检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Zhao, Yunrui Xu, Qianqian Jiang, Yangbangyan Wen, Peisong Huang, Qingming School of Computer Science and Technology University of Chinese Academy of Sciences China Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS China State Key Laboratory of Information Security Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management University of Chinese Academy of Sciences China

Positive-Unlabeled (PU) learning tries to learn binary classifiers from a few labeled positive examples with many unlabeled ones. Compared with ordinary semi-supervised learning, this task is much more challenging due to the absence of any known negative labels. While existing cost-sensitive-based methods have achieved state-of-the-art performances, they explicitly minimize the risk of classifying unlabeled data as negative samples, which might result in a negative-prediction preference of the classifier. To alleviate this issue, we resort to a label distribution perspective for PU learning in this paper. Noticing that the label distribution of unlabeled data is fixed when the class prior is known, it can be naturally used as learning supervision for the model. Motivated by this, we propose to pursue the label distribution consistency between predicted and ground-truth label distributions, which is formulated by aligning their expectations. Moreover, we further adopt the entropy minimization and Mixup regularization to avoid the trivial solution of the label distribution consistency on unlabeled data and mitigate the consequent confirmation bias. Experiments on three benchmark datasets validate the effectiveness of the proposed method. Code available at: https://***/Ray-rui/Dist-PU-Positive-UnlabeledLearning-from-a-Label-Distribution-Perspective. Copyright © 2022, The Authors. All rights reserved.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

Size-Invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection 41

Size-Invariance Matters: Rethinking Metrics and Losses for I...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Li, Feiran Xu, Qianqian Bao, Shilong Yang, Zhiyong Cong, Runmin Cao, Xiaochun Huang, Qingming Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Science Beijing Jiaotong University Beijing China School of Control Science and Engineering Shandong University Jinan China Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Cyber Science and Tech. Sun Yat-sen University Shenzhen Campus China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores the size-invariance of evaluation metrics in Salient Object Detection (SOD), especially when multiple targets of diverse sizes co-exist in the same image. We observe that current metrics are size-sensitive, where larger objects are focused, and smaller ones tend to be ignored. We argue that the evaluation should be size-invariant because bias based on size is unjustified without additional semantic information. In pursuit of this, we propose a generic approach that evaluates each salient object separately and then combines the results, effectively alleviating the imbalance. We further develop an optimization framework tailored to this goal, achieving considerable improvements in detecting objects of different sizes. Theoretically, we provide evidence supporting the validity of our new metrics and present the generalization analysis of SOD. Extensive experiments demonstrate the effectiveness of our method. The code is available at https://***/Ferry-Li/SI-SOD. Copyright 2024 by the author(s)

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Based Incentive Announcement System for Internet of Vehicles

Blockchain-Based Incentive Announcement System for Internet ...

引用

IEEE International Conference on Big data and Cloud Computing (BdCloud)

作者： Yang Yang Jialiang Chen Xianghan Zheng Ximeng Liu Wenzhong Guo Hairong Lv College of Mathematics and Computer Science Fuzhou University Fuzhou China Guangxi Key Laboratory of Cryptography and Information Security Guangnxi China Guangdong Provincial Key Laboratory of Data Security and Privacy Protection Guangzhou China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control (Minjiang University) Fuzhou China Ministry of Education Key Laboratory of Bioinformatics Bioinformatics Division and Center for Synthetic and Systems Biology Beijing National Research Center for Information Science and TechnologyDepartment of Automation Tsinghua University Beijing China

ISBN: (数字)9781728143286

ISBN: (纸本)9781728143293

With the rapid development of computation and communication technologies, the traditional vehicle ad hoc networks (VANETs) are changing to Internet of vehicle (IoV). Vehicular announcement networks in IoV have been widely used in the communication of vehicles. Generally, we need to solve two problems while establishing a vehicular announcement system. First, we need to protect user's privacy when broadcasting the message. Second, participants usually lack the enthusiasm to reply to the announcement. To solve these two problems, we propose a novel blockchain-based incentive announcement system that not only allows participants to anonymously announce their message on the blockchain in a non-trusted environment, but also motivates witnesses to respond to the request of the traffic information with incentive mechanism. Meanwhile, traffic messages and signatures in our system are tamper-resistant, which are recorded on the blockchain. According to the security and performance analysis, it shows that our system is privacy-preserving and efficient in computation cost.

关键词： Blockchain Privacy Smart contracts Authentication Internet Remuneration Hash functions

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

Study on the Relationships between Utilization Ratios and Conversion Rates of Nitrogen,Phosphorus and Potassium for Wheat

引用

Meteorological and Environmental Research 2020年第5期11卷 46-54页

作者： Zhiping HUANG Xianda HOU Shutian LIU 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 studied the relationships between utilization ratios and conversion rates of nitrogen,phosphorus and potassium 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 conceptual model of fertilizer utilization ratio of wheat for plot was that,Y N≈a+b×optimum nitrogen application amount+c×optimum fertilizer amount of K+d×rainfall in growth season,Y P≈a+b×optimum fertilizer amount of K+c×rainfall in growth season,Y K≈a+b×temperature in growth season+c×rainfall in growth season-d×optimum yield-e×optimum nitrogen application amount,respectively.②Fertilizer utilization ratio and nutrient conversion rate had 4 kinds of *** significant relationships:13,of which 8 were soil nutrients,the results showed that soil nutrients had little effect on nutrient conversion rate and fertilizer utilization ratio;consistent significant relationships:4,they were all nitrogen and phosphorus,explaining the importance of nitrogen and phosphorus;contrary significant relationships:6,they were all nitrogen and phosphorus,illustrating that phosphorus and nitrogen had inhibitory effect;complementary significant relationships:31,the cause of the complementary phenomenon was that the fertilizer utilization ratio was the measuring index of fertilizer efficiency in one season,while the nutrient conversion rate was the measuring index of fertilizer efficiency in more *** 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

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

FF-KGAT: Feature Fusion Based Knowledge Graph Attention Network for Recommendation 5

FF-KGAT: Feature Fusion Based Knowledge Graph Attention Netw...

引用

5th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2022

作者： Tao, Li Xiaoge, Li Chaodong, Wang Xianliang, Li Shuai, Gao Dan, Han Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xian University of Posts and Telecommunications Shaanxi Xi'an710121 China School of Computer Xian University of Posts and Telecommunications Shaanxi Xi'an710121 China Inspur Software Technology Co Ltd Software Development Project Management China Xian University of Posts and Telecommunications Shaanxi Xi'an710121 China School of Communication and Information Engineering Xian University of Posts and Telecommunications Shaanxi Xi'an710121 China

ISBN: (纸本)9781450396899

It is commonly agreed that a recommender system based on knowledge graph (KG) should not only use user-item interactions, but also take side information into account to deal with the problem of data sparsity. However, existing KG-based models present unique challenges that have the shortcoming of cold start and redundant iterations. To address the issue, we propose a Feature Fusion-based Knowledge Graph Attention Network (FF-KGAT) for the recommendation. FF-KGAT handles the cold-start problem through introducing user characteristics to fully explore the information of users. Additionally, FF-KGAT introduces the feature fusion graph, which removes slight nodes to obtain fewer iterations. Experimental results show that the proposed model significantly outperforms baseline methods. Particularly, the ndcg is increased by 9.83% and 10.25% on two public datasets, compared with the best performance of existing methods. © 2022 ACM.

关键词： Recommender systems

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

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

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：