传统的挖掘频繁项集的并行算法存在数据偏移、通信量大、同步次数较多和扫描数据库次数较多等问题。
There were problems in traditional parallel algorithms for mining frequent itemsets more or less: data deviation, large scale communication, frequent synchronization and scanning database.
理论分析与数值实验表明,该算法较列扫描并行算法优越。
The theoretical analysis and numerical experiment show that the new algorithm is better than the line-scan algorithm.
应用推荐