| 摘要: |
| 传统的评价方法不能处理带有模糊信息的城市空气质量的评价问题。基于结构风险最小化原则建立了带有模糊信息的支持向量分类模型和算法,在此基础上提出基于模糊支持向量机的城市空气质量评价方法;根据空气中的总悬浮颗粒物、二氧化硫、二氧化氮、空气综合污染指数4个指标,对我国50个主要城市2003年空气质量进行了综合评价,选择10个城市的评价结果进行了测试,结果表明:根据2003年数据采用本方法得到的邢台、张家口和沧州的空气污染指数与河北省环保专家提供的数据误差小于0.1;西宁、银川、乌鲁木齐、汕头、南京、大连、武汉的综合空气污染指数与国家环保总局提供的数据误差均小于0.5。 |
| 关键词: 支持向量机,模糊规划,空气质量,评价 |
| DOI：10.11841/j.issn.1007-4333.2006.05.133 |
| 投稿时间：2005-11-22 |
| 基金项目:国家自然科学基金资助项目(10371131) |
|
| Fuzzy support vector machine method for city air quality assessment |
|
|
|
| Abstract: |
| The traditional evaluating methods can not deal with the evaluation problem of city atmosphere quality with fuzzy information.Based on the principle of structural risk minimization,authors constructed a support vector classification model,as well as its algorithm with fuzzy information and proposed a new city atmosphere quality evaluating method based on the fuzzy support vector machine.According to the four indexes,the total amount of suspending granules,sulfur dioxide,nitrogen dioxide and atmosphere synthetical pollution index,the atmosphere qualities of 50 main cities in China in the year 2003 were estimated. |
| Key words: support vector machine,fuzzy programming,air quality,assessment |
