Please wait a minute...
Advanced Search
数据分析与知识发现  2017, Vol. 1 Issue (12): 49-62     https://doi.org/10.11925/infotech.2096-3467.2017.0786
  研究论文 本期目录 | 过刊浏览 | 高级检索 |
图书馆数字资源聚合质量预测模型构建*——基于改进遗传算法和BP神经网络
闫晶1,2(), 毕强1, 李洁1, 王福1
1吉林大学管理学院 长春 130022
2东北电力大学经济管理学院 吉林 132012
Construction of Aggregation Quality Predicting Model for Digital Resource in Library ——Based on Improved Genetic Algorithm and BP Neural Network
Yan Jing1,2(), Bi Qiang1, Li Jie1, Wang Fu1
1School of Management, Jilin University, Changchun 130022, China
2School of Economic Management, Northeast Electric Power University, Jilin 132012, China
全文: PDF (1280 KB)   HTML ( 2
输出: BibTeX | EndNote (RIS)      
摘要 

目的】针对图书馆数字资源聚合质量评价要求, 基于遗传算法对BP神经网络进行改进, 进而构建更为优化的图书馆数字资源聚合质量预测模型。【方法】利用遗传算法计算简单、对待求解问题依赖小、并发线程计算速度快等优点, 通过广义海明距离定义种群提高种群多样性, 进行种群选择、交叉、变异操作, 求解初始权重和阈值; 将改进的遗传算法引入BP神经网络, 通过权重和阈值的不断调整, 快速收敛至适应度设定值, 最终实现预测结果的进一步优化。【结果】采用MATLAB R2014a平台进行仿真实验, 预测结果平均误差2.74E-04, 同实际数据误差小, 模型精度较高。程序运行总时长18.56秒, 且三步就收敛到误差目标, 模型收敛速度快, 相较单一的遗传算法和BP算法具有更高的预测精度和效率。【局限】样本数据质量有待提高; 实验中未采用Train的其他快速训练函数进行训练时间和预测精度对比; 种群数量因计算复杂性而受限。【结论】模型能够对图书馆数字资源聚合质量做出高效、客观预测, 应用前景和延展性较好, 能有效运用于图书馆数字资源聚合质量评价结果检验、大样本评价以及大样本预测领域。

服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
闫晶
毕强
李洁
王福
关键词 数字资源聚合质量模型构建遗传算法BP神经网络    
Abstract

[Objective] This paper proposes a model to predict the quality of library digital resource aggregation with the help of improved BP neural network based on genetic algorithm. [Methods] The genetic algorithm is simple in computing, less dependent on the problems to be solved, and could quickly calculate concurrent threads. First, we obtained the initial weight and threshold with increased population diversity,selection, crossover and variation. Second, we introduced the improved genetic algorithm to the BP neural network, which rapidly reached the fitness setting level by constantly adjusting the weight and threshold values. Finally, we further optimized the performance of the prediction model. [Results] We used MATLAB R2014a platform to examine the proposed model and the average number of prediction errors was 2.74E-04, which was smaller than the actual data. It took the program 18.56 seconds or three steps to finish the task. The prediction accuracy and efficiency of the proposed model was better than the single genetic or BP algorithms. [Limitations] The quality of sample data needs to be improved. We did not compare our training time and prediction accuracy with those of other quick training functions. The population numbers are limited due to computational complexity. [Conclusions] The proposed model could predict the quality of digital resource aggregation efficiently and objectively.

Key wordsDigital Resource    Aggregation Quality    Model Construction    Genetic Algorithm    BP Neural Network
收稿日期: 2017-08-08      出版日期: 2017-12-29
ZTFLH:  G25 TP393  
基金资助:*本文系国家自然科学基金项目“语义网络环境下数字资源多维度聚合与可视化研究”(项目编号: 71273111)的研究成果之一
引用本文:   
闫晶, 毕强, 李洁, 王福. 图书馆数字资源聚合质量预测模型构建*——基于改进遗传算法和BP神经网络[J]. 数据分析与知识发现, 2017, 1(12): 49-62.
Yan Jing,Bi Qiang,Li Jie,Wang Fu. Construction of Aggregation Quality Predicting Model for Digital Resource in Library ——Based on Improved Genetic Algorithm and BP Neural Network. Data Analysis and Knowledge Discovery, 2017, 1(12): 49-62.
