A Survey on Clustering based Meteorological Data Mining
International Journal of Grid and Distributed Computing
Data mining is an important tool in meteorological problems solved. Cluster analysis techniques in data mining play an important role in the study of meteorological applications. The research progress of the clustering algorithms in meteorology in recent years is summarized in this paper. First, we give a brief introduction of the principles and characteristics of the clustering algorithms that are commonly used in meteorology. On the other hand, the applications of clustering algorithms in
... g algorithms in meteorology are analyzed, and the relationship between the various clustering algorithms and meteorological applications are summarized. Then we interpret the relationship from the perspectives of algorithms' characteristics and practical applications. Finally, some main research issues and directions of the clustering algorithms in meteorological applications are pointed out. (ii) the data is potentially noisy, (iii) massive quantities of data are available for mining, etc. Common data types in cluster analysis mainly contain interval -scale variables, binary variables, categorical variables, ordinal variables, ratio-scaled variables, variables of mixed types and vector objects. There are some commonly used distance measures, for example, Euclidean distance, Manhattan distance, Minkowski distance, Chebyshev distance, Mahalanobis distance, Hamming distance and correlation coefficient . Different measure methods have different features and advantages. Thus, in a specific meteorological application, combined with the data characteristics, choosing the appropriate clustering algorithm is the premise of successful experiments. research interests mainly include routing protocol and algorithm design, performance evaluation and optimization for wireless ad hoc and sensor networks. He is a member of the IEEE and ACM.