基于粗糙粒计算的数据挖掘算法研究模式识别与智能系统专业论文.docxVIP

II II Abstract Abstract: Data sets in the world are expanding by leaps and bounds. Mining hidden within the data, information or knowledge of modeling, is becoming increasingly important. It makes the data mining has become a hot research issue. The study finds that the indiscernibility information often exists in the data, many data mining algorithms can not adapt to the processing of these data. To deal with indiscernibility problem, a lot of data mining algorithms combine with rough set theory and granular computing theory. Research mainly includes the following aspects: A single-dimension hierarchical granulated attribute reduction algorithm. In handling continuous information attribute reduction, neighborhood granulation conditions are not same. Distance metric as a standard to measure the approximate relationship of different dimensions of distance calculated using the same approximate threshold, will inevitably lead to error on the classification accuracy. A single-dimension hierarchical granulated attribute reduction algorithm constructs neighborhood system in the same threshold condition, and uses hierarchical granulated relationship to calculate the classification accuracy. Experiments show that, the algorithm still has better attribute reduction effect in high classification accuracy. Rough K-means clustering algorithm based on imbalanced degree of cluster. Past rough K-means algorithm and its improved method, focus on the boundary of the object indiscernibility and the differences of data points between clusters, not concerning about differences of the data distribution in a cluster. Imbalance degree can effectively reflect importance of the data object in a cluster with distance to the mean center. Simulation analysis of UCI data show that the clustering algorithm can make inner-cluster more compact, more inter-cluster separation. Improved the imbalance degree of cluster. Not only the distance, but also some intensive areas can make an influence on the