链接本文:  
https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.2096-3467.2017.0786      或      https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/Y2017/V1/I12/49
  BP神经网络模型
  遗传算法步骤
来源 数字图书馆 网址
国外 1.Library of Congress https://www.loc.gov
2.Elsevier Library http://www.sciencedirect.com
3.EmeraldPublish http://emeraldgrouppublishing.com
4.Cambridge University
Library
http://www.lib.cam.ac.uk
5.California State Library http://www.library.ca.gov
国内 6.国家图书馆 http://www.nlc.cn
7.知网 http://www.cnki.net
8.万方 http://www.wanfangdata.com.cn
9.吉林大学图书馆 http://lib.jlu.edu.cn
10.广州图书馆 http://www.gzlib.gov.cn
  国内外数字图书馆样本
编号 X3 X4 X13 X16 X20 X21 X22
1 30 54 100.00% 5.96% 0.003 29 4.74
2 43 42 100.00% 5.63% 0.002 31 2.72
3 38 39 100.00% 4.35% 0.002 8 4.16
4 39 38 80.00% 3.98% 0.002 48 4.08
5 47 40 100.00% 2.61% 0.002 42 4.15
6 49 60 100.00% 7.68% 0.001 54 4.98
7 30 51 100.00% 6.72% 0.001 18 4.24
8 81 30 100.00% 6.53% 0.003 20 4.03
9 30 31 66.67% 3.62% 0.003 19 3.45
10 74 34 100.00% 6.68% 0.001 17 3.37
说明 以10个文献
为样本估计
以10个文献
为样本估计
结合数字图书馆官方
数据和用户自主发布
资源抽样估计
Post随机检索词10个为样本估计 以链接关系为边,
以资源站为节点
度大于10的核心
子网节点数量
待测评数字
图书馆节点
接近中心度
  客观指标基础数据表
编号 X1 X2 X3 X4 X5 X6 X7 X8 X9 X10 X11 X12 X13 输出
1 2.61 2.61 2.61 3.48 2.61 1.74 2.61 2.61 1.74 2.61 2.61 3.48 3.48 3.48
2 2.63 2.63 2.63 2.63 3.51 2.63 1.75 2.63 2.63 3.51 1.75 0.88 3.51 2.63
3 2.59 3.45 2.59 2.59 3.45 2.59 3.45 3.45 2.59 2.59 2.59 2.59 3.45 2.59
4 2.56 2.56 2.56 2.56 2.56 2.56 2.56 1.71 2.56 3.42 2.56 2.56 2.56 3.42
5 2.64 2.64 2.64 2.64 3.52 2.64 1.76 2.64 2.64 3.52 2.64 2.64 2.64 2.64
6 3.49 3.49 2.62 3.49 2.62 2.62 3.49 3.49 3.49 2.62 2.62 3.49 3.49 3.49
7 4.35 3.48 2.61 3.48 3.48 2.61 4.35 3.48 2.61 3.48 3.48 3.48 3.48 4.35
8 4.35 2.61 3.48 2.61 3.48 3.48 3.48 2.61 2.61 3.48 3.48 2.61 3.48 3.48
9 3.48 2.61 2.61 2.61 3.48 2.61 1.74 2.61 2.61 3.48 2.61 2.61 1.74 2.61
10 2.61 2.61 3.48 2.61 2.61 3.48 2.61 3.48 2.61 2.61 3.48 2.61 3.48 2.61
编号 X14 X15 X16 X17 X18 X19 X20 X21 X22 X23 X24 X25 X26 输出
1 1.74 3.48 3.48 3.48 3.48 3.48 3.48 2.61 3.48 3.48 2.61 3.48 2.61 3.48
2 1.75 3.51 2.63 2.63 0.88 1.75 2.63 2.63 1.75 3.51 1.75 1.75 1.75 2.63
3 2.59 2.59 2.59 3.45 2.59 3.45 2.59 2.59 3.45 3.45 3.45 2.59 3.45 2.59
4 2.56 3.42 2.56 2.56 3.42 2.56 3.42 3.42 2.56 2.56 3.42 2.56 3.42 3.42
5 2.64 2.64 1.76 2.64 2.64 2.64 2.64 2.64 2.64 2.64 2.64 2.64 2.64 2.64
6 3.49 3.49 3.49 3.49 3.49 2.62 2.62 3.49 3.49 2.62 3.49 2.62 3.49 3.49
7 3.48 2.61 3.48 3.48 3.48 2.61 2.61 2.61 3.48 3.48 3.48 3.48 2.61 4.35
8 3.48 2.61 3.48 3.48 2.61 2.61 3.48 2.61 2.61 3.48 2.61 3.48 2.61 3.48
9 2.61 2.61 2.61 2.61 2.61 2.61 3.48 2.61 2.61 3.48 2.61 3.48 2.61 2.61
