| Summary: | Mining high utility itemsets (HUI) is an interesting research problem in the field of data mining and knowledge discovery. Recently, bio-inspired computing has attracted considerable attention, leading to the development of new algorithms for mining HUIs. These algorithms have shown good performance in terms of efficiency, but are not guaranteed to find all HUIs in a database. That is, the quality is comparatively poor in terms of the number of discovered HUIs. To solve this problem, a new framework based on bioinspired algorithms is proposed. This approach adjusts the standard roadmap of bio-inspired algorithms by proportionally selecting discovered HUIs as the target values of the next population, rather than maintaining the current optimal values in the next population. Thus, the diversity within populations can be improved. Three new algorithms based on the Bio-HUI framework are developed using the genetic algorithm, particle swarm optimization, and the bat algorithm, respectively. Extensive tests conducted on publicly available datasets show that the proposed algorithms outperform existing state-of-the-art algorithms in terms of efficiency, quality of results, and convergence speed.
|
|---|
