Niching techniques have been widely incorporated into evolutionary algorithms for solving multimodal optimization problems (MMOPs). However, most of the existing niching techniques are either sensitive to the niching parameters or require extra fitness evaluations (FEs) to maintain the niche detection accuracy. In this paper, we propose a new automatic niching technique based on the affinity propagation clustering (APC) and design a novel niching differential evolution (DE) algorithm, termed as automatic niching DE (ANDE), for solving MMOPs. In the proposed ANDE algorithm, APC acts as a parameter-free automatic niching method that does not need to predefine the number of clusters or the cluster size. Also, it can facilitate locating multiple peaks without extra FEs. Furthermore, the ANDE algorithm is enhanced by a contour prediction approach (CPA) and a two-level local search (TLLS) strategy. Firstly, the CPA is a predictive search strategy. It exploits the individual distribution information in each niche to estimate the contour landscape, and then predicts the rough position of the potential peak to help accelerate the convergence speed. Secondly, the TLLS is a solution refine strategy to further increase the solution accuracy after the CPA roughly predicting the peaks. Compared with other state-of-the-art DE and non-DE multimodal algorithms, even the winner of competition on multimodal optimization, the experimental results on 20 widely used benchmark functions illustrate the superiority of the proposed ANDE algorithm.

Epilepsy detection from electrical characteristics of EEG signals obtained from the brain of undergone subject is a challenge task for both research and neurologist due to the non-stationary and chaotic nature of EEG signals. As epileptic EEG signals contain huge fluctuating information about the functional behavior of the brain, it is hard to distinguish the fundamental dynamic, complex network of EEG signals without considering the strength among the nodes as they are connected with each other on the basis of these strengths. The prior research on natural visibility graph did not consider this issue in epileptic seizure, although it is a very important key point to have representative information from the signals. Hence, this paper aims to introduce a new idea for epilepsy detection using complex network statistical properties by measuring different strengths of the edges in natural visibility graph theory, which is considered as weight. Thus, the proposed method is named “weighted visibility graph”. In this proposed method, first, the epileptic EEG signals are transformed into complex network and then two important statistical properties of a network such as modularity and average weighted degree used for extracting the imperative characteristics from a network of EEG signals. After that, the extracted features are evaluated by two modern machine-learning classifiers such as, support vector machine with a different kernel function and k-nearest neighbor. The experimental results demonstrate that the combined effect of both features is valuable for network metrics to characterize the EEG time series signals in case of weighted complex network generating up to 100% classification accuracy.