ACC index of SVM on the selected feature subset.

BackgroundCancer diagnosis based on machine learning has become a popular application direction. Support vector machine (SVM), as a classical machine learning algorithm, has been widely used in cancer diagnosis because of its advantages in high-dimensional and small sample data. However, due to the high-dimensional feature space and high feature redundancy of gene expression data, SVM faces the problem of poor classification effect when dealing with such data.MethodsBased on this, this paper proposes a hybrid feature selection algorithm combining information gain and grouping particle swarm optimization (IG-GPSO). The algorithm firstly calculates the information gain values of the features and ranks them in descending order according to the value. Then, ranked features are grouped according to the information index, so that the features in the group are close, and the features outside the group are sparse. Finally, grouped features are searched using grouping PSO and evaluated according to in-group and out-group.ResultsExperimental results show that the average accuracy (ACC) of the SVM on the feature subset selected by the IG-GPSO is 98.50%, which is significantly better than the traditional feature selection algorithm. Compared with KNN, the classification effect of the feature subset selected by the IG-GPSO is still optimal. In addition, the results of multiple comparison tests show that the feature selection effect of the IG-GPSO is significantly better than that of traditional feature selection algorithms.ConclusionThe feature subset selected by IG-GPSO not only has the best classification effect, but also has the least feature scale (FS). More importantly, the IG-GPSO significantly improves the ACC of SVM in cancer diagnostic.背景：基于机器学习的癌症诊断已成为热门应用方向。支持向量机（Support Vector Machine，SVM）作为经典机器学习算法，因在高维小样本数据上的固有优势，被广泛应用于癌症诊断领域。然而，基因表达数据存在高维特征空间与较高的特征冗余度，导致支持向量机在处理此类数据时面临分类效果欠佳的问题。 方法：基于上述问题，本文提出一种融合信息增益与分组粒子群优化（Grouping Particle Swarm Optimization，GPSO）的混合特征选择算法（IG-GPSO）。该算法首先计算各特征的信息增益值，并按取值降序排列；随后，基于信息指标对排序后的特征进行分组，使组内特征关联性较强、组间特征保持稀疏性；最后，利用分组粒子群优化算法对分组后的特征集进行搜索，并结合组内与组间指标完成评估。 结果：实验结果表明，在IG-GPSO筛选得到的特征子集上，支持向量机的平均分类准确率（Accuracy，ACC）可达98.50%，其性能显著优于传统特征选择算法。相较于K近邻（K-Nearest Neighbor，KNN）算法，IG-GPSO筛选出的特征子集仍能取得最优分类效果。此外，多组对照实验结果显示，IG-GPSO的特征选择效果显著优于传统特征选择算法。 结论：经IG-GPSO筛选得到的特征子集不仅具备最优的分类性能，同时特征规模（Feature Scale，FS）最小。更为关键的是，IG-GPSO显著提升了支持向量机用于癌症诊断时的分类准确率。