[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
需求的波动性与对预测精度的高要求使得销售预测成为学界与业界研究的重难点问题,销售预测的准确性极大影响着企业的生产及最终收益。本文针对饮品零售行业的销售预测问题进行了详细的研究,构建了引入天气因素的改进HyperGBM机器学习预...需求的波动性与对预测精度的高要求使得销售预测成为学界与业界研究的重难点问题,销售预测的准确性极大影响着企业的生产及最终收益。本文针对饮品零售行业的销售预测问题进行了详细的研究,构建了引入天气因素的改进HyperGBM机器学习预测模型,全面比较了传统预测方法(如ARIMA、SARIMA和Prophet)与HyperGBM在预测准确性上的差异,并分析了加入天气因素对HyperGBM预测效果的影响。由于南北方气候差异较大,本文的研究选择西安代表北方的天气特征,选择昆明代表南方季节性特征显著的天气,并根据历史销售数据对SKU进行分类,分析适用于不同类别SKU的销售预测方法。基于企业提供的72个饮品的SKU历史数据的研究表明,HyperGBM在63个(共71个)SKU上相较于传统预测方法的预测效果更好,RMSE指标平均提升22.9%。对于天气因素的进一步研究表明,将天气数据融合到HyperGBM后,预测的准确度较无天气因素的模型最高提升了31.6%。本文根据季节趋势分解法(seasonal-trend decomposition using loess,STL)和增广迪基-富勒测试(augmented dickey-fuller,ADF)两项检测结果,将SKU按周期性和稳定性的强弱均匀划分为四个类别:周期性强且稳定、周期性弱且稳定、周期性强但不稳定、周期性弱但不稳定。研究发现,不同类别的SKU适用于不同的预测方法,周期性强的SKU类别适合采用SARIMA预测方法,稳定性强的SKU类别适合采用HyperGBM机器学习算法。本文的结论可以为饮品零售行业的销售预测提供帮助,指导企业按照商品类别选择适用的销售预测方法。展开更多
The pelagic species is closely related to the marine environmental factors, and establishment of forecasting model of fishing ground with high accuracy is an important content for pelagic fishery. The chub mackerel（S...The pelagic species is closely related to the marine environmental factors, and establishment of forecasting model of fishing ground with high accuracy is an important content for pelagic fishery. The chub mackerel（Scomber japonicus） in the Yellow Sea and East China Sea is an important fishing target for Chinese lighting purse seine fishery. Based on the fishery data from China＇s mainland large-type lighting purse seine fishery for chub mackerel during the period of 2003 to 2010 and the environmental data including sea surface temperature（SST）, gradient of the sea surface temperature（GSST）, sea surface height（SSH） and geostrophic velocity（GV）, we attempt to establish one new forecasting model of fishing ground based on boosted regression trees. In this study, the fishing areas with fishing effort is considered as one fishing ground, and the areas with no fishing ground are randomly selected from a background field, in which the fishing areas have no records in the logbooks. The performance of the forecasting model of fishing ground is evaluated with the testing data from the actual fishing data in 2011. The results show that the forecasting model of fishing ground has a high prediction performance, and the area under receiver operating curve（AUC） attains 0.897. The predicted fishing grounds are coincided with the actual fishing locations in 2011, and the movement route is also the same as the shift of fishing vessels, which indicates that this forecasting model based on the boosted regression trees can be used to effectively forecast the fishing ground of chub mackerel in the Yellow Sea and East China Sea.展开更多
Fashion color forecasting is one of the most important factors for fashion marketing and manufacturing. Several models have been applied by previous researchers to conduct fashion color forecasting. However, few convi...Fashion color forecasting is one of the most important factors for fashion marketing and manufacturing. Several models have been applied by previous researchers to conduct fashion color forecasting. However, few convincing forecasting systems have been established. A prediction model for fashion color forecasting was established by applying an improved back propagation neural network (BPNN) model in this paper. Successive six-year fashion color palettes, released by INTERCOLOR, were used as learning information for the neural network to develop a reliable prediction model. Colors in the palettes were quantified by PANTONE color system. Additionally, performance of the established model was compared with other GM(1, 1) models. Results show that the improved BPNN model is suitable to predict future fashion color trend.展开更多
This paper analyses the features and dynamic changes of the spatial layout of air transportation utilization among different provinces in China. It makes use of data for the airport throughput and socio-economic devel...This paper analyses the features and dynamic changes of the spatial layout of air transportation utilization among different provinces in China. It makes use of data for the airport throughput and socio-economic development of every province throughout the country in the years 2006 and 2015, and employs airport passenger and cargo throughput per capita and per unit of GDP as measures of regional air transportation utilization, which is significant for refining indicators of regional air transportation scale and