检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Ma, Jie Chai, Qi Liu, Jun Yin, Qingyu Wang, Pinghui Zheng, Qinghua Ministry of Education of Key Lab for Intelligent Networks and Network Security School of Cyber Science and Engineering Xi’an Jiaotong University Shaanxi Xi’an710049 China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering The School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Xi’an710049 China Amazon United States

Textbook Question Answering (TQA) is the task of correctly answering diagram or non-diagram questions given large multi-modal contexts consisting of abundant essays and diagrams. In real-world scenarios, an explainable TQA system plays a key role in deepening humans’ understanding of learned knowledge. However, there is no work to investigate how to provide explanations currently. To address this issue, we devise a novel architecture towards span-level eXplanations for TQA (XTQA). In this paper, spans are the combinations of sentences within a paragraph. The key idea is to consider the entire textual context of a lesson as candidate evidence, and then use our proposed coarse-to-fine grained Explanation Extracting (EE) algorithm to narrow down the evidence scope and extract the span-level explanations with varying lengths for answering different questions. The EE algorithm can also be integrated into other TQA methods to make them explainable and improve the TQA performance. Experimental results show that XTQA obtains the best overall explanation result (mIoU) of 52.38% on the first 300 questions of CK12-QA test splits, demonstrating the explainability of our method (non-diagram: 150 and diagram: 150). The results also show that XTQA achieves the best TQA performance of 36.46% and 36.95% on the aforementioned splits respectively. We have released our code in https://***/dr-majie/*** Codes 68T07 Copyright © 2020, The Authors. All rights reserved.

关键词： Textbooks

来源：评论

学校读者我要写书评

暂无评论

Global context-aware progressive aggregation network for salient object detection

arXiv

引用

arXiv 2020年

作者： Chen, Zuyao Xu, Qianqian Cong, Runmin Huang, Qingming University of Chinese Academy of Sciences Beijing China Key Lab. of Intelligent Information Processing ICT CAS Beijing China Institute of Information Science Beijing Jiaotong University Beijing China Key Lab. of Big Data Mining and Knowledge Management CAS Beijing China Peng Cheng Laboratory Shenzhen Guangdong China

Deep convolutional neural networks have achieved competitive performance in salient object detection, in which how to learn effective and comprehensive features plays a critical role. Most of the previous works mainly adopted multiplelevel feature integration yet ignored the gap between different features. Besides, there also exists a dilution process of high-level features as they passed on the top-down pathway. To remedy these issues, we propose a novel network named GCPANet to effectively integrate low-level appearance features, high-level semantic features, and global context features through some progressive context-aware Feature Interweaved Aggregation (FIA) modules and generate the saliency map in a supervised way. Moreover, a Head Attention (HA) module is used to reduce information redundancy and enhance the top layers features by leveraging the spatial and channel-wise attention, and the Self Refinement (SR) module is utilized to further refine and heighten the input features. Furthermore, we design the Global Context Flow (GCF) module to generate the global context information at different stages, which aims to learn the relationship among different salient regions and alleviate the dilution effect of high-level features. Experimental results on six benchmark datasets demonstrate that the proposed approach outperforms the state-of-the-art methods both quantitatively and qualitatively. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Studies on the Provincial-level Index System of Ecological Balanced Fertilization for Rice in China

引用

Meteorological and Environmental Research 2020年第5期11卷 104-110页

作者： Zhiping HUANG Xianda HOU Shuojin WANG Shutian LIU Hongyan ZHENG Jian DING Changhong MI Ling LU Yanlin HOU Agro-Environmental Protection Institute Ministry of Agriculture and Rural AffairsTianjin 300191China Guangxi Geographical Indication Crops Research Center of Big Data Mining and Experimental Engineering Technology Nanning Normal UniversityNanning 530001China Guangxi Key Laboratory of Earth Surface Processes and Intelligent Simulation Nanning Normal UniversityNanning 530001China Key Laboratory of Environment Change and Resources Use in Beibu Gulf(Nanning Normal University) Nanning 530001China

