| 英文标题 | Association rule mining algorithm using improving treap with interpolation algorithm in large database |
| 作者英文名 | Xin Chunhua, Guo Yanguang, Lu Xiaobo |
| 机构英文名 | Dept. of Computer Technology & Information Management,Inner Mongolia Agricultural University,Baotou Inner Mongolia 014109,China |
| 英文摘要 | The explosive growth of information makes the process of data mining and analysis more difficult. It is very difficult for the common association rules mining algorithm to evaluate and discover the relationship between variables in large database under the premise of short running time and low correlation degree. This paper presented an algorithm for mining association rules in large databases based on improved treap. Firstly, the algorithm calculated the priority of each variable in the database. Then, it constructed the treap data structure by the interpolation algorithm to improve build-treap program in the priority model. Finally, it found the relationship of the database by traversing the program and generateRule program. After the stability analysis of the proposed algorithm, the simulation results show that the proposed algorithm can mine the <i>O</i>(<i>n</i> log <i>n</i>) times and <i>O</i>(<i>n</i><sup>2</sup>) times in the worst-case analysis and the best-case analysis, respectively. The algorithm can complete the task of variable relational mining in a large database with low correlation degree in a short time, which is much better than the traditional Apriori algorithm and FP growth algorithm. |
| 英文关键词 | improved treap algorithm; interpolation algorithm; large data base; priority model; association rules |