Even though the impact of Bacillus thuringiensis (Bt) cotton on pesticide use has been well documented, all previous stud- ies focus on the mean value of pesticide use. Using seven unique waves of panel data collect...Even though the impact of Bacillus thuringiensis (Bt) cotton on pesticide use has been well documented, all previous stud- ies focus on the mean value of pesticide use. Using seven unique waves of panel data collected between 1999 and 2012 in China, we show that Bt cotton adoption has not only caused a reduction of the mean value of pasticide use, but also a reduction of the standard deviation of pesticide use. We conclude that Bt technology adoption has also contributed to the stability of pesticide use in cotton production. We believe that this contribution is theoretically and practically relevant because of the long length of our unique dataset.展开更多
In case of machine learning,the problem of class imbalance is always troubling,i.e.one class of the samples has a larger magnitude than the other classes.This problem brings a preference of the classifier to the major...In case of machine learning,the problem of class imbalance is always troubling,i.e.one class of the samples has a larger magnitude than the other classes.This problem brings a preference of the classifier to the majority class,which leads to worse performance of the classifier on the minority class.We proposed an improved boosting tree(BT) algorithm for learning imbalanced data,called cost BT.In each iteration of the cost BT,only the weights of the misclassified minority class samples are increased.Meanwhile,the error rate in the weight formula of the base classifier is replaced by 1 minus F-measure.In this study,the performance of the cost BT algorithm is compared with other known methods on 9 public data sets.The compared methods include the decision tree and random forest algorithm,and both of them were combined with the sampling techniques such as synthetic minority oversampling technique(SMOTE),Borderline-SMOTE,adaptive synthetic sampling approach(ADASYN) and one sided selection.The cost BT algorithm performed better than the other compared methods in F-measure,G-mean and area under curve(AUC).In 6 of the 9 data sets,the cost BT algorithm has a superior performance to the other published methods.It can promote the prediction performance of the base classifiers by increasing the proportion of the minority class in the whole samples with only increasing the weights of the misclassified minority class samples in each iteration of the BT.In addition,computing the weights of the base classifiers with F-measure is helpful to the ensemble decisions.展开更多
基金financial supports of the National Natural Sciences Foundation of China (71773150,71273290 and 71333013)GM Variety Development Special Program (2016ZX08015-001)
文摘Even though the impact of Bacillus thuringiensis (Bt) cotton on pesticide use has been well documented, all previous stud- ies focus on the mean value of pesticide use. Using seven unique waves of panel data collected between 1999 and 2012 in China, we show that Bt cotton adoption has not only caused a reduction of the mean value of pasticide use, but also a reduction of the standard deviation of pesticide use. We conclude that Bt technology adoption has also contributed to the stability of pesticide use in cotton production. We believe that this contribution is theoretically and practically relevant because of the long length of our unique dataset.
基金supported by the National Key Research and Development Program of China(2018YFC0116902,2016YFC0901602)the National Natural Science Foundation of China(NSFC)(61876194)+2 种基金Joint Foundation for the NSFC and Guangdong Science Center for Big Data(U1611261)Medical Scientific Research Foundation of Guangdong Province of China(C2017037)Science and Technology Program of Guangzhou(201604020016)
文摘In case of machine learning,the problem of class imbalance is always troubling,i.e.one class of the samples has a larger magnitude than the other classes.This problem brings a preference of the classifier to the majority class,which leads to worse performance of the classifier on the minority class.We proposed an improved boosting tree(BT) algorithm for learning imbalanced data,called cost BT.In each iteration of the cost BT,only the weights of the misclassified minority class samples are increased.Meanwhile,the error rate in the weight formula of the base classifier is replaced by 1 minus F-measure.In this study,the performance of the cost BT algorithm is compared with other known methods on 9 public data sets.The compared methods include the decision tree and random forest algorithm,and both of them were combined with the sampling techniques such as synthetic minority oversampling technique(SMOTE),Borderline-SMOTE,adaptive synthetic sampling approach(ADASYN) and one sided selection.The cost BT algorithm performed better than the other compared methods in F-measure,G-mean and area under curve(AUC).In 6 of the 9 data sets,the cost BT algorithm has a superior performance to the other published methods.It can promote the prediction performance of the base classifiers by increasing the proportion of the minority class in the whole samples with only increasing the weights of the misclassified minority class samples in each iteration of the BT.In addition,computing the weights of the base classifiers with F-measure is helpful to the ensemble decisions.