10 2.61 2.61 3.48 2.61 2.61 2.61 1.74 2.61 2.61 2.61 3.48 2.61 2.61 2.61
  样本数据表
  GA2BP图书馆数字资源聚合质量预测模型
  GA2BP模型算法框架
输入参数 输入值 输入参数 输入值
输入层节点数 26 学习效率 0.9
隐含层节点数 17 动态参数 0.7
输出层节点数 1 允许误差 0.00001
进化代数 80 交叉概率 0.3
迭代次数 100 变异、选择概率 0.1
  模型参数输入数据
  模型训练过程
样本
编号
实际
预测
误差 样本
编号
实际
预测
误差
1 3.48 3.4631 -1.31E-03 5 2.64 2.6154 2.42E-04
2 2.63 2.6637 5.12E-04 6 3.49 3.4453 0.91E-03
3 2.59 2.5165 3.47E-04 7 4.35 4.3212 -2.13E-04
4 3.42 3.4132 6.25E-04 8 3.48 3.4452 -1.43E-03
  GA2BP模型训练样本输出
  GA2BP模型训练误差
  GA2BP模型训练迭代次数
  误差进化曲线
  训练性能曲线
(注: Best与Goal重合。)
  训练状态曲线
模型 样本编号 实际值 预测值 误差 平均误差
GA2BP 9 2.61 2.6076 3.12E-04 2.74E-04
10 2.61 2.6077 2.35E-04
GA 9 2.61 2.6215 1.15E-02 1.14E-02
10 2.61 2.6212 1.12E-02
BP 9 2.61 2.6154 5.43E-03 4.57E-03
10 2.61 2.6137 3.70E-03
  三种不同模型检测样本输出结果对比
  GA2BP同GA、BP预测结果对比
[1] 毕强, 王传清, 李洁. 基于语义的数字资源超网络聚合研究[J]. 情报科学, 2015, 33(3): 8-12.
[1] (Bi Qiang, Wang Chuanqing, Li Jie.Exploration of In-depth Aggregation of Digital Resources Supernetworks Based on Semantics[J]. Information Science, 2015, 33(3): 8-12.)
[2] Garibay C, Gutiérrez H, Figueroa A.Evaluation of a Digital Library by Means of Quality Function Deployment (QFD) and the Kano Model[J]. The Journal of Academic Librarianship, 2010, 36(2): 125-132.
doi: 10.1016/j.acalib.2010.01.002
[3] Heradio R, Cabrerizo F J, Fernández-Amorós D, et al.A Fuzzy Linguistic Model to Evaluate the Quality of Library 2.0 Functionalities[J]. International Journal of Information Management, 2013, 33(4): 642-654.
doi: 10.1016/j.ijinfomgt.2013.04.001
[4] 贾洁, 彭奇志. 基于BP神经网络的图书馆电子资源质量评价研究[J]. 图书情报工作, 2010, 54(21): 84-87.
[4] (Jia Jie, Peng Qizhi.Research on the Quality Evaluation of Library Electronic Resources Based on BP Neural Network[J]. Library and Information Service, 2010, 54(21): 84-87.)
[5] 张秀华, 辛江美. 基于粗糙集和BP神经网络的复合图书馆馆藏质量评价研究[J]. 情报理论与实践, 2009, 32(11): 107-111.
[5] (Zhang Xiuhua, Xin Jiangmei.Research on the Evaluation of Hybrid Library Collection Quality Based on Rough Set and BP Neural Network[J]. Information Studies: Theory & Application, 2009, 32(11): 107-111.)
[6] 陈莺. 基于遗传算法的BP神经网络在高校图书馆流通服务质量评价中的应用研究[J]. 情报探索, 2014(10): 12-15.
doi: 10.3969/j.issn.1005-8095.2014.10.003
[6] (Chen Ying.Study on Applications of Genetic Algorithm- based BP Neural Network in University Library Circulation Service Quality Evaluation[J]. Information Research, 2014 (10): 12-15.)
doi: 10.3969/j.issn.1005-8095.2014.10.003
[7] Werbos P J.From Backpropagation to Neurocontrol[C]// Proceedings of the International Conference on Neural Networks, Fuzzy Systems, Evolutionary Computing, and Virtual Reality. 1996: 476.
