通过微阵列数据中的基因分析来识别肿瘤是人工智能和生物信息学研究的关键领域。由于相对于有限的观察数量而言，基因数量较多，因此这项任务具有挑战性，这使得特征选择成为关键步骤。本文介绍了一种新颖的包装器特征选择方法，该方法利用将遗传算子与 Sinh Cosh 优化器 (SCHO) 相结合的混合优化算法，称为 SCHO-GO。 SCHO-GO 算法旨在避免局部最优、简化搜索过程并在不影响分类器性能的情况下选择最相关的特征。传统方法常常因搜索空间广泛而失效，因此需要混合方法。我们的方法旨在降低维度并提高分类精度，这在模式识别和数据分析中至关重要。 SCHO-GO 算法与支持向量机 (SVM) 分类器集成，显着提高了癌症分类的准确性。我们使用 CEC'2022 基准函数评估了 SCHO-GO 的性能，并将其与七种著名的元启发式算法进行了比较。统计分析表明 SCHO-GO 始终优于这些算法。对八个微阵列基因表达数据集（特别是基因表达癌症 RNA-Seq 数据集）的实验测试表明，SCHO-GO-SVM 模型的准确度高达 99.01%，凸显了其在处理复杂数据集方面的稳健性和精确度。此外，SCHO-GO 算法在特征选择和解决数学基准问题方面表现出色，为微阵列数据分析中的肿瘤识别和分类提供了一种有前景的方法。版权所有 © 2024 Elsevier Ltd。保留所有权利。

The identification of tumors through gene analysis in microarray data is a pivotal area of research in artificial intelligence and bioinformatics. This task is challenging due to the large number of genes relative to the limited number of observations, making feature selection a critical step. This paper introduces a novel wrapper feature selection method that leverages a hybrid optimization algorithm combining a genetic operator with a Sinh Cosh Optimizer (SCHO), termed SCHO-GO. The SCHO-GO algorithm is designed to avoid local optima, streamline the search process, and select the most relevant features without compromising classifier performance. Traditional methods often falter with extensive search spaces, necessitating hybrid approaches. Our method aims to reduce the dimensionality and improve the classification accuracy, which is essential in pattern recognition and data analysis. The SCHO-GO algorithm, integrated with a support vector machine (SVM) classifier, significantly enhances cancer classification accuracy. We evaluated the performance of SCHO-GO using the CEC'2022 benchmark function and compared it with seven well-known metaheuristic algorithms. Statistical analyses indicate that SCHO-GO consistently outperforms these algorithms. Experimental tests on eight microarray gene expression datasets, particularly the Gene Expression Cancer RNA-Seq dataset, demonstrate an impressive accuracy of 99.01% with the SCHO-GO-SVM model, highlighting its robustness and precision in handling complex datasets. Furthermore, the SCHO-GO algorithm excels in feature selection and solving mathematical benchmark problems, presenting a promising approach for tumor identification and classification in microarray data analysis.Copyright © 2024 Elsevier Ltd. All rights reserved.