[Objective] The research aimed to analyze change characteristics and forecast factors of the fog in Beibei District of Chongqing from 1953 to 2010. [Method] By observation data of the fog in Beibei District from 1953 ...[Objective] The research aimed to analyze change characteristics and forecast factors of the fog in Beibei District of Chongqing from 1953 to 2010. [Method] By observation data of the fog in Beibei District from 1953 to 2010, interdeoadal, interannual, seasonal and monthly varia- tion characteristics of the fog days and formation-dispersion time of the fog were conducted statistical analysis. Meteorological conditions and fore- cast factors of the fog were also analyzed. [Result] Distribution of the fog days in Beibei District had obvious interdecadal characteristics. Fog days was at its maximum in the 1980s while minimum in the 1960s. Fog duration presented slow increase trend. Interannual characteristic of the fog days overall presented increase trend, and it had 9-year periodic oscillation characteristic. Fog mainly concentrated in autumn and winter. Fog was mainly formed at night (20:00 -08:00) and dispersed in the daytime (08:00 -13:00). Meteorological conditions which affected heavy fog in Beibei District were water vapor and stratification, wind field, temperature, relative humidity and so on. [ Conclusion] The research provided theoretical basis for scientific predication and forecast of the fog in Beibei District.展开更多
Fuzzy sets theory cannot describe the neutrality degreeof data, which has largely limited the objectivity of fuzzy time seriesin uncertain data forecasting. With this regard, a multi-factor highorderintuitionistic fuz...Fuzzy sets theory cannot describe the neutrality degreeof data, which has largely limited the objectivity of fuzzy time seriesin uncertain data forecasting. With this regard, a multi-factor highorderintuitionistic fuzzy time series forecasting model is built. Inthe new model, a fuzzy clustering algorithm is used to get unequalintervals, and a more objective technique for ascertaining membershipand non-membership functions of the intuitionistic fuzzy setis proposed. On these bases, forecast rules based on multidimensionalintuitionistic fuzzy modus ponens inference are established.Finally, contrast experiments on the daily mean temperature ofBeijing are carried out, which show that the novel model has aclear advantage of improving the forecast accuracy.展开更多
目的:探讨老年髋部骨折手术延迟的影响因素,构建老年髋部骨折手术延迟风险预测模型。方法:选取2019年11月至2022年11月采用手术治疗的老年髋部骨折患者的病例资料进行研究,将纳入研究的患者按照2∶1的比例随机分为训练集(用于模型构建)...目的:探讨老年髋部骨折手术延迟的影响因素,构建老年髋部骨折手术延迟风险预测模型。方法:选取2019年11月至2022年11月采用手术治疗的老年髋部骨折患者的病例资料进行研究,将纳入研究的患者按照2∶1的比例随机分为训练集(用于模型构建)和验证集(用于模型验证)。从病历系统中提取纳入患者的信息,包括年龄、性别、体质量指数、骨折类型、美国麻醉医师协会(American Society of Anesthesiologists, ASA)分级、伤前日常活动能力(activities of daily living, ADL)、是否服用影响凝血功能的药物、入院至手术时间、手术方式,是否合并精神障碍、高血压、糖尿病、呼吸系统疾病、心功能不全、肝功能不全、肾功能不全、电解质紊乱、尿酮体异常、下肢静脉血栓、凝血功能异常,以及入院后血清肿瘤坏死因子-α、C反应蛋白水平等。将训练集中的患者根据入院至手术时间分为早期手术组(入院至手术时间<48 h)和延迟手术组(入院至手术时间≥48 h)。