Only the smell perception rule is considered in the butterfly optimization algorithm (BOA), which is prone to falling into a local optimum. Compared with the original BOA, an extra operator, i.e., color perception rule, is incorporated into the proposed hybrid-flash butterfly optimization algorithm (HFBOA), which makes it more in line with the actual foraging characteristics of butterflies in nature. Besides, updating the strategy of the control parameters by the logistic mapping is used in the HFBOA for enhancing the global optimal ability. The performance of the proposed method was verified by twelve benchmark functions, where the comparison experiment results show that the HFBOA converges quicker and has better stability for numerical optimization problems, which are compared with six state-of-the-art optimization methods. Additionally, the proposed HFBOA is successfully applied to six engineering constrained optimization problems (i.e., tubular column design, tension/compression spring design, cantilever beam design, etc.). The simulation results reveal that the proposed approach demonstrates superior performance in solving complex real-world engineering constrained tasks.
Medical images such as facial and tongue images have been widely used for intelligence-assisted diagnosis, which can be regarded as the multi-label classification task for disease location (DL) and disease nature (DN) of biomedical images. Compared with complicated convolutional neural networks and Transformers for this task, recent MLP-like architectures are not only simple and less computationally expensive, but also have stronger generalization capabilities. However, MLP-like models require better input features from the image. Thus, this study proposes a novel convolution complex transformation MLP-like (CCT-MLP) model for the multi-label DL and DN recognition task for facial and tongue images. Notably, the convolutional Tokenizer and multiple convolutional layers are first used to extract the better shallow features from input biomedical images to make up for the loss of spatial information obtained by the simple MLP structure. Subsequently, the Channel-MLP architecture with complex transformations is used to extract deep-level contextual features. In this way, multi-channel features are extracted and mixed to perform the multi-label classification of the input biomedical images. Experimental results on our constructed multi-label facial and tongue image datasets demonstrate that our method outperforms existing methods in terms of both accuracy (Acc) and mean average precision (mAP).
Complex optimization (CO) problems have been solved using swarm intelligence (SI) methods. One of the CO problems is the Wireless Sensor Network (WSN) coverage optimization problem, which plays an important role in Internet of Things (IoT). A novel hybrid algorithm is proposed, named hybrid particle swarm butterfly algorithm (HPSBA), by combining their strengths of particle swarm optimization (PSO) and butterfly optimization algorithm (BOA), for solving this problem. Significantly, the value of individual scent intensity should be non-negative without consideration of the basic BOA, which is calculated with absolute value of the proposed HPSBA. Moreover, the performance of the HPSBA is comprehensively compared with the fundamental BOA, numerous potential BOA variants, and tried-and-true algorithms, for solving the twenty-six commonly used benchmark functions. The results show that HPSBA has a competitive overall performance. Finally, when compared to PSO, BOA, and MBOA, HPSBA is used to solve the node coverage optimization problem in WSN. The experimental results demonstrate that the HPSBA optimized coverage has a higher coverage rate, which effectively reduces node redundancy and extends WSN survival time.