由于气温突变点的影响,负荷序列存在门限效应,导致传统线性时间序列模型的负荷预测效果较差。将气温突变点作为门限,建立了以气温为协变量的门限自回归移动平均(threshold autoregressive moving average with exogenous variable,TARM...由于气温突变点的影响,负荷序列存在门限效应,导致传统线性时间序列模型的负荷预测效果较差。将气温突变点作为门限,建立了以气温为协变量的门限自回归移动平均(threshold autoregressive moving average with exogenous variable,TARMAX)模型,提高了预测精度。首先,应用马尔科夫链蒙特卡洛(Markov chain Monte Carlo,MCMC)方法对气温突变点进行搜寻得到模型参数。然后,采用随机搜索变量的方法快速选择出最优模型,有效降低选择时间序列模型的计算量。最后,对不同季节下的居民日用电负荷进行预测。实例表明,与线性时间序列模型、长短期记忆网络(long short-term memory network,LSTM)和多层感知机(multilayer perceptron,MLP)相比,TARMAX模型提高了电力负荷的预测精度。展开更多
Objective: To identify the baseline factors independently related to 3- year myopia progression and axial elongation in COMET. Methods: A total of 469 children were enrolled, randomly assigned to progressive addition ...Objective: To identify the baseline factors independently related to 3- year myopia progression and axial elongation in COMET. Methods: A total of 469 children were enrolled, randomly assigned to progressive addition lenses with a + 2.00 diopter (D) addition or to single vision lenses and observed for 3 years. Eligible children were 6 to 11 years old, with spherical equivalent myopia of-1.25 to-4.50 D, bilaterally. The primary and secondary outcomes, myopia progression by cycloplegic autorefraction and axial elongation by A-scan ultrasonography, were measured annually. Multiple linear regression was used to adjust for covariates, including treatment. Results: Younger baseline age (6- 7 vs 11 years, 8 vs 11 years, and 9 vs 11 years, P<.001; 10 vs 11 years, P=.04), female sex (P=.01), and each ethnic group compared with African Americans (Asian, P=.02; Hispanic, P=.002; mixed, P=.002; white, P=.001) were independently associated with faster 3- year progression. Children aged 6 to 7 years had the fastest progression of all age groups, progressing by a mean (± SD) of 1.31 D± 0.13 more than children aged 11 years. Females progressed 0.16 D more than the males. Children of mixed, Hispanic, Asian, and white ethnicity progressed more than African American children by 0.49 D± 0.16, 0.33 D± 0.11, 0.32 D± 0.13, 0.27 D ± 0.08, respectively. Age and ethnicity, but not sex, were independently associated with axial elongation. Among these myopic children, a 0.5 mm increase in axial length was associated with 1 D of myopia progression. Conclusions: Younger baseline age was the strongest factor independently associated with faster myopic progression and greater axial elongation at 3 years. African American children had less myopic progression and axial elongation than the other ethnic groups.展开更多
文摘由于气温突变点的影响,负荷序列存在门限效应,导致传统线性时间序列模型的负荷预测效果较差。将气温突变点作为门限,建立了以气温为协变量的门限自回归移动平均(threshold autoregressive moving average with exogenous variable,TARMAX)模型,提高了预测精度。首先,应用马尔科夫链蒙特卡洛(Markov chain Monte Carlo,MCMC)方法对气温突变点进行搜寻得到模型参数。然后,采用随机搜索变量的方法快速选择出最优模型,有效降低选择时间序列模型的计算量。最后,对不同季节下的居民日用电负荷进行预测。实例表明,与线性时间序列模型、长短期记忆网络(long short-term memory network,LSTM)和多层感知机(multilayer perceptron,MLP)相比,TARMAX模型提高了电力负荷的预测精度。
文摘Objective: To identify the baseline factors independently related to 3- year myopia progression and axial elongation in COMET. Methods: A total of 469 children were enrolled, randomly assigned to progressive addition lenses with a + 2.00 diopter (D) addition or to single vision lenses and observed for 3 years. Eligible children were 6 to 11 years old, with spherical equivalent myopia of-1.25 to-4.50 D, bilaterally. The primary and secondary outcomes, myopia progression by cycloplegic autorefraction and axial elongation by A-scan ultrasonography, were measured annually. Multiple linear regression was used to adjust for covariates, including treatment. Results: Younger baseline age (6- 7 vs 11 years, 8 vs 11 years, and 9 vs 11 years, P<.001; 10 vs 11 years, P=.04), female sex (P=.01), and each ethnic group compared with African Americans (Asian, P=.02; Hispanic, P=.002; mixed, P=.002; white, P=.001) were independently associated with faster 3- year progression. Children aged 6 to 7 years had the fastest progression of all age groups, progressing by a mean (± SD) of 1.31 D± 0.13 more than children aged 11 years. Females progressed 0.16 D more than the males. Children of mixed, Hispanic, Asian, and white ethnicity progressed more than African American children by 0.49 D± 0.16, 0.33 D± 0.11, 0.32 D± 0.13, 0.27 D ± 0.08, respectively. Age and ethnicity, but not sex, were independently associated with axial elongation. Among these myopic children, a 0.5 mm increase in axial length was associated with 1 D of myopia progression. Conclusions: Younger baseline age was the strongest factor independently associated with faster myopic progression and greater axial elongation at 3 years. African American children had less myopic progression and axial elongation than the other ethnic groups.