先对2组患者的相关信息进行单因素对比分析,再对单因素分析中组间差异有统计学意义的因素进行多因素Logistic回归分析及多重共线性诊断;采用R软件基于贝叶斯网络模型构建老年髋部骨折手术延迟风险预测模型,并采用Netica软件进行贝叶斯网络模型推理。采用受试者操作特征(receiver operating characteristic, ROC)曲线评价老年髋部骨折手术延迟风险预测模型的区分度,采用校准曲线评价老年髋部骨折手术延迟风险预测模型的校准度。结果:(1)分组结果。共纳入老年髋部骨折患者318例,训练集212例、验证集106例。根据入院至手术时间,训练集中早期手术组78例、延迟手术组134例。(2)老年髋部骨折手术延迟影响因素的单因素分析结果。2组患者ASA分级、是否服用影响凝血功能的药物及是否合并精神障碍、高血压、糖尿病、呼吸系统疾病、心功能不全、电解质紊乱、凝血功能异常的比较,组间差异均有统计学意义(χ~2=3.862,P=0.049;χ~2=26.806,P=0.000;χ~2=29.852,P=0.000;χ~2=21.743,P=0.000;χ~2=25.226,P=0.000;χ~2=5.415,P=0.020;χ~2=11.683,P=0.001;χ~2=14.686,P=0.000;χ~2=6.057,P=0.014)。(3)老年髋部骨折手术延迟影响因素的多因素分析及多重共线性诊断结果。多因素Logistic回归分析结果显示,服用影响凝血功能的药物及合并精神障碍、高血压、糖尿病、呼吸系统疾病、心功能不全、电解质紊乱、凝血功能异常均是老年髋部骨折手术延迟的影响因素[β=0.328,P=0.000,OR=5.112,95%CI(2.686,9.728);β=0.322,P=0.000,OR=5.425,95%CI(2.884,10.203);β=0.302,P=0.000,OR=3.956,95%CI(2.189,7.148);β=0.312,P=0.000,OR=4.560,95%CI(2.476,8.398);β=0.291,P=0.021,OR=1.962,95%CI(1.108,3.474);β=0.296,P=0.001,OR=2.713,95%CI(1.520,4.844);β=0.303,P=0.000,OR=3.133,95%CI(1.729,5.679);β=0.296,P=0.015,OR=2.061,95%CI(1.154,3.680)];多重共线性诊断结果显示,上述影响因素均不存在共线性(VIF=1.134,VIF=1.266,VIF=1.465,VIF=1.389,VIF=1.342,VIF=1.183,VIF=1.346,VIF=1.259)。(4)基于贝叶斯网络模型的老年髋部骨折手术延迟风险预测模型的构建与推理结果。基于贝叶斯网络模型构建的老年髋部骨折手术延迟风险预测模型包括8个节点、8条有向边。模型显示,服用影响凝血功能的药物及合并精神障碍、呼吸系统疾病、电解质紊乱、凝血功能异常直接影响手术延迟的发生,合并心功能不全、高血压、糖尿病间接影响手术延迟的发生;推理结果显示,患者合并心功能不全、凝血功能异常及精神障碍时,手术延迟发生率为64.1%。(5)老年髋部骨折手术延迟风险预测模型的评价结果。采用训练集数据进行老年髋部骨折手术延迟风险预测模型评价,ROC曲线下面积为0.861[P=0.000,95%CI(0.810,0.912)],灵敏度为91.29%,特异度为93.35%;校准曲线显示其一致性指数为0.866[P=0.000,95%CI(0.702,0.943)];采用验证集数据进行老年髋部骨折手术延迟风险预测模型评价,ROC曲线下面积为0.848[P=0.000,95%CI(0.795,0.901)],灵敏度为91.62%,特异度为92.46%;校准曲线显示其一致性指数为0.879[P=0.000,95%CI(0.723,0.981)]。结论:服用影响凝血功能的药物以及合并精神障碍、高血压、糖尿病、呼吸系统疾病、心功能不全、电解质紊乱、凝血功能异常均为老年髋部骨折手术延迟的影响因素,基于上述因素构建的老年髋部骨折手术延迟风险预测模型具有较高的应用价值。展开更多
文摘[Objective] The research aimed to analyze change characteristics and forecast factors of the fog in Beibei District of Chongqing from 1953 to 2010. [Method] By observation data of the fog in Beibei District from 1953 to 2010, interdeoadal, interannual, seasonal and monthly varia- tion characteristics of the fog days and formation-dispersion time of the fog were conducted statistical analysis. Meteorological conditions and fore- cast factors of the fog were also analyzed. [Result] Distribution of the fog days in Beibei District had obvious interdecadal characteristics. Fog days was at its maximum in the 1980s while minimum in the 1960s. Fog duration presented slow increase trend. Interannual characteristic of the fog days overall presented increase trend, and it had 9-year periodic oscillation characteristic. Fog mainly concentrated in autumn and winter. Fog was mainly formed at night (20:00 -08:00) and dispersed in the daytime (08:00 -13:00). Meteorological conditions which affected heavy fog in Beibei District were water vapor and stratification, wind field, temperature, relative humidity and so on. [ Conclusion] The research provided theoretical basis for scientific predication and forecast of the fog in Beibei District.
