO
It is difficult to judge from face images and/or from biological signal (such as brain waves) what the driver's state of cognition is. This paper reports experiments measuring the state of cognition accompanied with gaze movement in the direction of depth. While measuring the cognition time, the experimental setup was able to measure the effect of gaze movement in the direction of depth. When the locations of displays were changed, there was no significant difference in the reaction time for the reflective/discriminative experiment. Experiments conducted to know gaze depth movement show a trend where the longer the gaze moving distance becomes, the more the discernment time increases. Results also show that it takes much more time in moving gaze toward far in the direction of depth as opposed to moving toward the near.