Smaller class sizes in early grades translated into students scoring higher on math tests in later grades in Tennessee’s experiment to see if smaller classes improved education, a study said on Friday. 低年级的小型...Smaller class sizes in early grades translated into students scoring higher on math tests in later grades in Tennessee’s experiment to see if smaller classes improved education, a study said on Friday. 低年级的小型班级能够使学生在高年级时获得数学测试的高分。田纳西州的一项旨在了解小型班级是否能够改进教育的实验得出如此结论。一项研究周五如是说。展开更多
Traditional classification algorithms perform not very well on imbalanced data sets and small sample size. To deal with the problem, a novel method is proposed to change the class distribution through adding virtual s...Traditional classification algorithms perform not very well on imbalanced data sets and small sample size. To deal with the problem, a novel method is proposed to change the class distribution through adding virtual samples, which are generated by the windowed regression over-sampling (WRO) method. The proposed method WRO not only reflects the additive effects but also reflects the multiplicative effect between samples. A comparative study between the proposed method and other over-sampling methods such as synthetic minority over-sampling technique (SMOTE) and borderline over-sampling (BOS) on UCI datasets and Fourier transform infrared spectroscopy (FTIR) data set is provided. Experimental results show that the WRO method can achieve better performance than other methods.展开更多
文摘Smaller class sizes in early grades translated into students scoring higher on math tests in later grades in Tennessee’s experiment to see if smaller classes improved education, a study said on Friday. 低年级的小型班级能够使学生在高年级时获得数学测试的高分。田纳西州的一项旨在了解小型班级是否能够改进教育的实验得出如此结论。一项研究周五如是说。
文摘Traditional classification algorithms perform not very well on imbalanced data sets and small sample size. To deal with the problem, a novel method is proposed to change the class distribution through adding virtual samples, which are generated by the windowed regression over-sampling (WRO) method. The proposed method WRO not only reflects the additive effects but also reflects the multiplicative effect between samples. A comparative study between the proposed method and other over-sampling methods such as synthetic minority over-sampling technique (SMOTE) and borderline over-sampling (BOS) on UCI datasets and Fourier transform infrared spectroscopy (FTIR) data set is provided. Experimental results show that the WRO method can achieve better performance than other methods.
