Event correlation is one key technique in network fault management. For the event sample acquisition problem in event correlation, a novel approach is proposed to collect the samples by constructing network simulation...Event correlation is one key technique in network fault management. For the event sample acquisition problem in event correlation, a novel approach is proposed to collect the samples by constructing network simulation platform. The platform designed can set kinds of network faults according to user's demand and generate a lot of network fault events, which will benefit the research on efficient event correlation techniques.展开更多
Supervised machine learning approaches are effective in text mining,but their success relies heavily on manually annotated corpora.However,there are limited numbers of annotated biomedical event corpora,and the availa...Supervised machine learning approaches are effective in text mining,but their success relies heavily on manually annotated corpora.However,there are limited numbers of annotated biomedical event corpora,and the available datasets contain insufficient examples for training classifiers;the common cure is to seek large amounts of training samples from unlabeled data,but such data sets often contain many mislabeled samples,which will degrade the performance of classifiers.Therefore,this study proposes a novel error data detection approach suitable for reducing noise in unlabeled biomedical event data.First,we construct the mislabeled dataset through error data analysis with the development dataset.The sample pairs’vector representations are then obtained by the means of sequence patterns and the joint model of convolutional neural network and long short-term memory recurrent neural network.Following this,the sample identification strategy is proposed,using error detection based on pair representation for unlabeled data.With the latter,the selected samples are added to enrich the training dataset and improve the classification performance.In the BioNLP Shared Task GENIA,the experiments results indicate that the proposed approach is competent in extract the biomedical event from biomedical literature.Our approach can effectively filter some noisy examples and build a satisfactory prediction model.展开更多
Sequential samples of single precipitation event were collected by the use of specially de-signed semi-automatic sequential precipitation collector in the spring of 1988 in Guilin City. ThePH value and soluble chemica...Sequential samples of single precipitation event were collected by the use of specially de-signed semi-automatic sequential precipitation collector in the spring of 1988 in Guilin City. ThePH value and soluble chemical species such as SO, NO, NH, Ca￣(2+), Mg￣(2+), Na￣+, K`+, F￣- andCl￣- were analyzed. An apparent decrease in the concentration of all ions except H￣+ and NO wasobserved at the initial portion of the events. The relative acidity increased as the event progress.The concentration of H￣+ was the result of comprehensive actions of all ions. The average scavengingratio of events was calculated and it is found that SO was the major contributor for acid rain inGuilin and Ca￣(2+) was the important neutralizer.展开更多
To control water impairment in urban storm- water, it is important to evaluate changing patterns of water quality parameters in stormwater runoff. Thus, the authors performed a series of experiments to investigate the...To control water impairment in urban storm- water, it is important to evaluate changing patterns of water quality parameters in stormwater runoff. Thus, the authors performed a series of experiments to investigate the dynamics of common water parameters during storm events in semi-arid areas, with multiple samples collected and analyzed in field stormwater applications. At this field monitoring site within McAuliffe Park, McAllen, Texas, in the United States, a storm event increased the concentra- tions of Escherichia coli （E. coli）, but this event represented a decreasing trend over the entire event period. Besides, peak intensity of different pollutants in the stormwater runoff occurred at different times other than at any peak flows, representing a complexity of the temporal and spatial measurements. Multi-sample per- event approaches recommended based on the complexity of the hydrograph and different peak intensity times of pollutants. In addition, high bacteria and total suspended solids （TSS） concentrations in the initial stage of the storm event should be considered when designing Best Manage- ment Practices （BMPs） and Low Impact Developments （LIDs）. New strategies and solutions for addressing ecohydrological challenges should be proposed to avoid collateral damages to their both common wealth in ecosystems and human well-beings.展开更多
基金the National Natural Science Foundation of China(69983 0 0 5 )
文摘Event correlation is one key technique in network fault management. For the event sample acquisition problem in event correlation, a novel approach is proposed to collect the samples by constructing network simulation platform. The platform designed can set kinds of network faults according to user's demand and generate a lot of network fault events, which will benefit the research on efficient event correlation techniques.
基金This work was supported by the National Natural Science Foundation of China(No.61672301)Jilin Provincial Science&Technology Development(20180101054JC)+1 种基金Science and Technology Innovation Guide Project of Inner Mongolia Autonomous Region of China(2017)Talent Development Fund of Jilin Province(2018).
文摘Supervised machine learning approaches are effective in text mining,but their success relies heavily on manually annotated corpora.However,there are limited numbers of annotated biomedical event corpora,and the available datasets contain insufficient examples for training classifiers;the common cure is to seek large amounts of training samples from unlabeled data,but such data sets often contain many mislabeled samples,which will degrade the performance of classifiers.Therefore,this study proposes a novel error data detection approach suitable for reducing noise in unlabeled biomedical event data.First,we construct the mislabeled dataset through error data analysis with the development dataset.The sample pairs’vector representations are then obtained by the means of sequence patterns and the joint model of convolutional neural network and long short-term memory recurrent neural network.Following this,the sample identification strategy is proposed,using error detection based on pair representation for unlabeled data.With the latter,the selected samples are added to enrich the training dataset and improve the classification performance.In the BioNLP Shared Task GENIA,the experiments results indicate that the proposed approach is competent in extract the biomedical event from biomedical literature.Our approach can effectively filter some noisy examples and build a satisfactory prediction model.
文摘Sequential samples of single precipitation event were collected by the use of specially de-signed semi-automatic sequential precipitation collector in the spring of 1988 in Guilin City. ThePH value and soluble chemical species such as SO, NO, NH, Ca￣(2+), Mg￣(2+), Na￣+, K`+, F￣- andCl￣- were analyzed. An apparent decrease in the concentration of all ions except H￣+ and NO wasobserved at the initial portion of the events. The relative acidity increased as the event progress.The concentration of H￣+ was the result of comprehensive actions of all ions. The average scavengingratio of events was calculated and it is found that SO was the major contributor for acid rain inGuilin and Ca￣(2+) was the important neutralizer.
文摘To control water impairment in urban storm- water, it is important to evaluate changing patterns of water quality parameters in stormwater runoff. Thus, the authors performed a series of experiments to investigate the dynamics of common water parameters during storm events in semi-arid areas, with multiple samples collected and analyzed in field stormwater applications. At this field monitoring site within McAuliffe Park, McAllen, Texas, in the United States, a storm event increased the concentra- tions of Escherichia coli （E. coli）, but this event represented a decreasing trend over the entire event period. Besides, peak intensity of different pollutants in the stormwater runoff occurred at different times other than at any peak flows, representing a complexity of the temporal and spatial measurements. Multi-sample per- event approaches recommended based on the complexity of the hydrograph and different peak intensity times of pollutants. In addition, high bacteria and total suspended solids （TSS） concentrations in the initial stage of the storm event should be considered when designing Best Manage- ment Practices （BMPs） and Low Impact Developments （LIDs）. New strategies and solutions for addressing ecohydrological challenges should be proposed to avoid collateral damages to their both common wealth in ecosystems and human well-beings.
