Solving energy-saving distributed heterogeneous flexible job shop scheduling problem (ES-DHFJSP) aims to enhance industrial production efficiency while minimizing energy consumption. State-of-the-art co-evolutionary algorithms have emerged as effective approaches for addressing ES-DHFJSP. However, existing methodologies demonstrate compromised convergence rates and excessive computational overhead when confronted with vast search spaces. In this work, we propose a novel solution space transformation-guided co-evolution algorithm (SSTCE) to overcome this limitation. In SSTCE, we first establish an inter-job similarity metric and incorporate constrained hierarchical clustering with optimal leaf ordering (CHC-OLO) to generate clustered job sets, which are subsequently utilized for population initialization that achieves a favorable balance between convergence and diversity. To enhance search capability in expansive solution spaces, we devise a dynamic solution space transformation mechanism that effectively reduces inefficient searches within the algorithm. Furthermore, we develop tailored local search strategies leveraging domain-specific knowledge of DHFJSP properties. Extensive experimental evaluations across 20 benchmark instances demonstrate that SSTCE significantly outperforms existing evolutionary algorithms in solving ES-DHFJSP.

Extensive collection of gene expression data has provided abundant resources for the identification of biomarker genes and disease classification. However, there are still many challenges in processing high-dimensional microarray data, such as balancing classification accuracy with feature subset size and computational costs. To address the issues, a novel co-evolutionary particle swarm optimization method is proposed for biomarker selection and disease classification (NCPSO). Firstly, a population initialization strategy based on gene weight is provided. This strategy accurately calculates the importance of genes to optimize the search space of candidate genes. Secondly, a co-evolutionary search method based on gene information transfer is designed. This method applies gene knowledge transfer search mechanism and gene weight update mechanism to two equally sized subpopulations, respectively. During the evolutionary search process, the gene information transfer and interaction are conducted to accelerate the acquisition of the globally optimal gene subset. Finally, the dynamic evolution supervision of gene individuals is provided. This process can real-time detect the impact of mutated genes on classification performance during the evolution process, thereby enhancing the classification accuracy of gene selection. To validate the effectiveness of the NCPSO algorithm, five state-of-the-art methods on six high-dimensional microarray datasets are compared and the experimental results demonstrate that NCPSO outperforms the comparison methods in terms of classification accuracy, selected gene subset size, and computational time.