检索结果-内蒙古大学图书馆

Comparison of the Index System of Ecological Balanced Fertilization for Three Crops

Meteorological and Environmental Research 2020年第5期11卷 76-90页

作者： Xianda HOU Hongyan ZHENG Shuojin WANG Shutian LIU Zhiping HUANG Jian DING Changhong MI 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 conducted comparative study of the index system of ecological balanced fertilization for rice,wheat and maize by data mining method based on data of"3414 fertilizer field trials"of rice,wheat and maize by published papers from national soil testing and recommendation since *** main conclusions of this paper were as follow:①since the three crops all belonged to Gramineae,they were consistent in variation trends of fertilizer utilization ratio,nutrient conversion rate,relative abundance-deficiency value of soil nutrient,optimum fertilization amount in most cases.②Due to the influence of the economic production,biological production,different water conditions in paddy field and dry farmland,length of growing season,cropping system(one year before and after the rotation)and so on,sometimes the laws of four aspects above mentioned for the three crops had opposite and gradient variations.

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 Maize

引用

Meteorological and Environmental Research 2020年第5期11卷 55-61页

作者： Hongyan ZHENG Shutian LIU Xianda HOU Shuojin WANG Zhiping HUANG 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 maize by data mining method based on data of"3414 fertilizer field trials"of maize 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 maize 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 maize were respectively higher than their respective utilization ratios under the optimum fertilization amount.③At present,the soil N for maize was in an absence state,and soil P and K were in a state of not obvious lack.④Optimum N,P and K fertilization amounts were significantly negatively correlated with their respective conversion ratios,respectively,and it provided a quantitative scientific basis for calculating the optimum fertilization amount according to the nutrient conversion *** province can use this significant relationship to guide the determination of the average optimal fertilization amounts of N,P and K and the optimal production in the province.⑤The research results of nutrient conversion rate showed that any excessive application of N,P and K would reduce their own nutrient conversion rates,and may also reduce the conversion rates of other *** characteristics of crops absorbing N,P and K proportionally required that soil nutrients must be balanced in order to obtain high production,and fertilization was only the main means to regulate soil nutrient balance.

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

A Survey on Accuracy-oriented Neural Recommendation: From Collaborative Filtering to Information-rich Recommendation

arXiv

引用

arXiv 2021年

作者： Wu, Le He, Xiangnan Wang, Xiang Zhang, Kun Wang, Meng Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Anhui Hefei230029 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Anhui Hefei230088 China University of Science and Technology of China Hefei230026 China National University of Singapore Singapore

Influenced by the great success of deep learning in computer vision and language understanding, research in recommendation has shifted to inventing new recommender models based on neural networks. In recent years, we have witnessed significant progress in developing neural recommender models, which generalize and surpass traditional recommender models owing to the strong representation power of neural networks. In this survey paper, we conduct a systematic review on neural recommender models from the perspective of recommendation modeling with the accuracy goal, aiming to summarize this field to facilitate researchers and practitioners working on recommender systems. Specifically, based on the data usage during recommendation modeling, we divide the work into collaborative filtering and information-rich recommendation: 1) collaborative filtering, which leverages the key source of user-item interaction data;2) content enriched recommendation, which additionally utilizes the side information associated with users and items, like user profile and item knowledge graph;and 3) temporal/sequential recommendation, which accounts for the contextual information associated with an interaction, such as time, location, and the past interactions. After reviewing representative work for each type, we finally discuss some promising directions in this field. © 2021, CC BY.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

NMR Spectra Denoising with Vandermonde Constraints

arXiv

引用

arXiv 2023年

作者： Guo, Di Xu, Runmin Wu, Jinyu Lin, Meijin Du, Xiaofeng Qu, Xiaobo School of Computer and Information Engineering Fujian Engineering Research Center for Medical Data Mining and Application Xiamen University of Technology Xiamen361024 China Department of Electronic Science Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance Xiamen University Xiamen361102 China Department of Applied Marine Physics and Engineering Xiamen University Xiamen361102 China

Nuclear magnetic resonance (NMR) spectroscopy serves as an important tool to analyze chemicals and proteins in bioengineering. However, NMR signals are easily contaminated by noise during the data acquisition, which can affect subsequent quantitative analysis. Therefore, denoising NMR signals has been a long-time concern. In this work, we propose an optimization model-based iterative denoising method, CHORD-V, by treating the time-domain NMR signal as damped exponentials and maintaining the exponential signal form with a Vandermonde factorization. Results on both synthetic and realistic NMR data show that CHORD-V has a superior denoising performance over typical Cadzow and rQRd methods, and the state-of-the-art CHORD method. CHORD-V restores low-intensity spectral peaks more accurately, especially when the noise is relatively high. © 2023, CC BY.

