面向欠发达地区大数据产业发展能力分析的网络化方法研究

doi:10.11959/j.issn.1000-436x.2017290

Abstract

Abstract:

Traditional evaluation methods of industrial development ability were mostly lack of objectivity.An evaluation model was proposed by using a BP neural network based on entropy weight.Evaluation index system of big data industry development ability in underdeveloped areas was established.Taking Guizhou industrial development data as samples,entropy weight method was used to determine expected output and compared with the actual output .The experimental results show that the proposed entropy weight-BP evaluation model can optimize error of using single BP network and improve the accuracy and objectivity of evaluation.

Key words: big data industry, development ability, BP model, entropy method

CLC Number:

Jun-xin SHEN,Ying-qian CHEN. Research on network analysis method for development ability of big data industry in underdeveloped area[J]. Journal on Communications, 2017, 38(12): 153-159.

Figures/Tables 11

References 15

[1]	杨倩倩, 路海娟, 朝乐门 . 大数据产业发展中存在的主要矛盾分析[J]. 情报理论与实践, 2016,39(10): 11-15.
	YANG Q Q , LU H J , CHAO L M . Analysis of major contradictions in development of big data industry[J]. Information Studies:Theory ＆Application, 2016,39(10): 11-15.
[2]	王伟玲 . 大数据产业的战略价值研究与思考[J]. 技术经济与管理研究, 2015(1): 117-120.
	WANG W L . Research and thinking on the strategic value of the big data industry[J]. Research on Technology Economy and Management, 2015(1): 117-120.
[3]	赵黎明, 刘猛 . 基于熵权TOPSIS的区域科技创新能力评价模型及实证研究[J]. 天津大学学报(社会科学版), 2014(5): 385-390.
	ZHAO L M , LIU M . Evaluation and empirical study on regional technology innovation ability based on TOPSIS method[J]. Journal of Tianjin University(Social Science Edition), 2014(5): 385-390.
[4]	赵正 . 建筑业企业技术创新能力评价研究[D]. 郑州:河南理工大学, 2011.
	ZHAO Z . Research on technological innovation capability of construction enterprises evaluation[D]. Zhengzhou:Henan Polytechnic University, 2011.
[5]	FU X H . Evaluation and trend analysis on the competitiveness of information industry in six provinces:based on factor analysis of panel data[J]. Journal of Xichang College, 2016.
[6]	LI X Z , GAO Y L , ZHAO H L . Comparative research on the IOT industry competitiveness of eastern,central and western China —a comprehensive evaluation based on TOPSIS and GRA[C]// IEEE International Conference on Grey Systems and Intelligent Services. 2015: 187-193.
[7]	LI X G , LU J , WANG H ,et al. Evaluation of application level of internet of things for coal mine[J]. Industry＆Mine Automation, 2015.
[8]	HONG Y R . The study of smart city evaluation based on the ANP-TOPSIS method[J]. Journal of Industrial Technological Economics, 2014.
[9]	ZHENG Y , CHEN Y . Research on evaluation model of university teachers' teaching quality based on BP neural network[J]. Journal of Chongqing University of Technology, 2015.
[10]	汪忠, 袁丹, 江资斌 ,等. 基于BP神经网络的社会企业动态能力评价研究[J]. 中国地质大学学报(社会科学版), 2016(1): 153-161.
	WANG Z , YUAN D , JIANG Z B ,et al. Evaluation of dynamic ability based on BP neural network in the social enterprise[J]. Journal of China University of Geosciences(Social Sciences Edition), 2016(1): 153-161.
[11]	邹凯, 包明林 . 基于灰色关联理论和BP神经网络的智慧城市发展潜力评价[J]. 科技进步与对策, 2015(17): 123-128.
	ZOU K , BAO M L . Evaluation of smart city develop potential based on gray relation theory and BP neural network[J]. Science ＆Technology Progress and Policy, 2015(17): 123-128.
[12]	吴志军, 王璐, 史荣 . 基于改进BP神经网络的ATM系统信息安全评估方法[J]. 通信学报, 2011,32(2): 150-158.
	WU Z J , WANG L , SHI R . Approach of information security assessment for ATM system based on improved BP model of artificial neural network[J]. Journal on Communications, 2011,32(2): 150-158.
[13]	石书彪, 陈焕新, 李冠男 ,等. 基于改进BP网络的冷水机组故障诊断[J]. 制冷学报, 2015,36(6): 34-39.
	SHI S B , CHEN H X , LI G N . Research on fault diagnosis of chillers based on improved BP network[J]. Journal of Refrigeration, 2015,36(6): 34-39.
[14]	郭俊华, 程聪慧, 何军 ,等. 基于熵权法的科技人才项目绩效评价研究--以上海市“浦江人才”计划为例[J]. 科技进步与对策, 2015(19): 119-125.
	GUO J H , CHENG C H , HE J ,et al. Research on performance evaluation for talents project based on entropy weight method-a case study on“Pujiang talents project”in Shanghai municipal[J]. Science＆Technology Progress and Policy, 2015(19): 119-125.
[15]	吴冲, 万翔宇 . 基于改进熵权法的区间直觉模糊 TOPSIS 方法[J]. 运筹与管理, 2014(5): 42-47.
	WU C , WAN X Y . Extended TOPSIS with interval-valued intuitionistic fuzzy information based on advanced entropy-weighted method[J]. Operations Research and Management Science, 2014 (5): 42-47.

Metrics

Recommended 0

No Suggested Reading articles found!

