Soil erosion gradation is a robust and objective quantitative indicator of soil erosion intensity. Recent applications of soil erosion gradation have focused on monitoring soil erosion with models or simulation of soi...Soil erosion gradation is a robust and objective quantitative indicator of soil erosion intensity. Recent applications of soil erosion gradation have focused on monitoring soil erosion with models or simulation of soil erosion through gradation trends. However, soil erosion simulation accuracy is generally being reduced due to the rare consideration of the relationship between soil erosion gradation and erosion evolution. In this study, we investigated different soil erosion intensity grades to demonstrate their sensitivity to types and rates of erosion. Specifically, the objective was to define the relationship between soil erosion gradation and soil erosion evolution in Changting, an undeveloped area in Fujian Province, China, for four time intervals (1975, 1990, 1999, and 2006). The time series of erosion gradation were developed by modeling analysis with integration of several erosion indicators, and the relationships between the erosion grades and evolution types and rates were quantified. Comparison of the collapsing forces with natural and restoring forces based on human activity demonstrated that there existed an obvious spatial uncertainty in the erosion evolution types, both positive and negative succession coexisted, and the evolution rates were mostly influenced by the force of policy orientation. The impacts of these driving forces were eventually reflected in the erosion intensity gradation and erosion evolution. The correlation between the negative succession rate and erosion intensity gradation was weak and showed a poor contribution to the average succession rate, while the negative correlation between the positive succession rate and erosion intensity gradation would be increasingly clear as time passed.展开更多
基于正项级数通项的比值 a n+p/ a n ≤ b n+p /b n 的分析,得到了 Kummer 判别法的一种推广形式,进一步给出了其极限表示.对推广的 Kummer 判别法中的赋值,分别得到推广的达朗贝尔判别法,推广的拉贝判别法及推广的贝特朗判别法.类似得...基于正项级数通项的比值 a n+p/ a n ≤ b n+p /b n 的分析,得到了 Kummer 判别法的一种推广形式,进一步给出了其极限表示.对推广的 Kummer 判别法中的赋值,分别得到推广的达朗贝尔判别法,推广的拉贝判别法及推广的贝特朗判别法.类似得到高斯判别法的推广形式.最后通过若干例子验证了方法的有效性.展开更多
In the last decade,there has been significant progress in time series classification.However,in real-world in-dustrial settings,it is expensive and difficult to obtain high-quality labeled data.Therefore,the positive ...In the last decade,there has been significant progress in time series classification.However,in real-world in-dustrial settings,it is expensive and difficult to obtain high-quality labeled data.Therefore,the positive and unlabeled learning(PU-learning)problem has become more and more popular recently.The current PU-learning approaches of the time series data suffer from low accuracy due to the lack of negative labeled time series.In this paper,we propose a novel shapelet based two-step(2STEP)PU-learning approach.In the first step,we generate shapelet features based on the posi-tive time series,which are used to select a set of negative examples.In the second step,based on both positive and nega-tive time series,we select the final features and build the classification model.The experimental results show that our 2STEP approach can improve the average F1 score on 15 datasets by 9.1%compared with the baselines,and achieves the highest F1 score on 10 out of 15 time series datasets.展开更多
A risk assessment based adaptive ultra-short-term wind power prediction(USTWPP)method is proposed in this paper.In this method,features are first extracted from the historical data,and then each wind power time series...A risk assessment based adaptive ultra-short-term wind power prediction(USTWPP)method is proposed in this paper.In this method,features are first extracted from the historical data,and then each wind power time series(WPTS)is split into several subsets defined by their stationary patterns.A WPTS that does not match any of the stationary patterns is then included in a subset of non-stationary patterns.Each WPTS subset is then related to a USTWPP model that is specially selected and optimized offline based on the proposed risk assessment index.For online applications,the pattern of the last short WPTS is first recognized,and the relevant prediction model is then applied for USTWPP.Experimental results confirm the efficacy of the proposed method.展开更多
基金Supported by the National Key Technology R&D Program of China (No. 2009BADC6B)
文摘Soil erosion gradation is a robust and objective quantitative indicator of soil erosion intensity. Recent applications of soil erosion gradation have focused on monitoring soil erosion with models or simulation of soil erosion through gradation trends. However, soil erosion simulation accuracy is generally being reduced due to the rare consideration of the relationship between soil erosion gradation and erosion evolution. In this study, we investigated different soil erosion intensity grades to demonstrate their sensitivity to types and rates of erosion. Specifically, the objective was to define the relationship between soil erosion gradation and soil erosion evolution in Changting, an undeveloped area in Fujian Province, China, for four time intervals (1975, 1990, 1999, and 2006). The time series of erosion gradation were developed by modeling analysis with integration of several erosion indicators, and the relationships between the erosion grades and evolution types and rates were quantified. Comparison of the collapsing forces with natural and restoring forces based on human activity demonstrated that there existed an obvious spatial uncertainty in the erosion evolution types, both positive and negative succession coexisted, and the evolution rates were mostly influenced by the force of policy orientation. The impacts of these driving forces were eventually reflected in the erosion intensity gradation and erosion evolution. The correlation between the negative succession rate and erosion intensity gradation was weak and showed a poor contribution to the average succession rate, while the negative correlation between the positive succession rate and erosion intensity gradation would be increasingly clear as time passed.
文摘基于正项级数通项的比值 a n+p/ a n ≤ b n+p /b n 的分析,得到了 Kummer 判别法的一种推广形式,进一步给出了其极限表示.对推广的 Kummer 判别法中的赋值,分别得到推广的达朗贝尔判别法,推广的拉贝判别法及推广的贝特朗判别法.类似得到高斯判别法的推广形式.最后通过若干例子验证了方法的有效性.
基金supported by the National Key Research and Development Program of China under Grant No.2020YFB1710001.
文摘In the last decade,there has been significant progress in time series classification.However,in real-world in-dustrial settings,it is expensive and difficult to obtain high-quality labeled data.Therefore,the positive and unlabeled learning(PU-learning)problem has become more and more popular recently.The current PU-learning approaches of the time series data suffer from low accuracy due to the lack of negative labeled time series.In this paper,we propose a novel shapelet based two-step(2STEP)PU-learning approach.In the first step,we generate shapelet features based on the posi-tive time series,which are used to select a set of negative examples.In the second step,based on both positive and nega-tive time series,we select the final features and build the classification model.The experimental results show that our 2STEP approach can improve the average F1 score on 15 datasets by 9.1%compared with the baselines,and achieves the highest F1 score on 10 out of 15 time series datasets.
基金supported in part by Special Fund of the National Basic Research Program of China(2013CB228204)NSFCNRCT Collaborative Project(No.51561145011)+1 种基金Australian Research Council Project(DP120101345)State Grid Corporation of China.
文摘A risk assessment based adaptive ultra-short-term wind power prediction(USTWPP)method is proposed in this paper.In this method,features are first extracted from the historical data,and then each wind power time series(WPTS)is split into several subsets defined by their stationary patterns.A WPTS that does not match any of the stationary patterns is then included in a subset of non-stationary patterns.Each WPTS subset is then related to a USTWPP model that is specially selected and optimized offline based on the proposed risk assessment index.For online applications,the pattern of the last short WPTS is first recognized,and the relevant prediction model is then applied for USTWPP.Experimental results confirm the efficacy of the proposed method.
