基于关联规则的MODIS影像绿潮检测  

MODIS Images Based on Association Rules Green Tide Monitoring

作　　者：迟丽宁[1] 邵峰晶[1] 王常颖[1] 孙仁诚[1] 

机构地区：[1]青岛大学信息工程学院,山东青岛266071

出　　处：《青岛大学学报（自然科学版）》2012年第2期58-61,共4页Journal of Qingdao University(Natural Science Edition)

基　　金：国家自然科学基金重大专项(91130035);国家自然科学基金(60974085);国家公益性行业科研专项(200905030);海洋沉积与环境地质国家海洋局重点实验室开放基金(MASEG200812);国家海洋局海洋赤潮灾害立体监测技术与应用重点实验室开放基金(MATHAB20120301)

摘　　要：由于缺乏对绿潮灾害的深入认识和有效的监视监测,海域管理部门的决策管理和防治措施还处于被动局面。为解决这一现状,选取青岛附近海域的3景MODIS影像作为实验数据,分析了浒苔的光谱特性并对浒苔进行了特征选择,然后运用关联规则挖掘出浒苔及其光谱之间的关联关系,并使用发现的关联规则对浒苔进行检测,检测结果相比同类研究具有较高的精确度。对提高绿潮研究的科学性和深入性具有重要意义。There is lack of in-depth understanding and effective monitoring of green tides. So the decisionmaking and control measures of the water management department are still in a passive state. In order to change this situation, three MODIS images are selected as experimental data, the features are selected by analyzing spectral characteristics of green tides. The analysis methods include mining, the association be- tween green tides and spectral characteristics by using association rules, detecting the entermorpha by using association rules. The result shows that the discovered association rules are with the higher accuracy compared to the similar studies. The study is of great significance for the further in-depth study of green tide.

关 键 词：绿潮 数据挖掘 关联规则 MODIS 

分 类 号：TP319[自动化与计算机技术—计算机软件与理论] P76[自动化与计算机技术—计算机科学与技术]