检索结果-内蒙古大学图书馆

Analysis of Grain Storage Loss Based on Decision Tree Algorithm

Procedia Computer Science 2017年 122卷 130-137页

作者： Xueli Liu Bingchan Li Dongqin Shen Jie Cao Bo Mao College of Information Engineering Collaborative Innovation Center for Modern Grain Circulation and Safety Jiangsu Key Laboratory of Grain Big-data Mining Nanjing University of Finance & Economics Nanjing 210023 China School of Electrical and Automation Engineering Jiangsu Maritime Institute Nanjing 211170 China Computer Science and Technology Computer Science and Engineering College Nanjing University of Science and Technology Nanjing 210094 China

Different grain storage factors will cause different degrees of grain loss. In this paper, the data mining method is used to study the loss of grain storage, and the grain loss analysis and forecasting model based on decision tree algorithm is proposed. The paper analyzes and predicts the grain loss caused by different grain storage factors. And the influence of model parameters on model fitting and accuracy is verified by the verification curve. Then the decision tree model is optimized by the method of grid search and cross validation, which improves the prediction accuracy of the decision tree model to analyze the grain loss.

关键词： Decision tree Grid search Cross validation Validation curve Grain storage loss

来源：评论

学校读者我要写书评

暂无评论

Analysis of the grain loss in harvest based on logistic regression

引用

Procedia Computer Science 2017年 122卷 698-705页

作者： Tingkai Huang Bingchan Li Dongqin Shen Jie Cao Bo Mao College of Information Engineering Collaborative Innovation Center for Modern Grain Circulation and Safety Jiangsu Key Laboratory of Grain Big-data Mining Nanjing University of Finance & Economics Nanjing 210023 China School of Electrical and Automation Engineering Jiangsu Maritime Institute Nanjing 211170 China Computer Science and Technology Computer Science and Engineering College Nanjing University of Science and Technology Nanjing 210094 China

In this paper, the grain loss assessment was studied based on logistic regression, and 5400 samples of 31 provinces in our country in the year 2012-2014 were selected, and the 7 typical provinces among them were respectively tested. Using the logistic regression model to predict the loss rate of grain harvesting step, the prediction result is 86.25%. The stochastic gradient descent algorithm is used to optimize the parameters of the model, when the learning_rate is 0.1, the prediction results of grain harvest losses of up to 92.53%, which further improves the prediction accuracy of grain harvest step loss.

关键词： Logistic regression stochastic gradient descent algorithm grain harvest step loss

来源：评论

学校读者我要写书评

暂无评论

Research on knowledge Sharing and Transfer in Remanufacturing engineering Management Based on SECI Model

引用

Frontiers of engineering Management 2016年第2期3卷 136-143页

作者： Ling-ling Zhang Ming-hui Zhao Qiao Wang School of Economics and Management University of Chinese Academy of Sciences Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences

In this paper, an application mode and method of knowledge management in remanufacturing engineering management is established based on Nonaka's SECI model. The relationships between knowledge transfer,knowledge sharing and remanufacturing engineering management are highlighted. It is noticeable that a great deal of knowledge transfer and sharing activities, which can improve the performance of remanufacturing engineering management constantly, are involved in remanufacturing engineering.

关键词： remanufacturing engineering management knowledge transfer and sharing knowledge management

来源：评论

学校读者我要写书评

暂无评论

Security Analysis Model, System Architecture and Relational Model of Enterprise Cloud Services

引用

International Journal of Automation and computing 2016年第6期13卷 574-584页

作者： Dang-Dang Niu Lei Liu Xin Zhang Shuai Lu Zhuang Li College of Computer Science and Technology Jilin University Changchun 130012 China Data Center Consolidation (Beijing) Industrial and Commercial Bank of China Beijing 100096 China College of Mathematics Jilin University Changchun 130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering Jilin University Changchun 130012 China

Cloud computing is one of the fastest growing and popular computer technologies, and there are more and more enterprise services based on the cloud computing. In order to save costs, more and more enterprises and their employees have hired the enterprise cloud services, and put much important information in the cloud gradually. Cloud service systems have become the main targets of malicious attacks. However, the cloud computing technologies are still not perfect, and the management and maintenance of enterprise cloud services are more complex compared to traditional network services of cloud computing. So, enterprise cloud services are more likely to encounter some security problems, and the influenced scale of these security problems is broad. But there are few researches on the security of enterprise cloud services. In this paper, we analyze the software as a service（Saa S） enterprise cloud services and introduce the research status of security problems in cloud computing environment. Combining with the analysis of the characteristics and application architecture of Saa S enterprise cloud services, we propose the security problems analysis model, the analysis system architecture and the relational model. Our researches can support further research of the automatic generation of solutions and guide the deployment of security policies of Saa S enterprise cloud services.

关键词： cloud deployment perfect maintenance likely users bases encounter relational costs

来源：评论

学校读者我要写书评

暂无评论

Laplacian SVM for Learning from Label Proportions

Laplacian SVM for Learning from Label Proportions

引用

IEEE International Conference on data mining Workshops (ICDM Workshops)

作者： Limeng Cui Zhensong Chen Fan Meng Yong Shi School of Computer and Control Engineering UCAS School of Economics and Management UCAS Key Laboratory on Big Data Mining and Knowledge Management CAS

ISBN: (纸本)9781509059119

Proportion-SVM has been deeply studied due to its broad application prospects, such as modeling voting behaviors and spam filtering. However, the geometric information has been widely ignored. Thus, current methods usually show sensitivity to noises. To address these problems, in this paper, we combine the proportion learning framework with Laplacian term. We exploit the advantages of Laplacian term. Extensive experiments show the effectiveness of our method.