In this paper,the index system of ecological balanced fertilization for rice was discussed by data mining method based on this *** aspects of provincial average,typical province and all samples were studied,and the results and conclusions were as follows:①climate condition was one of the main factors of soil formation,which was also an important basis for the division of rice growing *** proportion of available nutrients was different in different rice growing *** was the result of long-term climate and man-made action,which constituted the basic fertility pattern of soil available nutrients for rice in China.②One of the basic fertility indexes of rice soil in China was the proportion of available nutrients,which was the theoretical basis for adjusting the proportion of N,P and K fertilizers.③Although the total amount and proportion of available nutrients in different rice growing areas were different,they can be adjusted to the optimum absorption ratio of rice by fertilizing measures,so as to achieve the goal of ecological balanced fertilization such as high production and good quality.④The basic soil nutrient index of more than 8000 kg/hm 2 of rice production was more than 5 of available K/available P.

关键词： Optimum yield Optimum fertilization amount Nutrient conversion rate Fertilizer utilization ratio Relative abundance-deficiency value of soil nutrient

来源：评论

学校读者我要写书评

暂无评论

Incorporating Hidden Layer representation into Adversarial Attacks and Defences

arXiv

引用

arXiv 2020年

作者： Shen, Haojing Chen, Sihong Wang, Ran Wang, Xizhao Big Data Institute College of Computer Science and Software Engineering Guangdong Key Lab. of Intelligent Information Processing Shenzhen University Guangdong Shenzhen518060 China The College of Mathematics and Statistics Shenzhen University Shenzhen518060 China The Shenzhen Key Laboratory of Advanced Machine Learning and Applications Shenzhen University Shenzhen518060 China

In this paper, we propose a defence strategy to improves adversarial robustness incorporating hidden layer representation. The key of this defence strategy aims to compress or filter input’s information including adversarial perturbation. And this defence strategy can be regarded as an activation function which can be applied any kind of neural networks. We also prove theoretically the effectiveness of this defense strategy under certain conditions. Besides, incorporating hidden layer representation we propose three types of adversarial attacks to generate three types of adversarial examples, respectively. The experiments show that our defence method can significantly improve the adversarial robustness of deep neural networks which achieves the state-of-the-art performance even though we do not adopt adversarial training. © 2020, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Summary on the Index System of Ecological Balanced Fertilization for Rice

引用

Meteorological and Environmental Research 2020年第5期11卷 11-17页

作者： Ling LU Jian DING Hongyan ZHENG Shutian LIU Xianda HOU Shuojin WANG Zhiping HUANG Changhong MI Yanlin HOU Guangxi Geographical Indication Crops Research Center of Big Data Mining and Experimental Engineering Technology Nanning Normal UniversityNanning 530001China Guangxi Key Laboratory of Earth Surface Processes and Intelligent Simulation Nanning Normal UniversityNanning 530001China Key Laboratory of Environment Change and Resources Use in Beibu Gulf(Nanning Normal University) Nanning 530001China Agro-Environmental Protection Institute Ministry of Agriculture and Rural AffairsTianjin 300191China

This paper studied the index system of ecological balanced fertilization for rice by data mining method based on data of"3414 fertilizer field trials"of rice by published papers from national soil testing and recommendation since *** results and conclusions were as follows:①the optimum N,P and K fertilization amounts of rice were within the normal range,and the application of this standard could not cause obvious non-point source pollution.②N,P and K conversion ratios were 76.4%,166.58%and 261.89%higher than N,P and K utilization ratios under the optimum fertilizer amount of rice,respectively.③At present,the soil N for rice was in a low equilibrium stage,and soil P and K were in the middle and high level,in which P was in the accumulation stage,while K was in the depletion stage.④The relationship between fertilizer effect or fertility and optimum production had *** fertilizer effect was negatively correlated with the optimum fertilization amount of its own nutrient.N,P and K fertilizers had mutual promoting effect when they were *** nutrient played an inhibitory role in the fertilizer efficiency of its own *** nutrient sometimes played a role in promoting the efficiency of other nutrients,and sometimes inhibited *** was a positive correlation between soil nutrients with the same attribute.

