风电机组功率曲线建模是风电功率预测、状态监测、性能评估的关键环节。文章提出了一种基于lo-gistic函数和分位数回归的风电机组功率曲线建模算法。为解决风电功率的不确定性,文中在logistic函数中嵌入了分位回归损失函数,建立了分位...风电机组功率曲线建模是风电功率预测、状态监测、性能评估的关键环节。文章提出了一种基于lo-gistic函数和分位数回归的风电机组功率曲线建模算法。为解决风电功率的不确定性,文中在logistic函数中嵌入了分位回归损失函数,建立了分位数回归logistic模型(quantile regression logistic function,QRLF),并采用了三种优化算法进行优化;为降低原始数据中异常值的影响,提出了基于QRLF算法的自适应异常筛选方法;在三个风电场的SCADA(supervisory control and data acquisition)数据中进行了实例验证。文中采用五种评价指标对所提方法进行评估。结果表明,相比传统的风电机组功率曲线建模方法,文中所提方法可以同时提供较好的确定性功率曲线和概率性功率曲线结果。展开更多
In the era of green logistics,digital transformation has become an effective means for the logistics industry’s high-quality development.Using listed companies in China’s logistics industry from 2010 to 2021 as the ...In the era of green logistics,digital transformation has become an effective means for the logistics industry’s high-quality development.Using listed companies in China’s logistics industry from 2010 to 2021 as the research samples,this paper conducts an empirical test on the impact of the digital transformation of logistics enterprises on their green in-novation.Specifically,enterprise digital transformation indicators are constructed through the text analysis method,and the fixed-effects model is applied for analysis.The results indicate that the digital transformation of logistics enterprises has a significant promoting effect on their green innovation;the promoting effect of the digital transformation of logistics enterprises on green innovation is primarily achieved by easing corporate financing constraints and reducing corporate en-vironmental uncertainty;and the impact of digital transformation on green innovation is geographically heterogeneous.展开更多
目的:比较决策树和Logistic回归模型对体外受精-胚胎移植(in vitro fertilization and embryo transfer,IVF-ET)患者妊娠结局的预测价值。方法:纳入2021年1月至2022年10月在长治医学院附属和平医院接受IVF-ET的患者350例为研究对象,根...目的:比较决策树和Logistic回归模型对体外受精-胚胎移植(in vitro fertilization and embryo transfer,IVF-ET)患者妊娠结局的预测价值。方法:纳入2021年1月至2022年10月在长治医学院附属和平医院接受IVF-ET的患者350例为研究对象,根据妊娠结局分为妊娠成功组(215例)和妊娠失败组(135例)。收集患者临床资料,建立IVF-ET患者妊娠结局Logistic回归和决策树预测模型,并在是否基于Logistic回归结果条件下建立决策树分析模型(决策树1和决策树2),采用受试者工作特征(receiver operating characteristic,ROC)曲线对模型预测效果进行评价。结果:350例患者中,妊娠成功患者占61.43%,妊娠失败者占38.57%。妊娠失败组年龄≥35岁、不孕年限≥5年、周期次数≥1次、有心理精神障碍的患者比例及HCG日血清孕酮水平均高于妊娠成功组,获卵数≥10枚、受精率≥75%的患者比例及HCG日子宫内膜厚度、优质胚胎数小于妊娠成功组(P<0.05)。多因素Logistic回归分析结果显示,年龄、HCG日血清孕酮水平、优质胚胎数及心理精神障碍均是IVF-ET患者妊娠结局的影响因素(P<0.05)。决策树模型显示,年龄、HCG日血清孕酮水平、优质胚胎数为IVF-ET患者妊娠结局的影响因素。Logistic回归模型曲线下面积(area under curve,AUC)为0.832,预测敏感度、特异度和准确度分别为87.3%、71.4%、83.5%;决策树1的AUC为0.859,预测敏感度、特异度和准确度分别为85.1%、76.8%、85.6%;决策树2的AUC为0.820,预测敏感度、特异度和准确度分别为83.7%、73.2%、82.4%。决策树1的AUC大于决策树2(P<0.05),但与Logistic回归模型的AUC比较差异无统计学意义(P>0.05)。结论:Logistic回归模型和决策树模型对于IVF-ET患者妊娠结局均有一定的预测价值。展开更多
