HHUIM：一种新的启发式高效用项集挖掘方法

针对基于启发式的高效用项集挖掘算法在挖掘过程中可能丢失大量项集的问题，提出一种新的启发式高效用项集挖掘算法HHUIM。HHUIM利用哈里斯鹰优化算法进行种群的更新，能够有效减少项集的丢失。提出并设计了鹰的替换策略，解决了搜索空间较大的问题，降低了适应度函数值低于最小效用阈值的鹰的数量。此外，提出存储回溯策略，可有效防止算法收敛过快达到局部最优。大量的实验表明，所提算法优于目前最先进的启发式高效用项集挖掘算法。

HHUIM: new heuristic high utility itemset mining method

In response to the problem of potentially losing a large number of itemsets during the mining process of heuristic-based high utility itemset mining algorithms, this paper proposed a new heuristic-based high utility itemset mining algorithm, called HHUIM. HHUIM utilized the Harris hawk optimization algorithm for population update, effectively reducing the loss of itemsets. This paper also introduced and designed a hawk replacement strategy to solve the problem of a large search space by decreasing the number of hawks with fitness values below the minimum utility threshold. Furthermore, this paper proposed a storage backtracking strategy to prevent premature convergence to local optima. Extensive experiments demonstrate that the proposed algorithm outperforms the state-of-the-art heuristic-based high utility itemset mining algorithms.