关键词： Optimum yield Optimum fertilization amount Nutrient conversion rate Fertilizer utilization ratio Relative abundance-deficiency value of soil nutrient

来源：评论

学校读者我要写书评

暂无评论

Study on the Relationship between Utilization Ratios and Conversion Rates of Nitrogen,Phosphorus and Potassium for Rice

引用

Meteorological and Environmental Research 2020年第5期11卷 25-32页

作者： Shuojin WANG Zhiping HUANG Changhong MI Hongyan ZHENG Jian DING Shutian LIU Xianda HOU Ling LU Yanlin HOU Guangxi Geographical Indication Crops Research Center of Big Data Mining and Experimental Engineering Technology Nanning Normal UniversityNanning 530001China Guangxi Key Laboratory of Earth Surface Processes and Intelligent Simulation Nanning Normal UniversityNanning 530001China Key Laboratory of Environment Change and Resources Use in Beibu Gulf(Nanning Normal University) Nanning 530001China Agro-Environmental Protection Institute Ministry of Agriculture and Rural AffairsTianjin 300191China

This paper studied the relationships between utilization ratios and conversion rates of nitrogen,phosphorus and potassium for rice by data mining method based on data of"3414 fertilizer field trials"of rice by published papers from national soil testing and recommendation since *** results and conclusions were as follows:①the conceptual model of fertilizer utilization ratio of rice for plot was that,Y N≈a+b×optimum yield+c×optimum fertilizer amount of K,Y P≈a+b×optimum yield,Y K≈a respectively.②Fertilizer utilization ratio and nutrient conversion rate had 4 kinds of relationships:①no significant relationships:25,of which 14 were soil nutrients and 9 were environmental factors,the results showed that soil nutrients and environmental factors had little effect on nutrient yield ratio and fertilizer utilization ratio;②consistent significant relationships:2,one was that yield ratio and utilization ratio of N were positively correlated with the optimum production,explaining the importance of N for production,the other was that yield ratio and utilization ratio of P had a significantly positive correlation with conversion rate and utilization ratio of N,illustrating that nitrogen and phosphorus had mutual promotion;③contrary significant relationships:5,these showed as negative correlations of fertilizer utilization ratio and positive correlation of nutrient conversion ratio;④complementary significant relationships:22,the cause of the complementary phenomenon was that the fertilizer utilization ratio was the index of fertilizer efficiency in one season,while the nutrient conversion rate was the index of fertilizer efficiency in more seasons,which showed that the fertilizer utilization rate was significantly correlated,or the nutrient conversion rate was significantly correlated.

关键词： Optimum yield Optimum fertilization amount Nutrient conversion rate Fertilizer utilization ratio Relative abundance-deficiency value of soil nutrient

来源：评论

学校读者我要写书评

暂无评论

Specific Index System of Ecological Balanced Fertilization for Wheat

引用

Meteorological and Environmental Research 2020年第5期11卷 38-45页

作者： Zhiping HUANG Ling LU Shutian LIU Shuojin WANG Xianda HOU Hongyan ZHENG Jian DING Changhong MI Yanlin HOU Agro-Environmental Protection Institute Ministry of Agriculture and Rural AffairsTianjin 300191China Guangxi Geographical Indication Crops Research Center of Big Data Mining and Experimental Engineering Technology Nanning Normal UniversityNanning 530001China Guangxi Key Laboratory of Earth Surface Processes and Intelligent Simulation Nanning Normal UniversityNanning 530001China Key Laboratory of Environment Change and Resources Use in Beibu Gulf(Nanning Normal University) Nanning 530001China

This paper studied the index system of ecological balanced fertilization for wheat by data mining method based on data of"3414 fertilizer field trials"of wheat by published papers from national soil testing and recommendation since *** results and conclusions were as follows.①Soil nutrient content could not be used as indicator of fertilizer application of wheat.②The conceptual model of N utilization ratio of wheat for plot was Y N≈a+b×optimum production-c×optimum fertilizer amount of N-d×temperature in growing season-e×rainfall in growing season,and the conceptual model of P conversion rate was Y P≈a+b×optimum production+c×temperature in growing season+d×precipitation in growing season-e×optimum fertilizer amount of P-f×optimum fertilizer amount of K,and the conceptual model of K conversion rate of wheat plots was that,Y K≈a-b×optimum fertilizer amount of K.③The conceptual model of the optimum fertilizer amount of N of wheat for plot was Y N≈a+b×optimum production+c×optimum fertilizer amount of P-d×temperature in growing season-e×rainfall in growing season,and the conceptual model of the optimum fertilizer amount of P was Y P≈a+b×optimum production+c×optimum fertilizer amount of N+d×optimum fertilizer amount of K,and the conceptual model of the optimum fertilizer amount of K was Y K≈a+b×optimum fertilizer amount of P.④The conceptual model of relative abundance-deficiency value of soil N of wheat for plot was that Y N≈a-b×temperature in growing season-c×precipitation in growing season,and the conceptual model of relative abundance-deficiency value of soil P was Y P≈a+b×optimum yield+c×optimum fertilizer amount of N+d×precipitation in growing season-e×optimum fertilizer amount of K,and the conceptual model of relative abundance-deficiency value of soil K was Y K≈a+b×optimum yield+c×optimum fertilizer amount of K.

