检索结果-内蒙古大学图书馆

International Conference on Sensors, Measurement and Intelligent Materials (ICSMIM 2012)

作者： Ma, Qingyun Wang, Yong Wang, Ying Guangdong Univ Technol Fac Comp Sci Guangzhou Guangdong Peoples R China

ISBN: (纸本)9783037856529

In today's knowledge economy era, knowledge has become an important resource for social development. How to effectively manage knowledge has become the contemporary an important research direction. Medical Literature is the main carrier of medical knowledge, how to make good use of medical literature to become the key to the development of Chinese medicine. Although there are large numbers of medical literature, but penetrates its content to be actually irregular, the literature data lacks has the systematic analysis to make uniform, so that the application value relative reduces largely. Knowledge map as a timely, efficient, and visual knowledge navigation and management tools will be introduced to the medical information service management system, the urgent need to improve the level of medical information, the development of new drugs. In this paper, the use of the som algorithm knowledge mapping the pharmaceutical literature, it mainly includes single literature knowledge map generation and extensive literature knowledge map generated. First uses the GHsom algorithm construction single literature the knowledge map, then by the Esom algorithm, the single literature knowledge map integration with other knowledge map, finally there will produce the global knowledge map

关键词： Medical literature som algorithm knowledge map

来源：评论

学校读者我要写书评

暂无评论

The construction of fabric grading model based on som algorithm

The construction of fabric grading model based on SOM algori...

引用

International Conference on Intelligent Transportation, Big Data and Smart City (ICITBS)

作者： Lin, Weibin Miao, Zhifang Binzhou Polytech Binzhou 256603 Peoples R China

ISBN: (纸本)9781509004645

In the traditional textile field, the mechanization automation has been popularized, the enterprise is faced with the challenge of the consumer to the fabric quality. With the rapid development of computer, the application of artificial intelligence in fabric grading is more and more widely. This paper is based on the som algorithm to construct the evaluation model of the fabric. It can improve the efficiency of the complex type. To provide a reliable mathematical model and verification for the screening of fabrics in the textile industry and enterprises to improve their efficiency.

关键词： som algorithm Fabric grading Mathematical model Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Emotion Recognition Model based on som algorithm

Emotion Recognition Model based on SOM Algorithm

引用

International Conference on Smart City and Systems Engineering (ICSCSE)

作者： Liao, Yi Jiang, Youyi Xian Shiyou Univ Dept Mus Xian 710065 Peoples R China Xian Univ Sci & Technol Coll Geomat Xian 710054 Peoples R China

ISBN: (纸本)9781509055302

The use of computer technology to the music of the understanding and analysis of the music has become a hot spot in the field of music technology research. This paper is on the computer field of music and emotional understanding using som algorithm to classify the characteristics of music itself, and to train the computer automatic recognition. Thus a model of music emotion recognition based on som algorithm is established. Providing a new method and reference is for the automatic recognition of the emotion of music.

关键词： som algorithm music emotion automatic recognition emotion recognition

来源：评论

学校读者我要写书评

暂无评论

Study of College Human Resources Data Mining Based on the som algorithm

Study of College Human Resources Data Mining Based on the SO...

引用

Asia-Pacific Conference on Information Processing (APCIP 2009)

作者： Huang, Yan Tianjin Univ Technol & Educ Informat Technol & Engn Coll Tianjin Peoples R China

ISBN: (纸本)9780769536996

The decisive factor of the comprehensive strength of a college is the integrated intrinsic qualifications of its personnel. Its human resources management needs a technology to discover the valuable knowledge, identify the human developing stratagem and provide the support for decision. Base on the human resources data of two colleges in Tianjin, after data pretreatment, such as data integration, data clean, data transformation and data reduction, this paper finished clustering analysis applying the som algorithm, realized information visualization. In the process the algorithm is carefully chosen, the fitting number of input and output layer node is identified. After training and verification, the result is approved by the experts of management. It can represent correspondingly the 4 kinds of personnel-service and other, administration and teaching assistant, teaching and research. It can differentiate the personnel both in teaching and research, which is the distinct character of human resource in colleges. The data mining result presents the correct character and existing problem in college human resources management. The result will be the guidance rule on the employment, training and upgrading of the personnel in the college, providing some support to the decision of human resources management strategy of college as well.

关键词： Human Resources Data Mining Clustering Analysis Data Pretreatment som algorithm

来源：评论

学校读者我要写书评

暂无评论

The construction of fabric grading model based on som algorithm

The construction of fabric grading model based on SOM algori...

引用

International Conference on Intelligent Transportation, Big Data and Smart City

作者： Weibin Lin Zhifang Miao Binzhou Polytech. Binzhou China

ISBN: (纸本)9781509004652

关键词： som algorithm Fabric grading Mathematical model Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Study of College Human Resources Data Mining Based on the som algorithm

Study of College Human Resources Data Mining Based on the SO...

