Pedagogy and Reduction of K-nn Algorithm for Filtering Samples in the Breast Cancer Treatment
Pedagogy and Reduction of K-nn Algorithm for Filtering Samples in the Breast Cancer Treatment
复制标题
乳腺癌治疗中过滤样本的 K-nn 算法的教学法和简化
DOI：
10.1016/b978-0-12-419967-5.00003-x
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Dr. Suvarna Vani Koneru
中科院分区：
文献类型：
--
作者：
Sri Hari;Dr. Pragnyaban Nallamala;Dr. Suvarna Vani Mishra;Koneru;Nallamala;Dr. Pragnyaban Mishra;Dr. Suvarna Vani Koneru
- 医学诊断是当今确定任何疾病的首要任务。机器学习概念及其指定工具在这种诊断中带来了丰硕的成果。机器学习的识别系统和各种分类方法帮助大多数医学专家与传统实践相比更容易得出结论。乳腺癌是地球仪上大多数妇女的噩梦之一。近年来，随着乳腺癌患者的显著增加，乳腺癌分析（BCA）中的机器学习方法在诊断疾病方面取得了更好的结果。本文的当前上下文集中于使用混合机器学习方法与k-最近邻算法乳腺癌诊断与威斯康星州乳腺癌数据集（WBCD）。该方法是纯粹的性能分类的基础上，并呈现了99.14%的准确性相比，以前的文献调查存在。10-实施交叉验证并适当地用于获得准确度。到目前为止，获得的准确性结果仅适用于WBCD，但也可以明智地用于几个乳腺癌问题。
— Medical diagnosis is the primary task to determine any kind of disease today. Machine learning concepts and their specified tools in this diagnosing is bringing fruitful results. Recognition systems and various classification approaches of machine learning have helped most of the medical experts to draw conclusions easily compared to the traditional practices. Breast cancer is one among the nightmares in most of the women across the globe. As breast cancer patients are significantly increasing throughout the recent years, machine learning approaches in the breast cancer analysis (BCA) has proven better results in diagnosing the disease. The current context of this paper focuses on the usage of Hybrid machine learning approach with k-nearest neighbor algorithm breast cancer diagnosis with Wisconsin breast cancer dataset (WBCD). The approach is purely on the basis for performance classifications and rendered an accuracy of 99.14% as compared to the previous literature surveys existed. 10-fold cross validations are implemented and aptly used to obtain the accuracy. The accuracy results obtained so far are only on the WBCD, but can also be wisely used for several breast cancer problems.