关键词： Optimum yield Optimum fertilization amount Nutrient conversion rate Fertilizer utilization ratio Relative abundance-deficiency value of soil nutrient

来源：评论

学校读者我要写书评

暂无评论

Specific Index System of Ecological Balanced Fertilization for Rice

引用

Meteorological and Environmental Research 2020年第5期11卷 18-24,32页

作者： Xianda HOU Changhong MI Shuojin WANG Shutian LIU Zhiping HUANG Hongyan ZHENG Jian DING Ling LU Yanlin HOU Guangxi Geographical Indication Crops Research Center of Big Data Mining and Experimental Engineering Technology Nanning Normal UniversityNanning 530001China Guangxi Key Laboratory of Earth Surface Processes and Intelligent Simulation Nanning Normal UniversityNanning 530001China Key Laboratory of Environment Change and Resources Use in Beibu Gulf(Nanning Normal University) Nanning 530001China Agro-Environmental Protection Institute Ministry of Agriculture and Rural AffairsTianjin 300191China

This paper studied the nitrogen index system of ecological balanced fertilization for rice by data mining method based on data of"3414 fertilizer field trials"of rice by published papers from national soil testing and recommendation since *** results and conclusions were as follows.①Soil nutrient content could not be used as fertilization indicator of rice.②The conceptual model of nitrogen conversion rate of rice for plot was Y N≈a+b×optimum production-c×optimum nitrogen fertilization amount-d×optimum phosphorus fertilization amount,and the conceptual model of phosphorus conversion rate was Y P≈a-b×optimum phosphorus fertilization amount-c×optimum potassium fertilization amount,and the conceptual model of potassium conversion rate was Y K≈a+b×optimum production+c×optimum nitrogen fertilization amount-d×optimum potassium fertilization amount-e×annual average precipitation.③The conceptual model of the optimum nitrogen fertilization amount of rice for plot was Y N≈a+b×optimum production+c×optimum phosphorus fertilization amount-d×annual average precipitation,and the conceptual model of the optimum phosphorus fertilization amount was Y P≈a+b×optimum nitrogen fertilization amount+c×optimum potassium fertilization amount,and the conceptual model of the optimum potassium fertilization amount was Y K≈a+b×optimum phosphorus fertilization amount+c×annual average precipitation.④The conceptual model of relative abundance-deficiency value of soil nitrogen of rice for plot was Y N≈a-b×optimum nitrogen fertilization amount-c×optimum potassium fertilization amount,and the conceptual model of relative abundance-deficiency value of soil phosphorus was Y P≈a+b×soil available potassium-c×optimum potassium fertilization amount,and the conceptual model of relative abundance-deficiency value of soil potassium of rice was Y K≈a-b×optimum potassium fertilization amount.

关键词： Optimum yield Optimum fertilization amount Nutrient conversion rate Fertilizer utilization ratio Relative abundance-deficiency value of soil nutrient

来源：评论

学校读者我要写书评

暂无评论

Summary on the Index System of Ecological Balanced Fertilization for Wheat

引用

Meteorological and Environmental Research 2020年第5期11卷 33-37,45页

作者： Zhiping HUANG Shuojin WANG Shutian LIU Xianda HOU Hongyan ZHENG Jian DING Changhong MI Ling LU Yanlin HOU Agro-Environmental Protection Institute Ministry of Agriculture and Rural AffairsTianjin 300191China Guangxi Geographical Indication Crops Research Center of Big Data Mining and Experimental Engineering Technology Nanning Normal UniversityNanning 530001China Guangxi Key Laboratory of Earth Surface Processes and Intelligent Simulation Nanning Normal UniversityNanning 530001China Key Laboratory of Environment Change and Resources Use in Beibu Gulf(Nanning Normal University) Nanning 530001China

