Search

In optimization and decision-making, multi-objective optimization has emerged as a pivotal challenge. Over the past three decades, the concerted efforts of scholars and practitioners across various disciplines have significantly advanced the study and implementation of Multi-Objective Evolutionary Algorithms (MOEAs). MOEAs stand at the forefront of multi-objective decision-making methodologies, marking a vibrant area of inquiry within evolutionary computation. This body of work categorizes MOEAs into three distinct streams: Decomposition-based MOEA algorithms, Dominant relationship-based MOEA algorithms, and Evaluation index-based MOEA algorithms. Focusing specifically on dominance-based MOEAs, this study integrates them with chaotic evolution (CE) strategies to enhance the efficacy of multi-objective optimization processes. Through comparative analysis against traditional algorithms, the newly proposed chaotic MOEA demonstrates superior optimization performance, thereby setting a robust groundwork for the continuous evolution and application of MOEAs.

The emergence of COVID-19 has broken the silence of humanity and people are gradually becoming concerned about pneumonia-related diseases; thus, improving the recognition rate of pneumonia-related diseases is an important task. Neural networks have a remarkable effectiveness in medical diagnoses, though the internal parameters need to be set in accordance to different data sets; therefore, an important challenge is how to further improve the efficiency of neural network models. In this paper, we proposed a learning exponential distribution optimizer based on chaotic evolution, and we optimized Resnet50 for COVID classification, in which the model is abbreviated as IEDO-net. The algorithm introduces a criterion for judging the distance of the signal-to-noise ratio, a chaotic evolution mechanism is designed according to this criterion to effectively improve the search efficiency of the algorithm, and a rotating flight mechanism is introduced to improve the search capability of the algorithm. In the computed tomography (CT) image data of COVID-19, the accuracy, sensitivity, specificity, precision, and F1 score of the optimized Resnet50 were 94.42%, 93.40%, 94.92%, 94.29% and 93.84%, respectively. The proposed network model is compared with other algorithms and models, and ablation experiments and convergence and statistical analyses are performed. The results show that the diagnostic performance of IEDO-net is competitive, which validates the feasibility and effectiveness of the proposed network.

The emergence of COVID-19 has broken the silence of humanity and people are gradually becoming concerned about pneumonia-related diseases; thus, improving the recognition rate of pneumonia-related diseases is an important task. Neural networks have a remarkable effectiveness in medical diagnoses, though the internal parameters need to be set in accordance to different data sets; therefore, an important challenge is how to further improve the efficiency of neural network models. In this paper, we proposed a learning exponential distribution optimizer based on chaotic evolution, and we optimized Resnet50 for COVID classification, in which the model is abbreviated as IEDO-net. The algorithm introduces a criterion for judging the distance of the signal-to-noise ratio, a chaotic evolution mechanism is designed according to this criterion to effectively improve the search efficiency of the algorithm, and a rotating flight mechanism is introduced to improve the search capability of the algorithm. In the computed tomography (CT) image data of COVID-19, the accuracy, sensitivity, specificity, precision, and F1 score of the optimized Resnet50 were 94.42%, 93.40%, 94.92%, 94.29% and 93.84%, respectively. The proposed network model is compared with other algorithms and models, and ablation experiments and convergence and statistical analyses are performed. The results show that the diagnostic performance of IEDO-net is competitive, which validates the feasibility and effectiveness of the proposed network. [ABSTRACT FROM AUTHOR]

We propose a novel population-based optimization algorithm, Chaotic Evolution (CE), which uses ergodic property of chaos to implement exploration and exploitation functions of an evolutionary algorithm. CE introduces a mathematical mechanism into an iterative process of evolution and simulates ergodic motion in a search space with a simple principle. A control parameter, direction factor rate, is proposed to guide search direction in CE. It is easy to extend its search capability by using different chaotic system in CE algorithm framework. The scalability of CE is higher than that of some other evolutionary computation algorithms. A series of comparative evaluations and investigations is conducted to analyse characteristics of the proposal. Our proposal can obtain better optimization performance by comparing with differential evolution and some of its variants. We point out that the chaos theory is used not only to describe and explain a non-linear system, but also to implement a variety of optimization algorithms based on its ergodic property. [ABSTRACT FROM AUTHOR]