文摘风电机组功率曲线建模是风电功率预测、状态监测、性能评估的关键环节。文章提出了一种基于lo-gistic函数和分位数回归的风电机组功率曲线建模算法。为解决风电功率的不确定性,文中在logistic函数中嵌入了分位回归损失函数,建立了分位数回归logistic模型(quantile regression logistic function,QRLF),并采用了三种优化算法进行优化;为降低原始数据中异常值的影响,提出了基于QRLF算法的自适应异常筛选方法;在三个风电场的SCADA(supervisory control and data acquisition)数据中进行了实例验证。文中采用五种评价指标对所提方法进行评估。结果表明,相比传统的风电机组功率曲线建模方法,文中所提方法可以同时提供较好的确定性功率曲线和概率性功率曲线结果。
基金supported by the National Natural Science Foundation of China(72374061,72204243)the Ministry of Education’s Humanities and Social Science Research Youth Fund Project(20YJC630138,22YJC630056)+1 种基金Anhui Provincial Natural Science Foundation(2208085UD02)New Liberal Arts Fund Expansion Project of University of Science and Technology of China(FSSF-A-230317).
文摘In the era of green logistics,digital transformation has become an effective means for the logistics industry’s high-quality development.Using listed companies in China’s logistics industry from 2010 to 2021 as the research samples,this paper conducts an empirical test on the impact of the digital transformation of logistics enterprises on their green in-novation.Specifically,enterprise digital transformation indicators are constructed through the text analysis method,and the fixed-effects model is applied for analysis.The results indicate that the digital transformation of logistics enterprises has a significant promoting effect on their green innovation;the promoting effect of the digital transformation of logistics enterprises on green innovation is primarily achieved by easing corporate financing constraints and reducing corporate en-vironmental uncertainty;and the impact of digital transformation on green innovation is geographically heterogeneous.
文摘目的:比较决策树和Logistic回归模型对体外受精-胚胎移植(in vitro fertilization and embryo transfer,IVF-ET)患者妊娠结局的预测价值。方法:纳入2021年1月至2022年10月在长治医学院附属和平医院接受IVF-ET的患者350例为研究对象,根据妊娠结局分为妊娠成功组(215例)和妊娠失败组(135例)。收集患者临床资料,建立IVF-ET患者妊娠结局Logistic回归和决策树预测模型,并在是否基于Logistic回归结果条件下建立决策树分析模型(决策树1和决策树2),采用受试者工作特征(receiver operating characteristic,ROC)曲线对模型预测效果进行评价。结果:350例患者中,妊娠成功患者占61.43%,妊娠失败者占38.57%。妊娠失败组年龄≥35岁、不孕年限≥5年、周期次数≥1次、有心理精神障碍的患者比例及HCG日血清孕酮水平均高于妊娠成功组,获卵数≥10枚、受精率≥75%的患者比例及HCG日子宫内膜厚度、优质胚胎数小于妊娠成功组(P<0.05)。多因素Logistic回归分析结果显示,年龄、HCG日血清孕酮水平、优质胚胎数及心理精神障碍均是IVF-ET患者妊娠结局的影响因素(P<0.05)。决策树模型显示,年龄、HCG日血清孕酮水平、优质胚胎数为IVF-ET患者妊娠结局的影响因素。Logistic回归模型曲线下面积(area under curve,AUC)为0.832,预测敏感度、特异度和准确度分别为87.3%、71.4%、83.5%;决策树1的AUC为0.859,预测敏感度、特异度和准确度分别为85.1%、76.8%、85.6%;决策树2的AUC为0.820,预测敏感度、特异度和准确度分别为83.7%、73.2%、82.4%。决策树1的AUC大于决策树2(P<0.05),但与Logistic回归模型的AUC比较差异无统计学意义(P>0.05)。结论:Logistic回归模型和决策树模型对于IVF-ET患者妊娠结局均有一定的预测价值。
