A support vector machine time series forecasting model based on rough set data preprocessing was proposed by combining rough set attribute reduction and support vector machine regression algorithm. First, remove the r...A support vector machine time series forecasting model based on rough set data preprocessing was proposed by combining rough set attribute reduction and support vector machine regression algorithm. First, remove the redundant attribute for forecasting from condition attribute by rough set method; then use the minimum condition attribute set obtained after the reduction and the corresponding initial data, reform a new training sample set which only retain the important attributes influencing the forecasting accuracy; study and train the support vector machine with the training sample obtained after reduction, and then input the reformed testing sample set according to the minimum condition attribute and corresponding initial data. The model was tested and the mapping relation was got between the condition attribute and forecasting variable. Eventually, power supply and demand were forecasted in this model. The average absolute error rates of power consumption of the whole society and yearly maximum load are respectively 14.21% and 13.23%. It shows that RS-SVM time series forecasting model has high forecasting accuracy.展开更多
Function S-rough sets has the properties of dynamics, heredity, and memory. Function S-rough sets is penetrated and crossed with the issue of economic law forecast, then a new forecast model based on function S-rough ...Function S-rough sets has the properties of dynamics, heredity, and memory. Function S-rough sets is penetrated and crossed with the issue of economic law forecast, then a new forecast model based on function S-rough sets namely the two law forecast model is proposed, which includes upper law forecast model and lower law forecast model; and its＇ implement algorithm is given. Finally, the validity of the model is demonstrated by the forecast for region economic development of Hainan Province.展开更多
To enhance the accuracy of intuitionistic fuzzy time series forecasting model, this paper analyses the influence of universe of discourse partition and compares with relevant literature. Traditional models usually par...To enhance the accuracy of intuitionistic fuzzy time series forecasting model, this paper analyses the influence of universe of discourse partition and compares with relevant literature. Traditional models usually partition the global universe of discourse, which is not appropriate for all objectives. For example, the universe of the secular trend model is continuously variational. In addition, most forecasting methods rely on prior information, i.e., fuzzy relationship groups (FRG). Numerous relationship groups lead to the explosive growth of relationship library in a linear model and increase the computational complexity. To overcome problems above and ascertain an appropriate order, an intuitionistic fuzzy time series forecasting model based on order decision and adaptive partition algorithm is proposed. By forecasting the vector operator matrix, the proposed model can adjust partitions and intervals adaptively. The proposed model is tested on student enrollments of Alabama dataset, typical seasonal dataset Taiwan Stock Exchange Capitalization Weighted Stock Index (TAIEX) and a secular trend dataset of total retail sales for social consumer goods in China. Experimental results illustrate the validity and applicability of the proposed method for different patterns of dataset.展开更多
This study presents a model to forecast the Indian summer monsoon rainfall（ISMR）（June-September）based on monthly and seasonal time scales. The ISMR time series data sets are classified into two parts for modeling ...This study presents a model to forecast the Indian summer monsoon rainfall（ISMR）（June-September）based on monthly and seasonal time scales. The ISMR time series data sets are classified into two parts for modeling purposes, viz.,（1） training data set（1871-1960）, and（2） testing data set（1961-2014）.Statistical analyzes reflect the dynamic nature of the ISMR, which couldn＇t be predicted efficiently by statistical and mathematical based models. Therefore, this study suggests the usage of three techniques,viz., fuzzy set, entropy and artificial neural network（ANN）. Based on these techniques, a novel ISMR time series forecasting model is designed to deal with the dynamic nature of the ISMR. This model is verified and validated with training and testing data sets. Various statistical analyzes and comparison studies demonstrate the effectiveness of the proposed model.展开更多
精准的电力负荷预测有利于保障电力系统的安全、经济运行。针对现行预测算法存在的预测准确度低、模型耗时长等问题,提出一种基于随机森林(random forest,RF)算法和粗糙集理论(rough set theory,RST)的改进型深度学习(deeplearning, DL...精准的电力负荷预测有利于保障电力系统的安全、经济运行。针对现行预测算法存在的预测准确度低、模型耗时长等问题,提出一种基于随机森林(random forest,RF)算法和粗糙集理论(rough set theory,RST)的改进型深度学习(deeplearning, DL)短期负荷预测模型(RF-DL-RST)。该模型首先基于历史数据,利用随机森林算法提取影响负荷预测的关键特征量;然后将关键特征量和历史负荷值作为深度神经网络的输入、输出项进行训练,并通过粗糙集理论修正预测结果。最后,通过算例进行仿真验证,结果表明,该模型的预测准确度比单一的深度学习模型及不进行预测修正的模型更高。展开更多
基金Project(70373017) supported by the National Natural Science Foundation of China
文摘A support vector machine time series forecasting model based on rough set data preprocessing was proposed by combining rough set attribute reduction and support vector machine regression algorithm. First, remove the redundant attribute for forecasting from condition attribute by rough set method; then use the minimum condition attribute set obtained after the reduction and the corresponding initial data, reform a new training sample set which only retain the important attributes influencing the forecasting accuracy; study and train the support vector machine with the training sample obtained after reduction, and then input the reformed testing sample set according to the minimum condition attribute and corresponding initial data. The model was tested and the mapping relation was got between the condition attribute and forecasting variable. Eventually, power supply and demand were forecasted in this model. The average absolute error rates of power consumption of the whole society and yearly maximum load are respectively 14.21% and 13.23%. It shows that RS-SVM time series forecasting model has high forecasting accuracy.