基金supported by the National Natural Science Foundation of China(61309022)
文摘Fuzzy sets theory cannot describe the neutrality degreeof data, which has largely limited the objectivity of fuzzy time seriesin uncertain data forecasting. With this regard, a multi-factor highorderintuitionistic fuzzy time series forecasting model is built. Inthe new model, a fuzzy clustering algorithm is used to get unequalintervals, and a more objective technique for ascertaining membershipand non-membership functions of the intuitionistic fuzzy setis proposed. On these bases, forecast rules based on multidimensionalintuitionistic fuzzy modus ponens inference are established.Finally, contrast experiments on the daily mean temperature ofBeijing are carried out, which show that the novel model has aclear advantage of improving the forecast accuracy.
文摘小时天然气负荷预测受外部特征因素与预测方法的影响,为提高其预测精度并解决其他深度学习类模型或组合模型可解释性差、训练时间过长的问题,在引入“小时影响度”这一新特征因素的同时提出一种基于极端梯度提升树(extreme gradient boosting tress,XGBoost)模型与可解释性神经网络模型NBEATSx组合预测的方法;以XGBoost模型作为特征筛选器对特征集数据进行筛选,再将筛选降维后的数据集输入到NBEATSx中训练,提高NBEATSx的训练速度与预测精度;将负荷数据与特征数据经STL(seasonal and trend decomposition using Loess)算法分解为趋势分量、季节分量与残差分量,再分别输入到XGBoost中进行预测,减弱原始数据中的噪音影响;将优化后的NBEATSx与XGBoost模型通过方差倒数法进行组合,得出STL-XGBoost-NBEATSx组合模型的预测结果。结果表明:“小时影响度”这一新特征是小时负荷预测的重要影响因素,STL-XGBoost-NBEATSx模型训练速度有所提高,具有良好的可解释性与更高的预测准确性,模型预测结果的平均绝对百分比误差、均方误差、平均绝对误差分别比其余单一模型平均降低54.20%、63.97%、49.72%,比其余组合模型平均降低24.85%、34.39%、23.41%,模型的决定系数为0.935,能够很好地拟合观测数据。
文摘目的:探讨老年髋部骨折手术延迟的影响因素,构建老年髋部骨折手术延迟风险预测模型。方法:选取2019年11月至2022年11月采用手术治疗的老年髋部骨折患者的病例资料进行研究,将纳入研究的患者按照2∶1的比例随机分为训练集(用于模型构建)和验证集(用于模型验证)。从病历系统中提取纳入患者的信息,包括年龄、性别、体质量指数、骨折类型、美国麻醉医师协会(American Society of Anesthesiologists, ASA)分级、伤前日常活动能力(activities of daily living, ADL)、是否服用影响凝血功能的药物、入院至手术时间、手术方式,是否合并精神障碍、高血压、糖尿病、呼吸系统疾病、心功能不全、肝功能不全、肾功能不全、电解质紊乱、尿酮体异常、下肢静脉血栓、凝血功能异常,以及入院后血清肿瘤坏死因子-α、C反应蛋白水平等。