Mental fatigue is an important factor of human health and safety. It is important to achieve dynamic mental fatigue detection by using electroencephalogram (EEG) signals for fatigue prevention and job performance improvement. We in our study induced subjects' mental fatigue with 30 h sleep deprivation (SD) in the experiment. We extracted EEG features, including relative power, power ratio, center of gravity frequency (CGF), and basic relative power ratio. Then we built mental fatigue prediction model by using regression analysis. And we conducted lead optimization for prediction model. Result showed that R2 of prediction model could reach to 0.932. After lead optimization, 4 leads were used to build prediction model, in which R2 could reach to 0.811. It can meet the daily application accuracy of mental fatigue prediction.
When investing the relationship between independent and dependent variables in dose-response meta-analysis, the common method is to fit a regression function. A well-established model should take both linear and non-linear relationship into consideration. Traditional linear dose-response meta-analysis model showed poor applicability since it was based on simple linear function. We introduced a piecewise linear function into dose-response meta-analysis model which overcame this problem. In this paper, we will give a detailed discussion on traditional linear and piecewise linear regression model in dose-response meta-analysis.
ObjectiveTo observe the relationship between the serum level changes of high-sensitivity C-reactive protein (hsCRP), interleukin (IL)-18, intercellular adhesion molecule-1(ICAM1), matrix metalloproteinase (MMP)-9 and lipoprotein-associated phospholipase A2(Lp-PLA2), and the multiple factors of acute cerebral infarction (ACI). MethodsWe chose 76 patients with ACI treated between July 2012 and June 2014 as our study subjects.On the second day (acute phase) and the 15th day (recovery phase) after onset, we checked the patients for their serum levels of hsCRP, IL-18, ICAM1, MMP-9 and Lp-PLA2.Then, multiple linear regression analysis was performed to observe the correlation of the serum level change degree of inflammatory factors with hypertension, diabetes, coronary heart disease, smoking history, carotid atherosclerotic plaque, lipid levels, infarct size and National Institute of Health Stroke Scale (NIHSS) score. ResultsThe changes of all the inflammatory factors in the acute phase and the recovery phase of cerebral infarction were not significantly related to smoking history, hypertension, coronary heart disease, low-density lipoprotein and NIHSS scores (P > 0.05).The changes of hsCRP and ICAM1 had significant correlation with cerebral infarct size, diabetes mellitus and carotid atherosclerotic plaque (P < 0.05), and the change level of Lp-PLA2 was related to diabetes mellitus, and carotid atherosclerotic plaque (P < 0.05).MMP-9 serum level change had correlation with only cerebral infarct size (P < 0.05). ConclusionsSerum level changes of inflammatory factors are related to various factors of cerebral infarction.The main factors that affecting the serum level changes are cerebral infarction area, diabetes mellitus and carotid atherosclerosis.
Portal hypertension (PHT) is a common complication of liver cirrhosis, which could be measured by the means of portal vein pressure (PVP). However, there is no report about an effective and reliable way to achieve noninvasive assessment of PVP so far. In this study, firstly, we collected ultrasound images and echo signals of different ultrasound contrast agent (UCA) concentrations and different pressure ranges in a low-pressure environment based on an in vitro simulation device. Then, the amplitudes of the subharmonics in the echo signal were obtained by ultrasound grayscale image construction and fast Fourier transform (FFT). Finally, we analyzed the relationship between subharmonic amplitude (SA) and bionic portal vein pressure (BPVP) through linear regression. As a result, in the pressure range of 7.5–45 mm Hg and 8–20 mm Hg, the linear correlation coefficients (LCC) between SA and BPVP were 0.927 and 0.913 respectively when the UCA concentration was 1∶3 000, and LCC were 0.737 and 0.568 respectively when the UCA concentration was 1∶6 000. Particularly, LCC was increased to 0.968 and 0.916 respectively while the SAs of two UCA concentrations were used as the features of BPVP. Therefore, the results show a good performance on the linear relationship between SA and BPVP, and the LCC will be improved by using SAs obtained at different UCA concentrations as the features of BPVP. The proposed method provides reliable experimental verification for noninvasive evaluation of PVP through SA in clinical practice, which could be a guidance for improving the accuracy of PVP assessment.
ObjectiveTo provide method references for data visualization of multiple linear regression analysis.MethodsAfter importing data to R Studio, this paper conducted general descriptive statistics analysis, then constructed a linear model between independent variables and the target. After checking independence of observations, the normality of the target, and the linearity between variables, this paper estimated coefficients of independent variables, dealt with multicollinearity, tested significance of estimates and performed residual analysis to guarantee that the regression met its assumptions, and eventually used the fitted model for prediction.ResultsThe multiple linear regression analysis implemented by R Studio software had better visualization functions and easier operation than traditional R language software.ConclusionsR Studio software has good application value in realizing multiple linear regression analysis data visualization.