基金supported by the National Natural Science Foundation of China (60364001, 70461004)the Hainan Provincial Natural Science Foundation of China (807054)Hainan Provincial Eduction Office Foundation (HJ2008-56).
文摘Function S-rough sets has the properties of dynamics, heredity, and memory. Function S-rough sets is penetrated and crossed with the issue of economic law forecast, then a new forecast model based on function S-rough sets namely the two law forecast model is proposed, which includes upper law forecast model and lower law forecast model; and its＇ implement algorithm is given. Finally, the validity of the model is demonstrated by the forecast for region economic development of Hainan Province.
基金supported by the National Natural Science Foundation of China(61309022)
文摘To enhance the accuracy of intuitionistic fuzzy time series forecasting model, this paper analyses the influence of universe of discourse partition and compares with relevant literature. Traditional models usually partition the global universe of discourse, which is not appropriate for all objectives. For example, the universe of the secular trend model is continuously variational. In addition, most forecasting methods rely on prior information, i.e., fuzzy relationship groups (FRG). Numerous relationship groups lead to the explosive growth of relationship library in a linear model and increase the computational complexity. To overcome problems above and ascertain an appropriate order, an intuitionistic fuzzy time series forecasting model based on order decision and adaptive partition algorithm is proposed. By forecasting the vector operator matrix, the proposed model can adjust partitions and intervals adaptively. The proposed model is tested on student enrollments of Alabama dataset, typical seasonal dataset Taiwan Stock Exchange Capitalization Weighted Stock Index (TAIEX) and a secular trend dataset of total retail sales for social consumer goods in China. Experimental results illustrate the validity and applicability of the proposed method for different patterns of dataset.
基金supported by the Department of Science and Technology (DST)-SERB, Government of India, under Grant EEQ/ 2016/000021
文摘This study presents a model to forecast the Indian summer monsoon rainfall（ISMR）（June-September）based on monthly and seasonal time scales. The ISMR time series data sets are classified into two parts for modeling purposes, viz.,（1） training data set（1871-1960）, and（2） testing data set（1961-2014）.Statistical analyzes reflect the dynamic nature of the ISMR, which couldn＇t be predicted efficiently by statistical and mathematical based models. Therefore, this study suggests the usage of three techniques,viz., fuzzy set, entropy and artificial neural network（ANN）. Based on these techniques, a novel ISMR time series forecasting model is designed to deal with the dynamic nature of the ISMR. This model is verified and validated with training and testing data sets. Various statistical analyzes and comparison studies demonstrate the effectiveness of the proposed model.
文摘精准的电力负荷预测有利于保障电力系统的安全、经济运行。针对现行预测算法存在的预测准确度低、模型耗时长等问题,提出一种基于随机森林(random forest,RF)算法和粗糙集理论(rough set theory,RST)的改进型深度学习(deeplearning, DL)短期负荷预测模型(RF-DL-RST)。该模型首先基于历史数据,利用随机森林算法提取影响负荷预测的关键特征量;然后将关键特征量和历史负荷值作为深度神经网络的输入、输出项进行训练,并通过粗糙集理论修正预测结果。最后,通过算例进行仿真验证,结果表明,该模型的预测准确度比单一的深度学习模型及不进行预测修正的模型更高。
