检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:魏小亭[1] 蒲越[1] 李国东[1,2] WEI Xiao-ting PU Yue Li Guo-dong(Collge of Applied Mathematics,Xinjiang University Of Finance and Economics, Urumqi City 830012, China Research center of Xinjiang Social and Economic Statistics, Xinjiang University of Finance and Economics, Urumqi City 830012, China)
机构地区:[1]新疆财经大学应用数学学院,新疆乌鲁木齐830012 [2]新疆财经大学新疆社会经济统计研究中心,新疆乌鲁木齐830012
出 处:《吉林化工学院学报》2017年第7期80-84,共5页Journal of Jilin Institute of Chemical Technology
基 金:国家自然科学基金(11461063);国家社科基金(14BTJ021);国家教育部人文社会科学基金(13YJAZH040);新疆维吾尔自治区高校科研计划项目(XJEDU2013I26)
摘 要:冰雹是气象的主要灾害之一.冰雹云的发生发展具有突发性,移动迅速,生命史短等特点,这些特点使人工预报冰雹非常困难.本文利用FCM聚类算法与新疆维吾尔自治区阿克苏地区的雹云反射率图像相结合.首先将冰雹反射率图像由RGB转换到灰度空间,然后计算各强度的面积所占比例,根据冰雹图像的测度特征,计算得到各强度均值、方差、偏度和峰度,根据这四项指标作为FCM聚类算法样本数据库.利用此聚类算法对已有样本进行测试,检验结果表明:FCM聚类算法能够较好的识别降雹和非降雹,判别误差较小,具有一定的参考价值.Hail is one of the major meteorological disasters. The occurrence and development of hail cloud is sudden,moving quickly,the characteristics of the short history of life,these characteristics make artificial hail forecast is very difficult.The reflection of hail cloud in Akesu area FCM clustering algorithm and the Xinjiang Uygur Autonomous Region rate image combination.Firstly,hail reflectance image conversion from RGB to gray space.And then calculate the strength of the area proportion,according to the measurement characteristics of hail image,calculated the strength of mean,variance,skewness and kurtosis,according to the four indexes as the FCM clustering algorithm sample database. The existing samples were measured by using the clustering algorithm The test results show that the FCM clustering algorithm is able to identify hail and hail,which has a certain reference value.
分 类 号:TP391.4[自动化与计算机技术—计算机应用技术]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.222