将训练集中的患者根据入院至手术时间分为早期手术组(入院至手术时间<48 h)和延迟手术组(入院至手术时间≥48 h)。先对2组患者的相关信息进行单因素对比分析,再对单因素分析中组间差异有统计学意义的因素进行多因素Logistic回归分析及多重共线性诊断;采用R软件基于贝叶斯网络模型构建老年髋部骨折手术延迟风险预测模型,并采用Netica软件进行贝叶斯网络模型推理。采用受试者操作特征(receiver operating characteristic, ROC)曲线评价老年髋部骨折手术延迟风险预测模型的区分度,采用校准曲线评价老年髋部骨折手术延迟风险预测模型的校准度。结果:(1)分组结果。共纳入老年髋部骨折患者318例,训练集212例、验证集106例。根据入院至手术时间,训练集中早期手术组78例、延迟手术组134例。(2)老年髋部骨折手术延迟影响因素的单因素分析结果。2组患者ASA分级、是否服用影响凝血功能的药物及是否合并精神障碍、高血压、糖尿病、呼吸系统疾病、心功能不全、电解质紊乱、凝血功能异常的比较,组间差异均有统计学意义(χ~2=3.862,P=0.049;χ~2=26.806,P=0.000;χ~2=29.852,P=0.000;χ~2=21.743,P=0.000;χ~2=25.226,P=0.000;χ~2=5.415,P=0.020;χ~2=11.683,P=0.001;χ~2=14.686,P=0.000;χ~2=6.057,P=0.014)。(3)老年髋部骨折手术延迟影响因素的多因素分析及多重共线性诊断结果。多因素Logistic回归分析结果显示,服用影响凝血功能的药物及合并精神障碍、高血压、糖尿病、呼吸系统疾病、心功能不全、电解质紊乱、凝血功能异常均是老年髋部骨折手术延迟的影响因素[β=0.328,P=0.000,OR=5.112,95%CI(2.686,9.728);β=0.322,P=0.000,OR=5.425,95%CI(2.884,10.203);β=0.302,P=0.000,OR=3.956,95%CI(2.189,7.148);β=0.312,P=0.000,OR=4.560,95%CI(2.476,8.398);β=0.291,P=0.021,OR=1.962,95%CI(1.108,3.474);β=0.296,P=0.001,OR=2.713,95%CI(1.520,4.844);β=0.303,P=0.000,OR=3.133,95%CI(1.729,5.679);β=0.296,P=0.015,OR=2.061,95%CI(1.154,3.680)];多重共线性诊断结果显示,上述影响因素均不存在共线性(VIF=1.134,VIF=1.266,VIF=1.465,VIF=1.389,VIF=1.342,VIF=1.183,VIF=1.346,VIF=1.259)。(4)基于贝叶斯网络模型的老年髋部骨折手术延迟风险预测模型的构建与推理结果。基于贝叶斯网络模型构建的老年髋部骨折手术延迟风险预测模型包括8个节点、8条有向边。模型显示,服用影响凝血功能的药物及合并精神障碍、呼吸系统疾病、电解质紊乱、凝血功能异常直接影响手术延迟的发生,合并心功能不全、高血压、糖尿病间接影响手术延迟的发生;推理结果显示,患者合并心功能不全、凝血功能异常及精神障碍时,手术延迟发生率为64.1%。(5)老年髋部骨折手术延迟风险预测模型的评价结果。采用训练集数据进行老年髋部骨折手术延迟风险预测模型评价,ROC曲线下面积为0.861[P=0.000,95%CI(0.810,0.912)],灵敏度为91.29%,特异度为93.35%;校准曲线显示其一致性指数为0.866[P=0.000,95%CI(0.702,0.943)];采用验证集数据进行老年髋部骨折手术延迟风险预测模型评价,ROC曲线下面积为0.848[P=0.000,95%CI(0.795,0.901)],灵敏度为91.62%,特异度为92.46%;校准曲线显示其一致性指数为0.879[P=0.000,95%CI(0.723,0.981)]。结论:服用影响凝血功能的药物以及合并精神障碍、高血压、糖尿病、呼吸系统疾病、心功能不全、电解质紊乱、凝血功能异常均为老年髋部骨折手术延迟的影响因素,基于上述因素构建的老年髋部骨折手术延迟风险预测模型具有较高的应用价值。