comparing against them. It also analyzes the spatial differences of coupling between the regional air transportation utilization indicators and the key influencing factors on regional air transportation demand and utilization, which include per capita GDP, urbanization rate, and population density. Based on these key influencing factors, it establishes a multiple linear regression model to conduct forecasting of each province＇s future airport passenger and cargo throughput as well as throughput growth rates. The findings of the study are as follows：（1） Between 2006 and 2015, every province throughout the country showed a trend of year on year growth in their airport passenger and cargo throughput per capita. Throughput per capita grew fastest in Hebei, with a rise of 780%, and slowest in Beijing, with a rise of 38%. Throughput per capita was relatively high in western and southeastern coastal regions, and relatively low in northern and central regions. Airport passenger and cargo throughput per unit of GDP showed growth in provinces with relatively slow economic development, and showed negative growth in provinces with relatively rapid economic development. Throughput per unit of GDP grew fastest in Hebei, rising 265% between 2006 and 2015, and Hunan had the fastest negative growth, with a fall of 44% in the same period. Southwestern regions had relatively high throughput per unit of GDP, while in central, northern, and northeastern regions it was relatively low.（2） Strong correlation exists between airport passenger and cargo throughput per capita and per capita GDP, urbanization rate, and population density. Throughput per capita has positive correlation with per capita GDP and urbanization rate in all regions, and positive correlation with population density in most regions. Meanwhile, there is weak correlation between airport passenger and cargo throughput per unit of GDP and per capita GDP, urbanization rate, and population density, with positive correlation in some regions and negative correlation in others.（3） Between 2015 and 2025, it is estimated that all provinces experience a trend of rapid growth in their airport passenger and cargo throughput. Inner Mongolia and Hebei will see the fastest growth, rising221% and 155%, respectively, while Yunnan, Sichuan, and Hubei will see the slowest growth, with increases of 62%, 63%, and 65%, respectively.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.
文摘需求的波动性与对预测精度的高要求使得销售预测成为学界与业界研究的重难点问题,销售预测的准确性极大影响着企业的生产及最终收益。本文针对饮品零售行业的销售预测问题进行了详细的研究,构建了引入天气因素的改进HyperGBM机器学习预测模型,全面比较了传统预测方法(如ARIMA、SARIMA和Prophet)与HyperGBM在预测准确性上的差异,并分析了加入天气因素对HyperGBM预测效果的影响。由于南北方气候差异较大,本文的研究选择西安代表北方的天气特征,选择昆明代表南方季节性特征显著的天气,并根据历史销售数据对SKU进行分类,分析适用于不同类别SKU的销售预测方法。基于企业提供的72个饮品的SKU历史数据的研究表明,HyperGBM在63个(共71个)SKU上相较于传统预测方法的预测效果更好,RMSE指标平均提升22.9%。对于天气因素的进一步研究表明,将天气数据融合到HyperGBM后,预测的准确度较无天气因素的模型最高提升了31.6%。本文根据季节趋势分解法(seasonal-trend decomposition using loess,STL)和增广迪基-富勒测试(augmented dickey-fuller,ADF)两项检测结果,将SKU按周期性和稳定性的强弱均匀划分为四个类别:周期性强且稳定、周期性弱且稳定、周期性强但不稳定、周期性弱但不稳定。研究发现,不同类别的SKU适用于不同的预测方法,周期性强的SKU类别适合采用SARIMA预测方法,稳定性强的SKU类别适合采用HyperGBM机器学习算法。本文的结论可以为饮品零售行业的销售预测提供帮助,指导企业按照商品类别选择适用的销售预测方法。
基金The National High Technology Research and Development Program(863 Program)of China under contract No.2012AA092301the Public Science and Technology Research Funds Projects of Ocean under contract No.20155014+1 种基金the National Key Technology Research and Development Program of China under contract No.2013BAD13B01the Innovation Program of Shanghai Municipal Education Commissionof China under contract No.14ZZ147
文摘The pelagic species is closely related to the marine environmental factors, and establishment of forecasting model of fishing ground with high accuracy is an important content for pelagic fishery. The chub mackerel（Scomber japonicus） in the Yellow Sea and East China Sea is an important fishing target for Chinese lighting purse seine fishery. Based on the fishery data from China＇s mainland large-type lighting purse seine fishery for chub mackerel during the period of 2003 to 2010 and the environmental data including sea surface temperature（SST）, gradient of the sea surface temperature（GSST）, sea surface height（SSH） and geostrophic velocity（GV）, we attempt to establish one new forecasting model of fishing ground based on boosted regression trees. In this study, the fishing areas with fishing effort is considered as one fishing ground, and the areas with no fishing ground are randomly selected from a background field, in which the fishing areas have no records in the logbooks. The performance of the forecasting model of fishing ground is evaluated with the testing data from the actual fishing data in 2011. The results show that the forecasting model of fishing ground has a high prediction performance, and the area under receiver operating curve（AUC） attains 0.897. The predicted fishing grounds are coincided with the actual fishing locations in 2011, and the movement route is also the same as the shift of fishing vessels, which indicates that this forecasting model based on the boosted regression trees can be used to effectively forecast the fishing ground of chub mackerel in the Yellow Sea and East China Sea.