关键词： Nuclear magnetic resonance spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Ascl: Accelerating Semi-Supervised Learning Via Contrastive Learning

SSRN

引用

SSRN 2024年

作者： Liu, Haixiong Li, Zuoyong Wu, Jiawei Zeng, Kun Hu, Rong Zeng, Wei Fujian Provincial Key Laboratory of Big Data Mining and Applications School of Computer Science and Mathematics Fujian University of Technology Fuzhou350118 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Data Science Minjiang University Fuzhou350121 China School of Intelligent Systems Engineering Shenzhen Campus of Sun Yat-sen University Guangdong Shenzhen518107 China The Key Laboratory of Cognitive Computing and Intelligent Information Processing of Fujian Education Institutions Wuyi University Wuyishan354300 China School of Physics and Mechanical and Electrical Engineering Longyan University Longyan364012 China

SSL(Semi-supervised learning) is widely used in machine learning, which leverages labeled and unlabeled data to improve model performance. SSL aims to optimize class mutual information, but noisy pseudo-labels introduce false class information due to the scarcity of labels. Therefore, these algorithms often need significant training time to refine pseudo-labels for performance improvement iteratively. To tackle this challenge, we propose a novel plug-and-play method named ASCL(Accelerating Semi-Supervised Learning via Contrastive Learning). This method combines contrastive learning with uncertainty-based selection for performance improvement and accelerates the convergence of SSL algorithms. Contrastive learning initially emphasizes the mutual information between samples as a means to decrease dependence on pseudo-labels. Subsequently, it gradually turns to maximizing the mutual information between classes, aligning with the objective of semi-supervised learning. Uncertainty-based selection provides a robust mechanism for acquiring pseudo-labels. The combination of the contrastive learning module and the uncertainty-based selection module forms a virtuous cycle to improve the performance of the proposed model. Extensive experiments demonstrate that ASCL outperforms state-of-the-art methods in terms of both convergence efficiency and performance. In the experimental scenario where only one label is assigned per class in the CIFAR-10 dataset, the application of ASCL to Pseudo-label, UDA (Unsupervised data Augmentation for Consistency Training), and Fixmatch benefits substantial improvements in classification accuracy. Specifically, the results demonstrate notable improvements in respect of 16.32%, 6.9%, and 24.43% when compared to the original outcomes. Moreover, the required training time is reduced by almost 50%. © 2024, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Conceptual Modeling for Advanced Application Domains 1

引用

丛书名： Lecture Notes in Computer Science

1000年

作者： Shan Wang Katsumi Tanaka Shuigeng Zhou Tok-Wang Ling Jihong Guan Dong-qing Yang Fabio Grandi Eleni E. Mangina Il-Yeol Song Heinrich C. Mayr

来源：评论

学校读者我要写书评

暂无评论

SVQR: A novel secure visual quick response code and its anti-counterfeiting solution

引用

Journal of Information Hiding and Multimedia Signal Processing 2017年第5期8卷 1132-1140页

作者： Liu, Shi-Jian Zhang, Jing Pan, Jeng-Shyang Weng, Cai-Jie School of Information Science and Engineering Fujian University of Technology No3 Xueyuan Road University Town Minhou FuzhouFujian350118 China Key Laboratory of Big Data Mining and Applications of Fujian Province Fujian University of Technology No3 Xueyuan Road University Town Minhou FuzhouFujian350118 China

With the development of information science and increasingly demands for convenient communication, Quick Response (QR) codes are now popularly used all over the world. However, security problem is not considered in the designation of QR code, which makes it unsuitable for application requiring credibility. This paper presents an authentication solution to realize the anti-counterfeiting for message which is encoded following QR code standard. The solution includes a proposed secure and visual improved QR code involving digital signature and watermarking techniques, and a delicate authentication scheme. The effective and efficient of the proposed method are proved by experiments and analyses. © 2017, Ubiquitous International. All rights reserved.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

A Novel Local Search Algorithm Based on Connectivity Method and Vertex Penalty Mechanism for Minimum Weighted Connected Dominating Set Problem

SSRN

引用

SSRN 2024年

作者： Li, Ruizhi He, Jintao Yin, Minghao Hu, Shuli Ding, Nan Jilin University of Finance and Economics Changchun130117 China Northeast Normal University Changchun130117 China Business Big Data Research Center of Jilin Province Changchun130117 China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Changchun130012 China