[8] Bagley J D.The Behavior of Adaptive Systems Which Employ Genetic and Correlation Algorithms[D]. Ann Arbor, MI, USA: University of Michigan, 1967.
[9] 付晓明, 王福林, 尚家杰. 基于多子代遗传算法优化BP神经网络[J]. 计算机仿真, 2016, 33(3): 258-263.
doi: 10.3969/j.issn.1006-9348.2016.03.057
[9] (Fu Xiaoming, Wang Fulin, Shang Jiajie.Optimized BP Neural Network Algorithm Based on Multi-Child Genetic Algorithm[J]. Computer Simulation, 2016, 33(3): 258-263.)
doi: 10.3969/j.issn.1006-9348.2016.03.057
[10] Bhattacharya U.Digital Information Resources and Digital Information Literacy: A Symbiotic Approach[M]. Inflibnet Centre, 2007.
[11] 王菲菲, 邱均平. 信息计量视角下的数字文献资源语义化模型研究[J]. 情报资料工作, 2015, 36(4): 62-69.
[11] (Wang Feifei, Qiu Junping.Analysis of Digital Document Resource Semantic Model Under the Perspective of Informetrics[J]. Information and Documentation Services, 2015, 36(4): 62-69.)
[12] 高劲松, 程娅, 梁艳琪. 基于关联数据的图书馆数字资源语义互联研究[J]. 情报科学, 2017, 35(1): 8-13.
[12] (Gao Jinsong, Cheng Ya, Liang Yanqi.Semantic Interconnection Model of Library Digital Resources Based on Linked Data[J]. Information Science, 2017, 35(1): 8-13.
[13] 李洁. 基于SNA的馆藏数字资源知识聚合可视化研究[D].长春: 吉林大学, 2016.
[13] (Li Jie.Study on Knowledge Aggregation of Digital Resources Based on SNA[D]. Changchun: Jilin University, 2016.)
[14] 曾群, 刘昊, 李瑞婻. 基于知识关联理论的数字图书馆信息资源聚合研究[J]. 图书馆学研究, 2016(23): 36-41.
[14] (Zeng Qun, Liu Hao, Li Ruinan.Research on Digital Library Information Resources Aggregation Based on Knowledge Relevance Theory[J]. Research on Library Science, 2016 (23): 36-41.)
[15] 鞠建伟, 梁花侠. 高校图书馆服务用户满意度的BP神经网络模型的建立[J]. 情报杂志, 2004, 23(8): 103-104.
doi: 10.3969/j.issn.1002-1965.2004.08.042
[15] (Ju Jianwei, Liang Huaxia.The Application of BP Model in CS Evaluation of University Library[J]. Journal of Intelligence, 2004, 23(8): 103-104.)
doi: 10.3969/j.issn.1002-1965.2004.08.042
[16] 林仕高, 欧元贤. BP神经网络学习参数优化研究[J]. 微计算机信息, 2010, 26(16): 199-200.
doi: 10.3969/j.issn.2095-6835.2010.16.080
[16] (Lin Shigao, Ou Yuanxian.Research of the Optimization of the Learning Parameters in BP Neural Network[J]. Microcomputer Information, 2010, 26(16): 199-200.)
doi: 10.3969/j.issn.2095-6835.2010.16.080
[17] 孔国利, 张璐璐. 遗传算法的广义回归神经网络建模方法[J]. 计算机工程与设计, 2017, 38(2): 488-493.
[17] (Kong Guoli, Zhang Lulu.Generalized Regression Neural Network Modeling Method Based on Genetic Algorithm[J]. Computer Engineering and Design, 2017, 38(2): 488-493.)
[18] 朱春媚, 莫鸿强. 一类适应度函数的遗传算法编码[J]. 计算机应用, 2017, 37(7): 1972-1976, 1998.
doi: 10.11772/j.issn.1001-9081.2017.07.1972
[18] (Zhu Chunmei, Mo Hongqiang.Encoding of Genetic Algorithm for a Class of Fitness Functions[J]. Journal of Computer Applications, 2017, 37(7): 1972-1976, 1998.)
doi: 10.11772/j.issn.1001-9081.2017.07.1972
[19] 何士龙, 苏子林. 论优化BP神经网络的一种改进遗传算法[J]. 科技情报开发与经济, 2011, 21(1): 119-121.
doi: 10.3969/j.issn.1005-6033.2011.01.053
[19] (He Shilong, Su Zilin.An Improved Genetic Algorithm for Optimizing BP (Back Propagation) Neural Network[J]. Sci-Tech Information Development & Economy, 2011, 21(1): 119-121.)