This paper studied the index system of ecological balanced fertilization for wheat by data mining method based on data of"3414 fertilizer field trials"of wheat by published papers from national soil testing and recommendation since *** results and conclusions were as follows:①the optimum N,P and K fertilization amounts of wheat were within the normal range,and the application of this standard could not cause obvious non-point source pollution.②The conversion rates of N,P and K of wheat were 58.78%,58.63%and 199.88%higher than the utilization ratios of N,P and K under the optimum fertilization amount,respectively.③At present,the soil N for wheat was in a low equilibrium stage,and soil P and K were in the middle and high levels,in which P was in the accumulation stage,and K was in the depletion stage.④The relationship between fertilizer effect or fertility and optimum production had *** fertilizer effect was negatively correlated with the optimum fertilization amounts of its own nutrient and other nutrients.N,P and K fertilizers had mutual promoting effects when they were *** nutrient played an inhibitory role in the fertilizer efficiency of its own nutrient.⑤The phosphorus and potassium utilization ratios were significantly positively correlated with the optimum phosphorus fertilization amount and the optimal potassium fertilization amount,which was the scientific basis for phosphorus and potassium concentrated fertilization of wheat.

关键词： Optimum yield Optimum fertilization amount Nutrient conversion rate Fertilizer utilization ratio Relative abundance-deficiency value of soil nutrient

来源：评论

学校读者我要写书评

暂无评论

Research and Application of Prediction Model for Ecological Balanced Optimal Fertilization Amount for Three Crops

引用

Meteorological and Environmental Research 2020年第5期11卷 96-103页

作者： Zhiping HUANG Shutian LIU Xianda HOU Shuojin WANG Hongyan ZHENG Jian DING Changhong MI Ling LU Yanlin HOU Agro-Environmental Protection Institute Ministry of Agriculture and Rural AffairsTianjin 300191China Guangxi Geographical Indication Crops Research Center of Big Data Mining and Experimental Engineering Technology Nanning Normal UniversityNanning 530001China Guangxi Key Laboratory of Earth Surface Processes and Intelligent Simulation Nanning Normal UniversityNanning 530001China Key Laboratory of Environment Change and Resources Use in Beibu Gulf(Nanning Normal University) Nanning 530001China

This paper analyzed the modeling principle,process and application process of the new ecological balanced fertilization model by data mining method based on the relationships among soil abundance-deficiency index,optimum fertilization amount and nutrient conversion rate of N,P,K for rice,wheat and maize in column *** results and conclusions were as follows:①on the basis of two ecological balanced fertilization models(available and total nutrients),a prediction model system of optimum fertilization amount based on nutrient conversion rate was established,including 3 *** first model predicted the optimum fertilization amount based on nutrient conversion rate,and the second model determined prediction difference value of optimum fertilization amount in the first amendment based on optimum yield,and the third model determined prediction difference value of optimum fertilization amount in the second amendment based on nutrient conversion rate.②Nutrient conversion rate and optimum yield were the common parameters of two models based on contents of available and total nutrients,and they were the core parameters of ecological balanced fertilization *** the specific application,the nutrient conversion rate and optimum yield were determined mainly based on the comprehensive comparison between the regional or similar plot or one plot and the experimental plot.③The two error amendments were due to the use of the fixed nutrient removal of 100 kg seeds,and underestimated the nutrient conversion rate when higher optimum production and overestimated the nutrient conversion rate when lower optimum production.④It was proposed that the nutrient conversion rate was regarded as a comprehensive nutrient index(abundance-deficiency)of ecological balanced *** was not only a parameter to measure fertilizer efficiency,but also a parameter to measure the abundance-deficiency of nutrients,and a parameter to guide fertilization.

关键词： Optimum yield Optimum fertilization amount Nutrient conversion rate Fertilizer utilization ratio Relative abundance-deficiency value of soil nutrient

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：