The minimum weighted connected dominating set problem is a classical NP-hard problem with wide applications in practice. In this paper, an efficient local search algorithm is proposed to solve this problem. In this algorithm, firstly, an initial solution construction method based on greedy randomized adaptive strategy is adopted, which can balance the quality and the diversity of the initial solutions. Second, two new scoring functions, Ascore and Cscore, are proposed to increase the diversity of deleted vertices. Third, a new connectivity method is proposed so that the algorithm no longer relies on the shortest path between two connected components. Fourth, a vertex penalty mechanism is introduced, which helps the algorithm to jump out of the local optimum effectively. Fifth, two scoring functions, Ascore and Cscore, are combined with the vertex penalty mechanism to propose an effective vertex selection method, which helps the algorithm to select suitable vertices to be added to or removed from the current candidate solution. Finally, the propsoed local search algorithm is compared with seven state-of-the-art algorithms on three types of benchmark instances. The experimental results show that the algorithm exhibits better performance on these three types of classical benchmark instances. © 2024, The Authors. All rights reserved.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

A brief overview of kernel methods with prior information

引用

Procedia Computer Science 2022年 199卷 269-275页

作者： Saiji Fu Shiding Sun Xinfeng Wang Dalian Liu School of Economics and Management University of Chinese Academy of Sciences Beijing 100190 China Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing 100190 China School of Mathematical Sciences University of Chinese Academy of Sciences Beijing 100049 China Institute of Mathematics and Physics Beijing Union University Beijing 100101 China Institute of Fundamental and Interdisciplinary Sciences Beijing Union University Beijing 100101 China

With the progress of human society and the development of computer technology, more and more experience has been accu¬mulated, which can serve as prior information in model training. With the assistance of prior information, the performance of some machine learning algorithms has been significantly improved. In this article, we mainly discussed four types of prior information, namely knowledge sets, fuzzy sets, universum data, and privilege information. Specifically, (1) the knowledge sets are constraints composed of domain experience; (2) the fuzzy sets provide the importance of each instance through the fuzzy membership function; (3) the universum data belongs to none of the target classes, but reflects the domain information related to the field of interest; (4) the privileged information can provide more relevant information about training examples, but is not available during the testing phase. In order to illustrate how the prior information is integrated into the kernel methods, the cor¬responding representative models are reviewed in detail, including knowledge-based support vector machine(KSVM), fuzzy support vector machine(FSVM), universum support vector machine(USVM) and privileged support vector machine(SVM+). In addition, this article briefly introduced the most related and advanced research, including the deep learning extensions with prior information. Finally, the current challenge and the future trends of incorporating prior information into machine learning are discussed.

关键词： prior information kernel methods support vector machine deep learning

来源：评论

学校读者我要写书评

暂无评论

Image Forgery Localization with State Space Models

arXiv

引用

arXiv 2024年

作者： Lou, Zijie Cao, Gang Guo, Kun Weng, Shaowei Yu, Lifang School of Computer and Cyber Sciences Communication University of China Beijing100024 China State Key Laboratory of Media Convergence and Communication Communication University of China Beijing100024 China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou350118 China Department of Information Engineering Beijing Institute of Graphic Communication Beijing100026 China

Pixel dependency modeling from tampered images is pivotal for image forgery localization. Current approaches predominantly rely on Convolutional Neural Networks (CNNs) or Transformer-based models, which often either lack sufficient receptive fields or entail significant computational overheads. Recently, State Space Models (SSMs), exemplified by Mamba, have emerged as a promising approach. They not only excel in modeling long-range interactions but also maintain a linear computational complexity. In this paper, we propose LoMa, a novel image forgery localization method that leverages the selective SSMs. Specifically, LoMa initially employs atrous selective scan to traverse the spatial domain and convert the tampered image into ordered patch sequences, and subsequently applies multi-directional state space modeling. In addition, an auxiliary convolutional branch is introduced to enhance local feature extraction. Extensive experimental results validate the superiority of LoMa over CNN-based and Transformer-based state-of-the-arts. To our best knowledge, this is the first image forgery localization model constructed based on the SSM-based model. We aim to establish a baseline and provide valuable insights for the future development of more efficient and effective SSM-based forgery localization models. Code is available at https://***/multimediaFor/LoMa. Copyright © 2024, The Authors. All rights reserved.

关键词： Convolutional neural networks

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：