High-utility itemset mining (HUIM) is an important research topic in the data mining field. Typically, traditional HUIM algorithms must handle the exponential problem of huge search space when the database size or number of distinct items is very large. As an alternative and effective approach, evolutionary computation (EC)-based algorithms have been proposed to solve HUIM problems because they can obtain a set of nearly optimal solutions in limited time. However, it is still time-consuming for EC-based algorithms to find complete high-utility itemsets (HUIs) in transactional databases. To address this problem, we propose an HUIM algorithm based on an improved genetic algorithm (HUIM-IGA). In addition, a neighborhood exploration strategy is proposed to improve search efficiency for HUIs. To reduce missing HUIs, a population diversity maintenance strategy is employed in the proposed HUIM-IGA. An individual repair method is also introduced to reduce invalid combinations for discovering HUIs. In addition, an elite strategy is employed to prevent the loss of HUIs. Experimental results obtained on a set of real-world datasets demonstrate that the proposed algorithm can find complete HUIs in terms of the given minimum utility threshold, and the timeconsuming of HUIM-IGA is relatively lower when mining the same number of HUIs than state-of-the-art EC-based HUIM algorithms.INDEX TERMS Data mining, high-utility itemset mining, genetic algorithm, neighborhood exploration, diversity maintenance. of the Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence, Jiangsu. His major research areas and work are related to computational intelligence, machine learning, bioinformatics, and among others. He published more than 150 articles in journals, conference proceedings, and several books in the above areas.

No abstract

Protein-ligand docking is of great importance to drug design, since it can predict the binding affinity between ligand and protein, and guide the synthesis direction of the lead compounds. Over the past few decades, various docking programs have been developed, some of them employing novel optimization algorithms. However, most of those methods cannot simultaneously achieve both good efficiency and accuracy. Therefore, it is worthwhile to pour the efforts into the development of a docking program with fast speed and high quality of the solutions obtained.The research presented in this paper, based on the docking scheme of Vina, developed a novel docking program called RDPSOVina. The RDPSOVina employed a novel search algorithm but the same scoring function of Vina. It utilizes the random drift particle swarm optimization (RDPSO) algorithm as the global search algorithm, implements the local search with small probability, and applies Markov chain mutation to the particles' personal best positions in order to harvest more potential-candidates. To prove the outstanding docking performance in RDPSOVina, we performed the re-docking and cross-docking experiments on two PDBbind datasets and the Sutherlandcrossdock-set, respectively. The RDPSOVina exhibited superior protein-ligand docking accuracy and better cross-docking prediction with higher operation efficiency than most of the compared methods. The developed RDPSOVina is available at https://github.com/lijin-xing/RDPSOVina.

The goal of image splicing localization is to detect the tampered area in an input image. Deep learning models have shown good performance in such a task, but are generally unable to detect the boundaries of the tampered area well. In this paper, we propose a novel deep learning model for image splicing localization that not only considers local image features, but also extracts global information of images by using a multi-scale guided learning strategy. In addition, the model integrates spatial and channel self-attention mechanisms to focus on extracting important features instead of restraining unimportant or noisy features. The proposed model is trained on the CASIA v2.0 dataset, and its performance is tested on the CASIA v1.0, Columbia Uncompressed, and DSO-1 datasets. Experimental results show that, with the help of the multi-scale guided learning strategy and self-attention mechanisms, the proposed model can locate the tampered area more effectively than the state-of-the-art models.

No abstract