Since the previous research works are not synthetic and accurate enough for building a precise hypertension risk evaluation system,by ranking the significances for hypertension factors according to the information gai...Since the previous research works are not synthetic and accurate enough for building a precise hypertension risk evaluation system,by ranking the significances for hypertension factors according to the information gains on 2 231 normotensive and 823 hypertensive samples,totally 42 different neural network models are built and tested.The prediction accuracy of a model whose inputs are 26 factors is found to be much higher than the 81.61% obtained by previous research work. The prediction matching rates of the model for ＂hypertension or not＂,＂systolic blood pressure＂,and ＂diastolic blood pressure＂ are 95.79%,98.22% and 98.41%,respectively.Based on the found model and the object oriented techniques,an online hypertension risk evaluation system is developed,being able to gather new samples,learn the new samples,and improve its prediction accuracy automatically.展开更多
In order to eliminate the settlement underestimation in surcharge preload engineering, a study based on Bjerrum's creep diagram and the tangent slope definition of secondary consolidation coefficient was carried o...In order to eliminate the settlement underestimation in surcharge preload engineering, a study based on Bjerrum's creep diagram and the tangent slope definition of secondary consolidation coefficient was carried out to analyze the time effect of secondary consolidation coefficient of over consolidated soil, and a time–growth model for it was formulated. As Bjerrum's creep diagram is an idealized model, oedometer tests were performed to improve the above time–growth model of secondary consolidation coefficient for the purpose of achieving a better agreement with the actual ground situations. It is found that secondary consolidation coefficient of over consolidated soil not only decreases with the ratio of historical maximum to current effective stress of soil(OCR), but also increases with the development time of secondary consolidation. No matter how large OCR is, the long-term time effect of secondary consolidation coefficient of over consolidated soil is all significant. Based on the above results, a model for settlement estimation was formulated and a case study to estimate it indicates that the settlement estimated by our method is 2–5 times larger than that estimated by the previous method. Moreover, the larger the OCR is as well as the longer the service life is, the larger the difference between our method and the previous method is. Thus, the post-construction secondary settlement in surcharge preload engineering will be underestimated when neglecting the time effect of secondary consolidation coefficient in over consolidated state.展开更多
基金The National High Technology Research and Development Program of China(863Program)(No.2006AA02Z347)
文摘Since the previous research works are not synthetic and accurate enough for building a precise hypertension risk evaluation system,by ranking the significances for hypertension factors according to the information gains on 2 231 normotensive and 823 hypertensive samples,totally 42 different neural network models are built and tested.The prediction accuracy of a model whose inputs are 26 factors is found to be much higher than the 81.61% obtained by previous research work. The prediction matching rates of the model for ＂hypertension or not＂,＂systolic blood pressure＂,and ＂diastolic blood pressure＂ are 95.79%,98.22% and 98.41%,respectively.Based on the found model and the object oriented techniques,an online hypertension risk evaluation system is developed,being able to gather new samples,learn the new samples,and improve its prediction accuracy automatically.
基金Project(51178419)supported by the National Natural Science Foundation of China
文摘In order to eliminate the settlement underestimation in surcharge preload engineering, a study based on Bjerrum's creep diagram and the tangent slope definition of secondary consolidation coefficient was carried out to analyze the time effect of secondary consolidation coefficient of over consolidated soil, and a time–growth model for it was formulated. As Bjerrum's creep diagram is an idealized model, oedometer tests were performed to improve the above time–growth model of secondary consolidation coefficient for the purpose of achieving a better agreement with the actual ground situations. It is found that secondary consolidation coefficient of over consolidated soil not only decreases with the ratio of historical maximum to current effective stress of soil(OCR), but also increases with the development time of secondary consolidation. No matter how large OCR is, the long-term time effect of secondary consolidation coefficient of over consolidated soil is all significant. Based on the above results, a model for settlement estimation was formulated and a case study to estimate it indicates that the settlement estimated by our method is 2–5 times larger than that estimated by the previous method. Moreover, the larger the OCR is as well as the longer the service life is, the larger the difference between our method and the previous method is. Thus, the post-construction secondary settlement in surcharge preload engineering will be underestimated when neglecting the time effect of secondary consolidation coefficient in over consolidated state.
