The bioavailability of 22 heavy metals was investigated at 19 sampling sites in Tieguanyin tea garden in Anxi County,Fujian Province,southeastern China.Heavy metal concentrations were determined by inductively coupled...The bioavailability of 22 heavy metals was investigated at 19 sampling sites in Tieguanyin tea garden in Anxi County,Fujian Province,southeastern China.Heavy metal concentrations were determined by inductively coupled plasma-mass spectrometry(ICP-MS)and evaluated by geo-accumulation index(I_(geo)).Dilute nitric acid extraction was used to evaluate biological activity.Cu,Pb,and Cd were highly bioavailable and most easily absorbed by tea trees.Heavy metal bioavailability in the surface soil was as the ratio of the effective state to the total amount.Cd had the highest I_(geo)values,and the respective samples and sites were classified as moderately/strongly contaminated.Cd element is considered the main factor of heavy metal pollution in the tea garden in Anxi.The other heavy metals studied were present in lower concentrations;thus,the samples were classified as uncontaminated or slightly contaminated.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
基金supported by the National Science Foundation of China(21177043,21377042)the National Science Foundation of Fujian Province(2015J01147)+1 种基金Fujian Provincial Key Laboratory of Ecology-Toxicological Effects and Control for Emerging Contaminants(PY16006)the Research Program of Science and Technology of Quanzhou City Government(2012Z86,2014Z130)
文摘The bioavailability of 22 heavy metals was investigated at 19 sampling sites in Tieguanyin tea garden in Anxi County,Fujian Province,southeastern China.Heavy metal concentrations were determined by inductively coupled plasma-mass spectrometry(ICP-MS)and evaluated by geo-accumulation index(I_(geo)).Dilute nitric acid extraction was used to evaluate biological activity.Cu,Pb,and Cd were highly bioavailable and most easily absorbed by tea trees.Heavy metal bioavailability in the surface soil was as the ratio of the effective state to the total amount.Cd had the highest I_(geo)values,and the respective samples and sites were classified as moderately/strongly contaminated.Cd element is considered the main factor of heavy metal pollution in the tea garden in Anxi.The other heavy metals studied were present in lower concentrations;thus,the samples were classified as uncontaminated or slightly contaminated.
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.
