Differential evolution (DE) is a very effective stochastic optimization algorithm based on population for solving various real-world problems. The quality of solutions to these problems is mainly determined by the combination of mutation strategies and their parameters in DE. However, in the process of solving these problems, the population diversity and local search ability will gradually deteriorate. Therefore, we propose a multi-population differential evolution (MUDE) algorithm with a uniform local search to balance exploitation and exploration. With MUDE, the population is divided into multiple subpopulations with different population sizes, which perform different mutation strategies according to the evolution ratio, i.e., DE/rand/1, DE/current-to-rand/1, and DE/current-to-pbest/1. To improve the diversity of the population, the information is migrated between subpopulations by the soft-island model. Furthermore, the local search ability is improved by way of the uniform local search. As a result, the proposed MUDE maintains exploitation and exploration capabilities throughout the process. MUDE is extensively evaluated on 25 functions of the CEC 2005 benchmark. The comparison results show that the MUDE algorithm is very competitive with other DE variants and optimization algorithms in generating efficient solutions.

Deep neural networks (DNNs) have famously been applied in various ordinary duties. However, DNNs are sensitive to adversarial attacks which, by adding imperceptible perturbation samples to an original image, can easily alter the output. In state-of-the-art white-box attack methods, perturbation samples can successfully fool DNNs through the network gradient. In addition, they generate perturbation samples by only considering the sign information of the gradient and by dropping the magnitude. Accordingly, gradients of different magnitudes may adopt the same sign to construct perturbation samples, resulting in inefficiency. Unfortunately, it is often impractical to acquire the gradient in real-world scenarios. Consequently, we propose a self-adaptive approximated-gradient-simulation method for black-box adversarial attacks (SAGM) to generate efficient perturbation samples. Our proposed method uses knowledge-based differential evolution to simulate gradients and the self-adaptive momentum gradient to generate adversarial samples. To estimate the efficiency of the proposed SAGM, a series of experiments were carried out on two datasets, namely MNIST and CIFAR-10. Compared to state-of-the-art attack techniques, our proposed method can quickly and efficiently search for perturbation samples to misclassify the original samples. The results reveal that the SAGM is an effective and efficient technique for generating perturbation samples.

Differential evolution (DE) is a highly effective evolutionary algorithm. However, the performance of DE depends on strategies and control parameters. The combination of many strategies helps balance the exploitation and exploration of DE. In this study, a multi-population based on k-means clustering is proposed to realize an ensemble of multiple strategies, thereby resulting in a new DE variant, namely KSDE, where similar individuals in the population implement the same mutation strategies, and dissimilar subpopulations migrate information through the soft island model (SIM). Firstly, the population is virtually divided into k subpopulations by the k-means clustering algorithm. Secondly, the individual specific mutation scheme is selected from a strategy pool by random method. Finally, the migration of subpopulation information is done using soft island model. The performance of the KSDE algorithm is evaluated on 13 benchmark problems. The experiments show that KSDE algorithm improves the performance of the DE algorithm.

The optimization of complex industrial systems is the key to improving the efficiency and safety of system operation. With the increasing scale of modern industry and the complexity of the production process, traditional optimization methods such as state transition algorithm (STA) are difficult to apply to the optimization problems of complex systems. Insufficient individual diversity of candidate solutions and the susceptibility of the algorithm to local optima are two main challenges that need to be addressed. This paper proposes a novel heuristic optimization method named CSL-STA, which integrates communication and self-learning strategies with STA. The communication strategy increases diversity during algorithm iteration, while the self-learning strategy increases the probability of escaping local optima. A series of comprehensive experiments have been conducted to verify the performance of the proposed method. These experimental results reveal that CSL-STA surpasses several existing optimization algorithms regarding global search capability and solution accuracy.