To facilitate the development of the basis for the selection of plants for re-vegetating tailings in Zambia, an as sessment of the performance of tree species growing on tailings dams was conducted. The performance of...To facilitate the development of the basis for the selection of plants for re-vegetating tailings in Zambia, an as sessment of the performance of tree species growing on tailings dams was conducted. The performance of species was determined in terms of relative density, frequency and importance value for each species. The study reveals variations in performance of species; for example in terms of importance values, Acacia polyacantha （33.5%）, Toona ciliata （21.4%）, Acacia sieberana （9.9%）, Bauhinia thonningii （9.1%） and Peltophorum africanum （8.3%） were the most dominant species. The dominance of these species on tailings dams demonstrates tolerance to railings dams conditions. The study recommends that emphasis must be placed on these species in re-vegetating tailings dams.展开更多
Instance-specific algorithm selection technologies have been successfully used in many research fields,such as constraint satisfaction and planning. Researchers have been increasingly trying to model the potential rel...Instance-specific algorithm selection technologies have been successfully used in many research fields,such as constraint satisfaction and planning. Researchers have been increasingly trying to model the potential relations between different candidate algorithms for the algorithm selection. In this study, we propose an instancespecific algorithm selection method based on multi-output learning, which can manage these relations more directly.Three kinds of multi-output learning methods are used to predict the performances of the candidate algorithms：（1）multi-output regressor stacking;（2） multi-output extremely randomized trees; and（3） hybrid single-output and multioutput trees. The experimental results obtained using 11 SAT datasets and 5 Max SAT datasets indicate that our proposed methods can obtain a better performance over the state-of-the-art algorithm selection methods.展开更多
文摘To facilitate the development of the basis for the selection of plants for re-vegetating tailings in Zambia, an as sessment of the performance of tree species growing on tailings dams was conducted. The performance of species was determined in terms of relative density, frequency and importance value for each species. The study reveals variations in performance of species; for example in terms of importance values, Acacia polyacantha （33.5%）, Toona ciliata （21.4%）, Acacia sieberana （9.9%）, Bauhinia thonningii （9.1%） and Peltophorum africanum （8.3%） were the most dominant species. The dominance of these species on tailings dams demonstrates tolerance to railings dams conditions. The study recommends that emphasis must be placed on these species in re-vegetating tailings dams.
基金mainly supported by the National Natural Science Foundation of China(Nos.61125201,61303070,and U1435219)
文摘Instance-specific algorithm selection technologies have been successfully used in many research fields,such as constraint satisfaction and planning. Researchers have been increasingly trying to model the potential relations between different candidate algorithms for the algorithm selection. In this study, we propose an instancespecific algorithm selection method based on multi-output learning, which can manage these relations more directly.Three kinds of multi-output learning methods are used to predict the performances of the candidate algorithms：（1）multi-output regressor stacking;（2） multi-output extremely randomized trees; and（3） hybrid single-output and multioutput trees. The experimental results obtained using 11 SAT datasets and 5 Max SAT datasets indicate that our proposed methods can obtain a better performance over the state-of-the-art algorithm selection methods.