文摘Fashion color forecasting is one of the most important factors for fashion marketing and manufacturing. Several models have been applied by previous researchers to conduct fashion color forecasting. However, few convincing forecasting systems have been established. A prediction model for fashion color forecasting was established by applying an improved back propagation neural network (BPNN) model in this paper. Successive six-year fashion color palettes, released by INTERCOLOR, were used as learning information for the neural network to develop a reliable prediction model. Colors in the palettes were quantified by PANTONE color system. Additionally, performance of the established model was compared with other GM(1, 1) models. Results show that the improved BPNN model is suitable to predict future fashion color trend.
基金National Natural Science Foundation of China,No.41171433Philosophy and Social Science Foundation of China,No.16BJY039
文摘This paper analyses the features and dynamic changes of the spatial layout of air transportation utilization among different provinces in China. It makes use of data for the airport throughput and socio-economic development of every province throughout the country in the years 2006 and 2015, and employs airport passenger and cargo throughput per capita and per unit of GDP as measures of regional air transportation utilization, which is significant for refining indicators of regional air transportation scale and comparing against them. It also analyzes the spatial differences of coupling between the regional air transportation utilization indicators and the key influencing factors on regional air transportation demand and utilization, which include per capita GDP, urbanization rate, and population density. Based on these key influencing factors, it establishes a multiple linear regression model to conduct forecasting of each province＇s future airport passenger and cargo throughput as well as throughput growth rates. The findings of the study are as follows：（1） Between 2006 and 2015, every province throughout the country showed a trend of year on year growth in their airport passenger and cargo throughput per capita. Throughput per capita grew fastest in Hebei, with a rise of 780%, and slowest in Beijing, with a rise of 38%. Throughput per capita was relatively high in western and southeastern coastal regions, and relatively low in northern and central regions. Airport passenger and cargo throughput per unit of GDP showed growth in provinces with relatively slow economic development, and showed negative growth in provinces with relatively rapid economic development. Throughput per unit of GDP grew fastest in Hebei, rising 265% between 2006 and 2015, and Hunan had the fastest negative growth, with a fall of 44% in the same period. Southwestern regions had relatively high throughput per unit of GDP, while in central, northern, and northeastern regions it was relatively low.（2） Strong correlation exists between airport passenger and cargo throughput per capita and per capita GDP, urbanization rate, and population density. Throughput per capita has positive correlation with per capita GDP and urbanization rate in all regions, and positive correlation with population density in most regions. Meanwhile, there is weak correlation between airport passenger and cargo throughput per unit of GDP and per capita GDP, urbanization rate, and population density, with positive correlation in some regions and negative correlation in others.（3） Between 2015 and 2025, it is estimated that all provinces experience a trend of rapid growth in their airport passenger and cargo throughput. Inner Mongolia and Hebei will see the fastest growth, rising221% and 155%, respectively, while Yunnan, Sichuan, and Hubei will see the slowest growth, with increases of 62%, 63%, and 65%, respectively.
