| 114 | 0 | 137 |
| 下载次数 | 被引频次 | 阅读次数 |
针对乳腺癌良性与恶性的鉴别，提出一种融合粒子群优化与网格搜索的支持向量机模型(GPSO-SVM).该方法先通过网格搜索初步确定粒子群优化的超参数范围，并在粒子群优化迭代过程中阶段性引入网格搜索.联合完成对支持向量机超参数的优化，有效结合了网格搜索的全局搜索能力与粒子群算法的局部精细寻优优势，提高了参数寻优的效率与准确性.实验结果显示，GPSO-SVM模型在4种不同乳腺癌数据集上的五折交叉验证准确率分别达到98.60%、97.00%、90.52%和88.89%,优于其他寻优方法.
Abstract：For the binary classification of benign and malignant breast cancer, a support vector machine model optimized by particle swarm optimization and grid search(GPSO-SVM) is proposed.Grid search is used to initially define PSO parameter ranges and is periodically incorporated during iterations to optimize SVM hyperparameters. This hybrid method leverages the global search ability of grid search and the local refinement of PSO, enhancing parameter optimization efficiency and accuracy. Experimental results demonstrate that the GPSO-SVM model achieved five-fold cross-validation accuracies of 98.60%, 97.00%, 90.52%, and 88.89% on four different breast cancer datasets, outperforming other optimization approaches.
[1] ABHISHEKA B,BISWAS S K,PURKAYASTHA B.A comprehensive review on breast cancer detection,classification and segmentation using deep learning[J].Archives of Computational Methods in Engineering,2023,30(8):5023-5052.
[2] AYYILDIZ O,AYDIN Z,YILMAZ B,et al.Lung cancer subtype differentiation from positrone mission tomography images[J].Turkish Journal of Electrical Engineering and Computer Sciences,2020,28(1):262-274.
[3] 林中飞，王南芳，李小红.基于机器学习的前列腺癌患者分类研究[J].应用数学进展，2021,10(10):3261-3268.
[4] LILHORE U K,SIMAIYA S,PANDEY H,et al.Breast cancer detection in the IoT cloud-based healthcare environment using fuzzy cluster segmentation and SVM classifier[J].Ambient communications and amputer systems,2022,356:165-179.
[5] 崔洪铭，赵扬，于彬，等.基于机器学习算法的胃肠癌患者术后短期并发症的预测研究[J].临床医学进展，2023,13(3):5017-5035.
[6] ARNOLD C,BIEDEBACH L,KüPFER A,et al.The role of hyperparameters in machine learning models and how to tune them[J].Political Science Research and Methods,2023,12(3):841-848.
[7] ALI N M,BESAR R,AB AZIZ N A.A case study of microarray breast cancer classification using machine learning algorithms with grid search cross validation[J].Bulletin of Electrical Engineering and Informa-tics,2023,12(2):1047-1054.
[8] PATRCIO M,PEREIRAJ,CRISSTOMO J,et al.Breast Cancer Coimbra.[DS/OL].(2018)[2025-05-01].https://archive.ics.uci.edu/dataset/451/breast+cancer+coimbra.
[9] WOLBERG W,STREET W,MANGASARIAN O.Breast Cancer Wisconsin(Prognostic)[DS/OL].1995[2025-05-01].UCI Machine Learning Repository.https://doi.org/10.24432/C5GK50.
[10] WOLBERG W,MANGASARIAN O,STREET N,et al.Breast Cancer Wisconsin (Diagnostic)[DS/OL].1993[2025-05-01].https://archive.ics.uci.edu/dataset/17/breast+cancer+wisconsin+diagnostic.
[11] WOLBERG W.Breast Cancer Wisconsin (Original)[DS/OL].1990[2025-05-01].https://archive.ics.uci.edu/dataset/15/breast+cancer+wisconsin+original.
[12] ANDOYO F A,ARIFUDIN R.Optimization of classification accuracy using K-Means and Genetic algorithm by Integrating C4.5 algorithm for diagnosis breast cancer disease[J].Journal of Advances in Information Systems and Technology,2021,3(1):1-8.
[13] FAHAD A.Statistical analysis of random forest classifier in breast cancer diagnosis[J].ARPN Journal of Engineering and Applied Sciences,2025,20(4):177-187.
[14] SINGH A K.Breast cancer classification using ML on WDBC[M]//Machine vision and augmented intelligence:Select proceedings of MAI 2022.Singapore:Springer Nature Singapore,2023:609-619.
[15] KUSHWAHA V.Breast cancer diagnostic using machine learning:Applying supervised learning techniques to coimbra and wisconsin datasets[D].Lappeenranta:Lappeenranta-Lahti University of Technology LUT,2023.
基本信息:
DOI：10.13804/j.cnki.2095-6991.2026.01.018
中图分类号:R737.9;TP18
引用信息:
[1]汪颖,王琳.基于PSO和网格优化结合的SVM算法癌症分类研究[J].兰州文理学院学报(自然科学版),2026,40(01):56-61.DOI:10.13804/j.cnki.2095-6991.2026.01.018.
2026-01-10
2026-01-10