doi: 10.3969/j.issn.1005-6033.2011.01.053
[20] 张秀华, 高伟. 基于GA-BPNN组合模型的图书馆绩效评价及实证研究[J]. 情报学报, 2012, 31(8): 890-896.
doi: 10.3772/j.issn.1000-0135.2012.08.014
[20] (Zhang Xiuhua, Gao Wei.Library Performance Evaluation and an Empirical Study Based on GA-BPNN Combinatorial Model[J]. Journal of the China Society for Scientific and Technical Information, 2012, 31(8): 890-896.)
doi: 10.3772/j.issn.1000-0135.2012.08.014
[21] 邰丽君, 胡如夫, 赵韩, 等. 改进遗传神经网络算法在销售预测中的应用研究[J]. 现代图书情报技术, 2012(1): 63-67.
[21] (Tai Lijun, Hu Rufu, Zhao Han, et al.Application Research of Improved Genetic Neural Network Algorithm in Sales Forecast[J]. New Technology of Library and Information Service, 2012(1): 63-67.)
[22] 罗长寿, 周丽英. 改进遗传算法的神经网络模型研究[J]. 情报杂志, 2005, 24(5): 65-66.
doi: 10.3969/j.issn.1002-1965.2005.05.024
[22] (Luo Changshou, Zhou Liying.Research on the Neural Network Model for Improving Genetic Algorithm[J]. Journal of Intelligence, 2005, 24(5): 65-66.)
doi: 10.3969/j.issn.1002-1965.2005.05.024
[23] Tani A, Candela L, Castelli D.Dealing with Metadata Quality: The Legacy of Digital Library Efforts[J]. Information Processing & Management, 2013, 49(6): 1194-1205.
doi: 10.1016/j.ipm.2013.05.003
[24] Cummings J.Full-Text Aggregation: An Examination of Metadata Accuracy and Implications for Resource Sharing[J]. Serials Review, 2003, 29(1): 11-15.
doi: 10.1016/S0098-7913(02)00256-3
[25] Tejeda-Lorente A, Porcel C, Peis E, et al.A Quality Based Recommender System to Disseminate Information in a University Digital Library[J]. Information Sciences, 2014, 261: 52-69.
doi: 10.1016/j.ins.2013.10.036
[26] Kokkinos P, Varvarigos E A.Scheduling Efficiency of Resource Information Aggregation in Grid Networks[J]. Future Generation Computer Systems, 2012, 28(1): 9-23.
doi: 10.1016/j.future.2011.06.008
[27] 肖奎, 罗保山, 吴天吉. 一种限定领域的网络文档资源质量评价方法——以维基百科为例[J]. 情报理论与实践, 2016, 39(12): 120-123.
doi: 10.16353/j.cnki.1000-7490.2016.12.022
[27] (Xiao Kui, Luo Baoshan, Wu Tianji.An Approach for the Quality Evaluation of Web Document Resources in Specific Domains: A Case Study of Wikipedia[J]. Information Studies: Theory & Application, 2016, 39(12): 120-123.)
doi: 10.16353/j.cnki.1000-7490.2016.12.022
[28] 邱均平, 董克. 引文网络中文献深度聚合方法与实证研究——以WOS数据库中XML研究论文为例[J]. 中国图书馆学报, 2013, 39(2): 111-120.
[28] (Qiu Junping, Dong Ke.Methods and Empirical Research on Deep Integration of Literature in Citation Network: Case Study on XML Research Literature from WOS[J]. Journal of Library Science in China, 2013, 39(2): 111-120.)
[29] 张博, 乔欢. 协同知识生产社区的内容质量评估模型研究——以维基百科为例[J]. 现代情报, 2015, 35(10): 17-22.
doi: 10.3969/j.issn.1008-0821.2015.10.004
[29] (Zhang Bo, Qiao Huan.Evaluating the Quality of Content in Online Collaborative Knowledge Production Communities[J]. Journal of Modern Information, 2015, 35(10): 17-22.)
doi: 10.3969/j.issn.1008-0821.2015.10.004
[30] 赵文轩, 李春旺. 关联数据质量评价方法研究述评[J]. 情报理论与实践, 2016, 39(2): 134-138.
doi: 10.16353/j.cnki.1000-7490.2016.02.028
[30] (Zhao Wenxuan, Li Chunwang.Research on Quality Evaluation Method for Correlation Data[J]. Information Studies: Theory & Application, 2016, 39(2): 134-138.)