引用

2009 Asia-Pacific Conference on Information Processing

作者： Yan Huang Information Technology and Engineering College Tianjin University of Technology and Education Tianjin,China

The decisive factor of the comprehensive strength of a college is the integrated intrinsic qualifications of its *** human resources management needs a technology to discover the valuable knowledge,identify the human developing stratagem and provide the support for *** on the human resources data of two colleges in Tianjin,after data pretreatment,such as data integration,data clean,data transformation and data reduction,this paper finished clustering analysis applying the som algorithm,realized information *** the process the algorithm is carefully chosen,the fitting number of input and output layer node is *** training and verification,the result is approved by the experts of *** can represent correspondingly the 4 kinds of personnel-service and other,administration and teaching assistant,teaching and *** can differentiate the personnel both in teaching and research,which is the distinct character of human resource in *** data mining result presents the correct character and existing problem in college human resources *** result will be the guidance rule on the employment,training and upgrading of the personnel in the college,providing some support to the decision of human resources management strategy of college as well.

关键词： component Human Resources Data Mining Clustering Analysis Data Pretreatment som algorithm

来源：评论

学校读者我要写书评

暂无评论

Empirical Research on Financial Risk Identification of Chinese Listed Companies Based on som Neural Network Model

Empirical Research on Financial Risk Identification of Chine...

引用

第五届（2013）金融风险与公司金融国际研讨会

作者： LI Guangrong NIU Xiuhong Management School China University of Mining & Technology (Beijing)

ISBN: (纸本)9787894370631

This paper aims at applying Self-organizing Feature Map neural network algorithm on the research of Chinese listed company's financial risk identification and finally obtains good empirical results by taking 100 companies in China's Shanghai and Shenzhen stock markets from 2010 to 2011 as study samples. The results show that the Self-organizing Feature Map neural network algorithm is an appropriate method to identificate the financial risk of Chinese listed company. The analysis of empirical results is consistent with the actual situation.

关键词： financial risk listed company neural network som algorithm

来源：评论

学校读者我要写书评

暂无评论

How to use the Kohonen algorithm to simultaneously analyze individuals and modalities in a survey

引用

NEUROCOMPUTING 2005年第1期63卷 193-207页

作者： Cottrell, M Letrémy, P Univ Paris 01 SAMOS MATISSE CNRSUMR 8595 F-75634 Paris 13 France

The Kohonen algorithm (som, Self-Organization and Associative Memory, Springer Series in Information Sciences, vol. 8, Springer, Berlin, 1984;Self-Organizing Maps, Springer Series in Information Science, vol. 30, Springer, Berlin, 1995) is a very powerful tool for data analysis. It was originally designed to model organized connections between some biological neural networks. It was also immediately considered as a very good algorithm to realize vectorial quantization, and at the same time pertinent classification, with nice properties for visualization. If the individuals are described by quantitative variables (ratios, frequencies, measurements. amounts, etc.), the straightforward application of the original algorithm leads to build code vectors and to associate to each of them the class of all the individuals which are more similar to this code-vector than to the others. But, in case of individuals described by categorical (qualitative) variables having a finite number of modalities (like in a survey), it is necessary to define a specific algorithm. In this paper, we present a new algorithm inspired by the som algorithm, which provides a simultaneous classification of the individuals and of their modalities. (C) 2004 Elsevier B.V. All rights reserved.

关键词： survey qualitative variables categorical variables correspondence analysis som algorithm

来源：评论

学校读者我要写书评

暂无评论

Application of the self-organizing feature map algorithm in facial image morphing

引用

NEURAL PROCESSING LETTERS 2001年第1期14卷 35-47页

作者： Su, MC Liu, IC Natl Cent Univ Dept Comp Sci & Informat Engn Chungli Taiwan Tamkang Univ Dept Elect Engn Taipei Taiwan

A new facial image morphing algorithm based on the Kohonen self-organizing feature map (som) algorithm is proposed to generate a smooth 2D transformation that reflects anchor point correspondences. Using only a 2D face image and a small number of anchor points, we show that the proposed morphing algorithm provides a powerful mechanism for processing facial expressions.

关键词： animation facial expression feature map image morphing image warping som algorithm

来源：评论

学校读者我要写书评

暂无评论

A healing mechanism to improve the topological preserving property of feature maps

引用

IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS 2002年第4期E85D卷 735-743页

作者： Su, MC Chou, CH Chang, HT Natl Cent Univ Dept Comp Sci & Informat Engn Taipei Taiwan Tamkang Univ Dept Elect Engn Taipei Taiwan

Recently feature maps have been applied to various problem domains, The success of sonic of these applications critically depends on whether feature maps are topologically ordered, Several different approaches have been proposed to improve the conventional self-organizing feature map (som) algorithm. However, these approaches do not guarantee that a topologically-ordered feature map can be formed at the end of a simulation, Therefore, the trial-and-error procedure still dominates the procedure of forming feature maps. In this paper. we propose a healing mechanism to repair feature maps that are not well topologically ordered. The healed map is then further fine-tuned by the conventional som algorithm with a small learning rate and a small-sized neighborhood set so as to improve the accuracy of the map, Two data sets were tested tu illustrate the performance of the proposed method.

关键词： feature maps som algorithm topological property

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：