基于SOM神经网络的区域复合生态系统健康评估  

Health Assessment of Regional Complex Ecosystem Based on Self-Organizing Map Neural Network

作　　者：樊国敬[1] 田秀华[2] 

机构地区：[1]赣南师范大学历史文化与旅游学院,江西赣州341000 [2]安徽财经大学商学院,安徽蚌埠233041

出　　处：《统计与决策》2017年第11期85-89,共5页Statistics & Decision

基　　金：江西省高校高水平学科社会学建设资助项目(GNSDSHX2017086)

摘　　要：文章基于SOM神经网络,分析与评估了我国四大经济区域复合生态系统健康等级。空气质量、住房消费和节能降耗对复合生态系统健康评估影响力最大;中国区域复合生态系统主要处在健康和亚健康状态,江苏复合生态系统健康值排名第一,处于健康状态;天津经济子系统和海南自然子系统排名第一,健康值都超过0.8,处在很健康的状态;北京社会子系统健康指数排名第一;东部地区生态系统健康总指数最高,社会、经济和自然健康指数排名都是第一,也都超过0.6,处在健康等级。Based on Self-organizing Map （SOM） neural network, this paper makes assessment of the health grade of regional complex ecosystem of the four economic regions. Conclusions are as follows： firstly, the most influential factors for the health as- sessment of complex ecosystem are air quality, housing consumption, energy-saving and cost-reducing. Secondly, China＇ s region- al complex ecosystem is mainly in health and sub-health status. The health value of Jiangsu＇ s complex ecosystem ranks first, in health status; Tianjin＇ s economic subsystem and Hainan＇ s natural subsystem ranks first, and their health value is all above 0.8, in the state of good health; the health index of Beijing＇ s social subsystem ranks first. Lastly, the combined health index of the eastern region＇ s ecosystem is the highest, and the social, economic and natural health indices all rank first, above 0.6, in health state.

关 键 词：SOM神经网络 区域复合生态系统 健康评估 

分 类 号：F205[经济管理—国民经济]