Hazelnut husk brown rot has been identified as a new disease in Liaoning Province in recent years.The objective of this study as to identify the pathogen.[Method]In this study,a standard sample of hazelnut husk brown ...Hazelnut husk brown rot has been identified as a new disease in Liaoning Province in recent years.The objective of this study as to identify the pathogen.[Method]In this study,a standard sample of hazelnut husk brown rot was collected from Songmudao Base in Dalian City,Liaoning Province.The pathogen was identified by the studies of the morphology,pathogenicity,and analyses of ITS and LSU sequences.The pathogen was isolated and purified,which was confirmed by Koch’s postulates.The symptoms after inoculation were the same as those collected directly from a diseased tree,which showed that it was the pathogenic fungus.The cultural characteristics and conidia and the morphology of the pathogenic fungi were similar to those of Botrytis cinerea’s.The ITS sequences and LSU sequences were compared to the associated strain sequences in GenBank,with 100%identity to Botrytis cinerea(GenBank accession number:MN589848.1)and Botrytis cinerea(GenBank accession number:KU140653.1),respectively.The infection status of the pathogen on the hazelnut husks was also observed.The studies suggested that the pathogen leading to the hazelnut husk brown rot as a new disease in Liaoning Province was Botrytis cinerea.展开更多
Decision-making for autonomous vehicles in the presence of obstacle occlusions is difficult because the lack of accurate information affects the judgment.Existing methods may lead to overly conservative strategies and...Decision-making for autonomous vehicles in the presence of obstacle occlusions is difficult because the lack of accurate information affects the judgment.Existing methods may lead to overly conservative strategies and timeconsuming computations that cannot be balanced with efficiency.We propose to use distributional reinforcement learning to hedge the risk of strategies,optimize the worse cases,and improve the efficiency of the algorithm so that the agent learns better actions.A batch of smaller values is used to replace the average value to optimize the worse case,and combined with frame stacking,we call it Efficient-Fully parameterized Quantile Function(EFQF).This model is used to evaluate signal-free intersection crossing scenarios and makes more efficient moves and reduces the collision rate compared to conventional reinforcement learning algorithms in the presence of perceived occlusion.The model also has robustness in the case of data loss compared to the method with embedded long and short term memory.展开更多
基金This work was financially supported by the Liaoning Provincial Natural Science Foundation of China(Grant No.2021-MS-057).
文摘Hazelnut husk brown rot has been identified as a new disease in Liaoning Province in recent years.The objective of this study as to identify the pathogen.[Method]In this study,a standard sample of hazelnut husk brown rot was collected from Songmudao Base in Dalian City,Liaoning Province.The pathogen was identified by the studies of the morphology,pathogenicity,and analyses of ITS and LSU sequences.The pathogen was isolated and purified,which was confirmed by Koch’s postulates.The symptoms after inoculation were the same as those collected directly from a diseased tree,which showed that it was the pathogenic fungus.The cultural characteristics and conidia and the morphology of the pathogenic fungi were similar to those of Botrytis cinerea’s.The ITS sequences and LSU sequences were compared to the associated strain sequences in GenBank,with 100%identity to Botrytis cinerea(GenBank accession number:MN589848.1)and Botrytis cinerea(GenBank accession number:KU140653.1),respectively.The infection status of the pathogen on the hazelnut husks was also observed.The studies suggested that the pathogen leading to the hazelnut husk brown rot as a new disease in Liaoning Province was Botrytis cinerea.
基金This work was supported partly by Beili Huidong(Changshu)Vehicle Technology Company.
文摘Decision-making for autonomous vehicles in the presence of obstacle occlusions is difficult because the lack of accurate information affects the judgment.Existing methods may lead to overly conservative strategies and timeconsuming computations that cannot be balanced with efficiency.We propose to use distributional reinforcement learning to hedge the risk of strategies,optimize the worse cases,and improve the efficiency of the algorithm so that the agent learns better actions.A batch of smaller values is used to replace the average value to optimize the worse case,and combined with frame stacking,we call it Efficient-Fully parameterized Quantile Function(EFQF).This model is used to evaluate signal-free intersection crossing scenarios and makes more efficient moves and reduces the collision rate compared to conventional reinforcement learning algorithms in the presence of perceived occlusion.The model also has robustness in the case of data loss compared to the method with embedded long and short term memory.