关键词： Support vector machines Laplace equations Kernel Training Optimization data models data mining

来源：评论

学校读者我要写书评

暂无评论

DCAR: A Discriminative and Compact Audio Representation for Audio Processing

DCAR: A Discriminative and Compact Audio Representation for ...

引用

作者： Jing, Liping Liu, Bo Choi, Jaeyoung Janin, Adam Bernd, Julia Mahoney, Michael W. Friedland, Gerald Beijing Key Laboratory of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing100044 China College of Information Science and Technology Agricultural University of Hebei Hebei071000 China International Computer Science Institute BerkeleyCA94704 United States Delft University of Technology Delft2628 Netherlands Department of Statistics University of California Berkeley BerkeleyCA94720 United States Department of Electrical Engineering and Computer Sciences University of California Berkeley BerkeleyCA94720 United States Lawrence Livermore National Laboratory LivermoreCA94550 United States

This paper presents a novel two-phase method for audio representation, discriminative and compact audio representation (DCAR), and evaluates its performance at detecting events and scenes in consumer-produced videos. In the first phase of DCAR, each audio track is modeled using a Gaussian mixture model (GMM) that includes several components to capture the variability within that track. The second phase takes into account both global structure and local structure. In this phase, the components are rendered more discriminative and compact by formulating an optimization problem on a Grassmannian manifold. The learned components can effectively represent the structure of audio. Our experiments used the YLI-MED and DCASE Acoustic Scenes datasets. The results show that variants on the proposed DCAR representation consistently outperform four popular audio representations (mv-vector, i-vector, GMM, and HEM-GMM). The advantage is significant for both easier and harder discrimination tasks;we discuss how these performance differences across tasks follow from how each type of model leverages (or does not leverage) the intrinsic structure of the data. © 2017 IEEE.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Path ω-automaton

引用

Journal of Information Hiding and Multimedia Signal Processing 2017年第3期8卷 640-648页

作者： Jiang, Hua Zou, Fumin Lin, Rongde Li, Lingxiang Key Lab of Granular Computing Minnan Normal University ZhangzhouFujian China Beidou Navigation and Smart Traffic Innovation Center of Fujian Province FuzhouFujian China School of Mathematical Science Huaqiao university QuanzhouFujian China Fujian Provincial Key Laboratory of Big Data Mining and Applications FuzhouFujian China School of Electronics and Information Engineering Hunan University of Science and Engineering YongzhouHunan China

Automata theory is an important branch of theoretical computer science. ω-automaton is an important part of automata theory. The judgment standard for the equivalence of two automata is the equivalence of their acceptance language. Acceptance conditions for automata are expressed with state set. This paper tries to use path to express acceptance conditions for ω-automaton that is convenient for judging the automatons equivalence property and transforming between different types of automata. With the help of Path ω-automaton, Muller automaton is transformed into Büchi automaton. Compared with the existing algorithm, the state scale of Büchi automaton has been reduced and the problem of state space explosion has been relieved. The research findings in this paper contribute to enrich the existing ω-automaton theory and provide a new idea for ω-automaton theory and application research. © 2017.

关键词： Automata theory

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

What and how affect influence the consequence of product trial 20

What and how affect influence the consequence of product tri...

引用

20th Pacific Asia Conference on Information Systems, PACIS 2016

作者： Sun, Kai Zuo, Meiyun Kong, Dong Key Laboratory of Data Engineering and Knowledge Engineering School of Business Renmin University of China Beijing China Research Institute of Smart Aged Care School of Information National Academy of Development and Strategy Renmin University of China Beijing China

ISBN: (纸本)9789860491029

IT product trial is an important method to promote consumers' attitude toward IT product. Affect is one of the most essential factors and components in determining consumers' attitude. However, previous studies pay more attention to the affective response to trial, which measure the holistic feeling about product trial experience. Affect in product trial is complex and multipartite that different parts may have different influence on consumers' attitude. Therefore, we build the Affective Response Framework to divide consumers' affect into affective response to product, affective response to behaviour, and affective response to environment. And then we analyse the relationship between three components of affective response and consumers' attitude. In order to test the hypothesis, we launch a field study of new IT product trial (an electroencephalogram product) among 205 college students. Results reveal that affective response to product and behaviour have positive influence on attitude toward product;affective response to behaviour and environment have positive influence on attitude toward trial.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Authoring tool of sharable question items based on QTI specification for e-learning assessment

Authoring tool of sharable question items based on QTI speci...

引用

2017第二届亚太计算智能与信息技术学术会议 (APCIIT 2017)

作者： Tien-Wen Sung You-Te Lu Chia-Jung Lee Yuan-Hsun Liao Chyun-Chyi Chen Fujian Provincial Key Laboratory of Big Data Mining and Applications College of Information Science and EngineeringFujian University of Technology Department of Information and Communication Southern Taiwan University of Science and Technology Department of Information Management Tainan University of Technology Department of Management Information System Far East University

Although online examination for e-learning is widely realized nowadays. However the production of question bank is time-consuming. This paper proposes an assessment authoring tool to assist teachers in creating reusable test question items. The items conforms to the IMS Question and Test Interoperability(QTI) specification and are easy to share,reuse,exchange,and access across distributed learning management systems(LMS). System design and implementation were presented in this paper for sharing and contributing development experiences to related works.

关键词： System IMS Authoring tool of sharable question items based on QTI specification for e-learning assessment

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：