一级指标	二级指标
	经济水平 X₁
发展基础能力	基础设施 X₂
	产业结构 X₃
	社会发展 X₄
	财政支持能力 S₁
产业发展支持能力	税收支持能力 S₂
	法律支持能力 S₃
	规划组织能力 S₄
系统协调与整合能力	协调能力 S₅
	整合能力 S₆
	信息产业规模水平 X₅
信息化及信息产业总体水平	信息社会发展指数 X₆
	信息消费指数 X₇
	通信基础设施建设情况 X₈
信息基础设施支撑能力	互联网用户发展情况 X₉
	电话用户发展情况 X₁₀
科技与人才	科研技术水平 X₁₁
	人才队伍建设 X₁₂

编号	二级指标	可量化指标	2006年	2007年	2008年	…	2014年
X₁	经济水平	财政总收入/亿元	0.000	0.064	0.134	…	1.000
X₂	基础设施	用水普及率	0.814	0.886	0.000	…	1.000
X₃	产业结构	第三产业占比	0.000	0.492	0.631	…	0.354
X₄	社会发展	城镇居民人均消费性支出/元	0.000	0.108	0.179	…	1.000
X₅	信息产业规模水平	电子信息产业主营业务收入/亿元	0.000	0.066	0.137	…	1.000
X₆	信息社会发展指数	信息社会发展指数	0.000	0.034	0.091	…	1.000
X₇	信息消费系数	信息消费系数/万元	0.000	0.141	0.270	…	1.000
X₈	通信基础设施建设情况	光缆总长度/万千米	0.000	0.016	0.015	…	1.000
X₉	互联网用户发展情况	年末互联网宽带接入用户/万户	0.000	0.028	0.055	…	1.000
X₁₀	电话用户发展情况	年末电话用户/万户	0.000	0.095	0.241	…	1.000
X₁₁	科研技术水平	专利授权数/件	0.000	0.045	0.045	…	1.000
X₁₂	人才队伍建设	普通高等学校在校学生数/万人	0.000	0.085	0.193	…	1.000

编号	二级指标	2006年	2007年	2008年	…	2014年
S₁	财政支持能力	0.662	0.676	0.689	…	0.776
S₂	税收支持能力	0.591	0.602	0.614	…	0.692
S₃	法律支持能力	0.656	0.656	0.656	…	0.656
S₄	规划组织能力	0.642	0.655	0.668	…	0.752
S₅	协调能力	0.556	0.568	0.579	…	0.652
S₆	整合能力	0.679	0.693	0.707	…	0.796

综合评价值	产业发展能力等级
0~0.6	不适合发展
0.61~0.75	较弱
0.76~0.89	中等
0.90~1	较强

指标	权重	指标	权重
X₁	0.055 4	X₁₀	0.052 9
X₂	0.057 6	X₁₁	0.056 2
X₃	0.057 7	X₁₂	0.056 5
X₄	0.056 1	S₁	0.053 8
X₅	0.053 5	S₂	0.056 3
X₆	0.056 8	S₃	0.054 7
X₇	0.055 5	S₄	0.053 4
X₈	0.054 5	S₅	0.056 5
X₉	0.056 6	S₆	0.055 9

Research on network analysis method for development ability of big data industry in underdeveloped area

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 11

References 15

Related Articles 8

Metrics

Recommended 0

年份	发展能力值
2006	0.046 9
2007	0.141 8
2008	0.253 3
2009	0.312 0
2010	0.467 1
2011	0.615 2
2012	0.740 0
2013	0.874 5
2014	0.962 7

年份	期望值	输出值	残差	发展能力等级
2006	0.046 9	0.062 1	0.015 2
2007	0.141 8	0.151 8	0.010 0
2008	0.253 3	0.253 2	0.000 1	不适合发展
2009	0.312 0	0.322 9	0.010 9
2010	0.467 1	0.476 9	0.009 8
2011	0.615 2	0.611 8	0.003 4	较弱
2012	0.740 0	0.723 4	0.016 6	较弱
2013	0.874 5	0.876 5	0.002 0	中等
2014	0.962 7	0.968 4	0.005 7	较强

[1]	Xiaoyu XU, Hao HU, Hongqi ZHANG, Yuling LIU. Random routing defense method based on deep deterministic policy gradient [J]. Journal on Communications, 2021, 42(6): 41-51.
[2]	Wenchen HE, Shaoyong GUO, Xuesong QIU, Liandong CHEN, Suxiang ZHANG. Node selection method in federated learning based on deep reinforcement learning [J]. Journal on Communications, 2021, 42(6): 62-71.
[3]	Chaonong XU,Jianxiong WU,Yongjun XU. Highly reliable access algorithm for PD-NOMA based IoT with delay guarantee [J]. Journal on Communications, 2020, 41(9): 210-221.
[4]	Ming TANG,Xi CHEN. Multi-dimensional adaptive transmission technique for shortto-medium reach optical fiber communication system [J]. Journal on Communications, 2019, 40(11): 156-170.
[5]	Zhou-wen TAN,Hong-li LIU,Jie ZHAN,Zi-ji MA,Shu-gang LIU. Adaptive noise mitigation based on peak estimate and feedback compensation in power line communication [J]. Journal on Communications, 2017, 38(12): 86-97.
[6]	Yong-hong KUO,Ru-quan WANG,Jian CHEN. Reconstruction algorithm based on multi-reference frames hypothesis optimization for compressive sensing [J]. Journal on Communications, 2017, 38(12): 1-9.
[7]	Ya-hui WANG,Hong-feng KUANG,Li-dong ZHU. Capacity analysis of the MEO satellite constellation [J]. Journal on Communications, 2017, 38(Z1): 193-199.
[8]	Jie HAN,Tao ZHANG,Huan-huan WANG,Dong-fang REN. Communication emitter individual identification based on 3D-Hibert energy spectrum and multi-scale fractal features [J]. Journal on Communications, 2017, 38(4): 99-109.