doi: 10.16353/j.cnki.1000-7490.2016.02.028
[31] 王振蒙, 姜恩波. 关联书目数据质量评估框架构建与实证评估[J]. 图书情报工作, 2016, 60(15): 108-115.
doi: 10.13266/j.issn.0252-3116.2016.15.015
[31] (Wang Zhenmeng, Jiang Enbo.Building and Empirical Assessment of Quality Assessment Framework of Linked Bibliographic Data[J]. Library and Information Service, 2016, 60(15): 108-115.)
doi: 10.13266/j.issn.0252-3116.2016.15.015
[32] 王福. 数字图书馆资源聚合质量影响因素研究[J]. 情报理论与实践, 2016, 39(12): 86-90, 113.
doi: 10.16353/j.cnki.1000-7490.2016.12.016
[32] (Wang Fu.Research on the Factors Affecting the Quality of Digital Library Resources Aggregation[J]. Information Studies: Theory & Application, 2016, 39(12): 86-90, 113.)
doi: 10.16353/j.cnki.1000-7490.2016.12.016
[33] 刘宏哲, 须德. 基于本体的语义相似度和相关度计算研究综述[J]. 计算机科学, 2012, 39(2): 8-13.
doi: 10.3969/j.issn.1002-137X.2012.02.002
[33] (Liu Hongzhe, Xu De.Ontology Based Semantic Similarity and Relatedness Measures Review[J]. Computer Science, 2012, 39(2): 8-13.)
doi: 10.3969/j.issn.1002-137X.2012.02.002
[34] Yeung C A, Gibbins N, Shadbolt N.Understanding the Semantics of Ambiguous Tags in Folksonomies[C]// Proceedings of the 1st International Conference on Emergent Semantics and Ontology Evolution. 2007.
[35] 吴贝贝, 夏翠娟. 关联书目数据模型比较研究[J]. 图书馆杂志, 2015, 34(5): 71-79.
[35] (Wu Beibei, Xia Cuijuan.Comparative Study of Linked Bibliographic Data Models in Libraries[J]. Library Journal, 2015, 34(5): 71-79.)
[36] 孙琛琛, 申德荣, 寇月, 等. 面向关联数据的联合式实体识别方法[J]. 计算机学报, 2015, 38(9): 1739-1754.
doi: 10.11897/SP.J.1016.2015.01739
[36] (Sun Chenchen, Shen Derong, Kou Yue, et al.A Related Data Oriented Joint Entity Resolution Approach[J]. Chinese Journal of Computers, 2015, 38(9): 1739-1754.)
doi: 10.11897/SP.J.1016.2015.01739
[37] 姜恩波, 王振蒙. 关联数据质量评估研究综述[J]. 情报杂志, 2016, 35(4): 171-176.
doi: 10.3969/j.issn.1002-1965.2016.04.031
[37] (Jiang Enbo, Wang Zhenmeng.The Quality Evaluation of Linked Data: An Overview[J]. Journal of Intelligence, 2016, 35(4): 171-176.)
doi: 10.3969/j.issn.1002-1965.2016.04.031
[38] 唐一之, 张仲义. 基于本体的知识聚合策略[J]. 吉首大学学报: 自然科学版, 2008, 29(2): 72-76.
doi: 10.3969/j.issn.1007-2985.2008.02.020
[38] (Tang Yizhi, Zhang Zhongyi.Ontology-Based Study on Knowledge Aggregation Strategy[J]. Journal of Jishou University: Natural Science Edition, 2008, 29(2): 72-76.)
doi: 10.3969/j.issn.1007-2985.2008.02.020
[39] 黄莺. 元数据质量的定量评估方法综述[J]. 图书情报工作, 2013, 57(4): 143-148.
doi: 10.7536/j.jssn.0252-3116.2013.04.025
[39] (Huang Ying.Review on Quantitative Assessment of Metadata Quality[J]. Library and Information Service, 2013, 57(4): 143-148.)
doi: 10.7536/j.jssn.0252-3116.2013.04.025
[40] 欧石燕, 胡珊, 张帅. 本体与关联数据驱动的图书馆信息资源语义整合方法及其测评[J]. 图书情报工作, 2014, 58(2): 5-13.
doi: 10.13266/j.issn.0252-3116.2014.02.001
[40] (Ou Shiyan, Hu Shan, Zhang Shuai.An Ontology & Linked Data Driven Semantic Integration Method of Library Information Resources and Its Evaluation[J]. Library and Information Service, 2014, 58(2): 5-13.)
doi: 10.13266/j.issn.0252-3116.2014.02.001
[41] 邱均平, 方国平. 高校图书馆语义化馆藏资源深度聚合模式及其应用研究[J]. 图书馆学研究, 2014(21): 64-71.
