Quantum inspired elephant swarm intelligence for frequent item-sets mining

This paper introduces two novel quantum-inspired swarm intelligence approaches, namely Quantum-inspired Discrete Elephant Herding Optimization (QDEHO) and Quantum-inspired Discrete Elephant Water Search Algorithm (QDESWSA), for solving discrete optimization problems. Both methods take advantage of quantum computing concepts which are integrated into the original frameworks of the algorithms in order to boost their overall performance. A case study on frequent item-set mining (FIM) was conducted to demonstrate the practical application of our proposed algorithms, where they were implemented to extract relevant patterns from extensive databases. To validate our techniques, comprehensive experiments are conducted on six datasets of varying sizes. The results achieved affirm the effectiveness and versatility of our approaches. Additionally, a comparative study with relevant state of the art algorithms such as Bat algorithm (BAT) and Whale Optimization Algorithm (WOA) is performed, revealing the superiority of QDEHO and QDESWSA across most datasets.