Ilex asprella(Hook.et Arn.)Champ.ex Benth is one of the most important traditional Chinese medicines in southern China.The seeds of Ilex asprella usually have extremely low germination due to their dormancy characteri...Ilex asprella(Hook.et Arn.)Champ.ex Benth is one of the most important traditional Chinese medicines in southern China.The seeds of Ilex asprella usually have extremely low germination due to their dormancy characteristics,which severely impacts the efficiency of seedling raising and increases labor costs.In this study,to improve the seed germination of I.asprella,the effects of germination substrate,hormone,winnowing,and stratification treatments on the seed germination of I.asprella were investigated.The results of the germination matrix showed that the highest germination percentage of 45.2%was achieved under the 20℃/10℃day/night temperature and vermiculite germination medium conditions.The results of hormone treatments revealed that 100–400 mg/L of gibberellin(GA)and 50–100 mg/L of salicylic acid(SA)were found to be effective in releasing the dormancy of I.asprella seeds.Moreover,winnowing could effectively eliminate unsaturated seeds and impurities,thus improving the seed germination of I.asprella.Furthermore,warm temperature(15℃)stratification could expand the temperature range of I.asprella’s seed germination,which was beneficial for seed germination of I.asprella and for seed nursery at room temperature in production practice.The present study obtained a method to break dormancy and increase seed germination in I.asprella,thereby forming a groundwork for improving the efficiency of large-scale planting of I.asprella.展开更多
With the rapid growth of web-based social networking technologies in recent years, author identification and analysis have proven increasingly useful. Authorship analysis provides information about a document’s autho...With the rapid growth of web-based social networking technologies in recent years, author identification and analysis have proven increasingly useful. Authorship analysis provides information about a document’s author, often including the author’s gender. Men and women are known to write in distinctly different ways, and these differences can be successfully used to make a gender prediction. Making use of these distinctions between male and female authors, this study demonstrates the use of a simple stream-based neural network to automatically discriminate gender on manually labeled tweets from the Twitter social network. This neural network, the Modified Balanced Winnow, was employed in two ways;the effectiveness of data stream mining was initially examined with an extensive list of n-gram features. Feature selection techniques were then evaluated by drastically reducing the feature list using WEKA’s attribute selection algorithms. This study demonstrates the effectiveness of the stream mining approach, achieving an accuracy of 82.48%, a 20.81% increase above the baseline prediction. Using feature selection methods improved the results by an additional 16.03%, to an accuracy of 98.51%.展开更多
基金supported by the Fund Projects of the Central Government in Guidance of Local Science and Technology Development(GuiKeZY22096020)Natural Science Foundation of Guangxi(2019GXNSFBA245073)+1 种基金National Natural Science Foundation of China(82260750,82260749)Cooperative Project of Guangxi Botanical Garden of Medicinal Plants with China Resources Sanjiu Medical&Pharmaceutical Co.,Ltd.(202112-1).
文摘Ilex asprella(Hook.et Arn.)Champ.ex Benth is one of the most important traditional Chinese medicines in southern China.The seeds of Ilex asprella usually have extremely low germination due to their dormancy characteristics,which severely impacts the efficiency of seedling raising and increases labor costs.In this study,to improve the seed germination of I.asprella,the effects of germination substrate,hormone,winnowing,and stratification treatments on the seed germination of I.asprella were investigated.The results of the germination matrix showed that the highest germination percentage of 45.2%was achieved under the 20℃/10℃day/night temperature and vermiculite germination medium conditions.The results of hormone treatments revealed that 100–400 mg/L of gibberellin(GA)and 50–100 mg/L of salicylic acid(SA)were found to be effective in releasing the dormancy of I.asprella seeds.Moreover,winnowing could effectively eliminate unsaturated seeds and impurities,thus improving the seed germination of I.asprella.Furthermore,warm temperature(15℃)stratification could expand the temperature range of I.asprella’s seed germination,which was beneficial for seed germination of I.asprella and for seed nursery at room temperature in production practice.The present study obtained a method to break dormancy and increase seed germination in I.asprella,thereby forming a groundwork for improving the efficiency of large-scale planting of I.asprella.
文摘With the rapid growth of web-based social networking technologies in recent years, author identification and analysis have proven increasingly useful. Authorship analysis provides information about a document’s author, often including the author’s gender. Men and women are known to write in distinctly different ways, and these differences can be successfully used to make a gender prediction. Making use of these distinctions between male and female authors, this study demonstrates the use of a simple stream-based neural network to automatically discriminate gender on manually labeled tweets from the Twitter social network. This neural network, the Modified Balanced Winnow, was employed in two ways;the effectiveness of data stream mining was initially examined with an extensive list of n-gram features. Feature selection techniques were then evaluated by drastically reducing the feature list using WEKA’s attribute selection algorithms. This study demonstrates the effectiveness of the stream mining approach, achieving an accuracy of 82.48%, a 20.81% increase above the baseline prediction. Using feature selection methods improved the results by an additional 16.03%, to an accuracy of 98.51%.