[41] (Qiu Junping, Fang Guoping.Research on the Depth Aggregation Model and Its Application of the Semantic Collection in University Libraries[J]. Research on Library Science, 2014 (21): 64-71.)
[42] 王晰巍, 赵丹, 张长亮, 等. 基于社会网络的新媒体网络舆情信息传播研究——以反腐倡廉话题为例[J]. 情报杂志, 2016, 35(3): 103-110.
[42] (Wang Xiwei, Zhao Dan, Zhang Changliang, et al.Research on Public Opinion Information Dissemination of New Media Network Based on Social Network - Taking the Anti-corrruption Campaign as an Example[J]. Journal of Information, 2016, 35(3): 103-110.)
[43] 苏新宁. 大数据时代数字图书馆面临的机遇和挑战[J]. 中国图书馆学报, 2015, 41(6): 4-12.
doi: 10.13530/j.cnki.jlis.150028
[43] (Su Xinning.Opportunities and Challenges Faced by Digital Libraries in the Era of Big Data[J]. Journal of Library Science in China, 2015, 41(6): 4-12.)
doi: 10.13530/j.cnki.jlis.150028
[44] 饶浩, 陈海媚. 主成分分析与BP神经网络在微博舆情预判中的应用[J]. 现代情报, 2016, 36(7): 58-62.
doi: 10.3969/j.issn.1008-0821.2016.07.011
[44] (Rao Hao, Chen Haimei.Application of Micro-blog Public Opinion Prediction Based on Combination of Principal Component Analysis and BP Neural Network[J]. Journal of Modern Information, 2016, 36(7): 58-62.)
doi: 10.3969/j.issn.1008-0821.2016.07.011
[45] 徐恺英, 常改, 邢天亮. 基于SVM神经网络的高校科研能力评价模型构建[J]. 图书情报工作, 2011, 55(22): 52-55.
[45] (Xu Kaiying, Chang Gai, Xing Tianliang.Evaluation Model of Universtiy Scientific Research Ability Based on SVM Neural Network[J]. Library and Information Service, 2011, 55(22): 52-55.)
[46] 于海东. 社会网络中的知识扩散路径优化设计[J]. 情报科学, 2014, 32(7): 114-118.
[46] (Yu Haidong.Optimization of Knowledge Diffusion Route in Social Network[J]. Information Science, 2014, 32(7): 114-118.)
[47] 杜戈, 韩增奇, 李宁霞, 等. 基于神经网络和遗传算法的信息传输安全风险度评估模型[J]. 情报杂志, 2010, 29(S1): 207-209.
doi: 10.3969/j.issn.1002-1965.2010.z1.067
[47] (Du Ge, Han Zengqi, Li Ningxia, et al.An Assessment Model of Information Transmission Security Risk Based on Neural Network and Genetic Algorithm[J]. Journal of Intelligence, 2010, 29(S1): 207-209.)
doi: 10.3969/j.issn.1002-1965.2010.z1.067
[48] 徐承爱, 林伟, 肖红. 一种基于加权海明距离的自适应遗传算法[J]. 华南师范大学学报: 自然科学版, 2015, 47(6): 121-127.
doi: 10.6054/j.jscnun.2015.05.003
[48] (Xu Cheng’ai, Lin Wei, Xiao Hong.An Adaptive Genetic Algorithm Based on Weighted Hamming Distance[J]. Journal of South China Normal University: Natural Science Edition, 2015, 47(6): 121-127.)
doi: 10.6054/j.jscnun.2015.05.003
[49] 危志明, 陈琪. 基于遗传神经网络的图书馆流通量预测[J]. 情报探索, 2009(10): 5-7.
doi: 10.3969/j.issn.1005-8095.2009.10.002
[49] (Wei Zhiming, Chen Qi.Research on Prediction of Library Circulation Based on Genetic Neural Network[J]. Information Research, 2009 (10): 5-7.)
doi: 10.3969/j.issn.1005-8095.2009.10.002
[50] 黄光球, 汪晓海, 刘兆明. 基于神经网络-交叉变异-FFT的组合加解密方法[J]. 情报杂志, 2006, 25(10): 5-7.
