In the past two decades, software aging has been studied by both academic and industry communities. Many scholars focused on analytical methods or time series to model software aging process. While machine learning ha...In the past two decades, software aging has been studied by both academic and industry communities. Many scholars focused on analytical methods or time series to model software aging process. While machine learning has been shown as a very promising technique in application to forecast software state: normal or aging. In this paper, we proposed a method which can give practice guide to forecast software aging using machine learning algorithm. Firstly, we collected data from a running commercial web server and preprocessed these data. Secondly, feature selection algorithm was applied to find a subset of model parameters set. Thirdly, time series model was used to predict values of selected parameters in advance. Fourthly, some machine learning algorithms were used to model software aging process and to predict software aging. Fifthly, we used sensitivity analysis to analyze how heavily outcomes changed following input variables change. In the last, we applied our method to an IIS web server. Through analysis of the experiment results, we find that our proposed method can predict software aging in the early stage of system development life cycle.展开更多
Objective Brachial-ankle pulse wave velocity （baPWV） is widely used as a simple noninvasive measure of arterial softness. The aim of this study was to evaluate the usefulness of baPWV as a predictor of the carotid a...Objective Brachial-ankle pulse wave velocity （baPWV） is widely used as a simple noninvasive measure of arterial softness. The aim of this study was to evaluate the usefulness of baPWV as a predictor of the carotid artery atherosclerosis in the elderly. Methods A total of 721 elderly participants （mean ~ SD age, 70.3 -4- 5.6years） were enrolled in the current study. All participant underwent both baPWV measurement and B-mode ultrasound for the intima-media thickness. Carotid atherosclerosis （CAS） was defined as the present of carotid plaque or and/or intima media thickness for at least 1.1 mm. Results A multivariate logistic regression analysis reveals that age, sex, brachial-ankle pulse wave velocity, smoking and LDL-C level showed a significant correlation with the presence of CAS. The odds ratios of CAS associated with a 500cm/s increase of brachial-ankle pulse wave velocity were 2.378 [95% confidence interval, 1.36 to 4.00, P〈0.05], 3.733 [95% confidence interval, 1.729 to 8.058, P〈0.01], 4.438 [95% confidence interval, 1.659 to 11.803, P〈0.01]. The baPWV significantly correlated with IMT by bivariate correlation analysis （r=-0.39; p=0.001）. After adjusting for factors influencing, baPWV all the same correlated with IMT （r=-0.35; p=0.001）.Conclusion These results indicate that brachial-ankle PWV is an independent predictor of CAS in the elderly.It also means that the direct measurement of arterial stiffness by this simple method may be of great help for the evaluation of carotid artherosclerosis, at least in the elderly展开更多
基金supported by the grants from Natural Science Foundation of China(Project No.61375045)the joint astronomic fund of the national natural science foundation of China and Chinese Academic Sinica(Project No.U1531242)Beijing Natural Science Foundation(4142030)
文摘In the past two decades, software aging has been studied by both academic and industry communities. Many scholars focused on analytical methods or time series to model software aging process. While machine learning has been shown as a very promising technique in application to forecast software state: normal or aging. In this paper, we proposed a method which can give practice guide to forecast software aging using machine learning algorithm. Firstly, we collected data from a running commercial web server and preprocessed these data. Secondly, feature selection algorithm was applied to find a subset of model parameters set. Thirdly, time series model was used to predict values of selected parameters in advance. Fourthly, some machine learning algorithms were used to model software aging process and to predict software aging. Fifthly, we used sensitivity analysis to analyze how heavily outcomes changed following input variables change. In the last, we applied our method to an IIS web server. Through analysis of the experiment results, we find that our proposed method can predict software aging in the early stage of system development life cycle.
文摘Objective Brachial-ankle pulse wave velocity （baPWV） is widely used as a simple noninvasive measure of arterial softness. The aim of this study was to evaluate the usefulness of baPWV as a predictor of the carotid artery atherosclerosis in the elderly. Methods A total of 721 elderly participants （mean ~ SD age, 70.3 -4- 5.6years） were enrolled in the current study. All participant underwent both baPWV measurement and B-mode ultrasound for the intima-media thickness. Carotid atherosclerosis （CAS） was defined as the present of carotid plaque or and/or intima media thickness for at least 1.1 mm. Results A multivariate logistic regression analysis reveals that age, sex, brachial-ankle pulse wave velocity, smoking and LDL-C level showed a significant correlation with the presence of CAS. The odds ratios of CAS associated with a 500cm/s increase of brachial-ankle pulse wave velocity were 2.378 [95% confidence interval, 1.36 to 4.00, P〈0.05], 3.733 [95% confidence interval, 1.729 to 8.058, P〈0.01], 4.438 [95% confidence interval, 1.659 to 11.803, P〈0.01]. The baPWV significantly correlated with IMT by bivariate correlation analysis （r=-0.39; p=0.001）. After adjusting for factors influencing, baPWV all the same correlated with IMT （r=-0.35; p=0.001）.Conclusion These results indicate that brachial-ankle PWV is an independent predictor of CAS in the elderly.It also means that the direct measurement of arterial stiffness by this simple method may be of great help for the evaluation of carotid artherosclerosis, at least in the elderly