[50] (Huang Guangqiu, Wang Xiaohai, Liu Zhaoming.A Combining Encryption and Decryption Algorithm Based on Neural Networks Cross-and-Variation and FFT[J]. Journal of Intelligence, 2006, 25(10): 5-7.)
[51] 张修文, 付佳, 孙达辰, 等. 基于遗传算法优化的BPNN读者满足率评价模型[J]. 中华医学图书情报杂志, 2013, 22(10): 68-70.
doi: 10.3969/j.issn.1671-3982.2013.10.018
[51] (Zhang Xiuwen, Fu Jia, Sun Dachen, et al.Genetic Algorithm-based Optimal Assessment Model of BPNN Readers’ Satisfaction Rate[J]. Chinese Journal of Medical Library and Information Science, 2013, 22(10): 68-70.)
doi: 10.3969/j.issn.1671-3982.2013.10.018
[52] MathWorks. MATLAB R2014a [CP]. 2014.
[53] 赵伟, 张秀华. 基于遗传神经网络的图书馆成效评估研究[J]. 情报理论与实践, 2013, 36(12): 94-98.
[53] (Zhao Wei, Zhang Xihua.Evaluation on Library Effectiveness Based on Genetic Neural Network[J]. Information Studies: Theory & Application, 2013, 36(12): 94-98.)
[1] 程铁军, 王曼, 黄宝凤, 冯兰萍. 基于CEEMDAN-BP模型的突发事件网络舆情预测研究*[J]. 数据分析与知识发现, 2021, 5(11): 59-67.
[2] 吴彦文, 蔡秋亭, 刘智, 邓云泽. 融合多源数据和场景相似度计算的数字资源推荐研究*[J]. 数据分析与知识发现, 2021, 5(11): 114-123.
[3] 徐晨飞, 叶海影, 包平. 基于深度学习的方志物产资料实体自动识别模型构建研究*[J]. 数据分析与知识发现, 2020, 4(8): 86-97.
[4] 何振宇,董祥祥,朱庆华. 基于用户使用行为视角的百度百科词条分类研究*[J]. 数据分析与知识发现, 2019, 3(6): 117-122.
[5] 武玉英, 孙平, 何喜军, 蒋国瑞. 新能源领域专利转让加权网络中主体间技术交易机会预测*[J]. 数据分析与知识发现, 2018, 2(11): 73-79.
[6] 潘竹虹,萧德洪. 一种支持双栈及高速网络的数字资源利用分析系统数据过滤方法[J]. 现代图书情报技术, 2016, 32(3): 90-96.
[7] 高劲松, 程娅, 梁艳琪. 面向关联数据集的本体匹配方法研究[J]. 现代图书情报技术, 2015, 31(6): 33-40.
[8] 吴振新, 王玉菊, 付鸿鹄, 李春旺, 刘建华. 构建可信赖的数字资源长期保存系统摄入工作流[J]. 现代图书情报技术, 2015, 31(3): 1-7.
[9] 顾嘉伟, 王胜清, 赵丹群, 陈文广. 公共文化数字资源云服务的一种中心化身份认证模式[J]. 现代图书情报技术, 2015, 31(2): 64-71.
[10] 路永和, 梁明辉. 遗传算法在改进文本特征提取方法中的应用[J]. 现代图书情报技术, 2014, 30(4): 48-57.
[11] 马宁宁, 李超, 曲云鹏. 面向数字资源长期保存的自动过时风险管理系统的设计与实现[J]. 现代图书情报技术, 2013, (4): 69-76.
[12] 邰丽君, 胡如夫, 赵韩, 陈曹维. 改进遗传神经网络算法在销售预测中的应用研究[J]. 现代图书情报技术, 2012, 28(1): 63-67.
[13] 张晗, 韩爽, 白星, 崔雷. 利用遗传算法确定医学文献的研究热点[J]. 现代图书情报技术, 2011, 27(3): 57-61.
[14] 钱红丽 马自卫 李高虎. 基于开源环境下的本地数字资源系统的设计与技术实现[J]. 现代图书情报技术, 2010, 26(7/8): 102-109.
[15] 高建秀 吴振新 孙硕. 云存储在数字资源长期保存中的应用探讨[J]. 现代图书情报技术, 2010, 26(6): 1-6.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 2015 《数据分析与知识发现》编辑部
地址:北京市海淀区中关村北四环西路33号 邮编:100190
电话/传真:(010)82626611-6626,82624938
E-mail:jishu@mail.las.ac.cn