Author:
Kong Xixi,Zhou Mengran,Bian Kai,Lai Wenhao,Hu Feng,Dai Rongying,Yan Jingjing
Abstract
AbstractBreast cancer is the second dangerous cancer in the world. Breast cancer data often contains more redundant information. Redundant information makes the breast cancer auxiliary diagnosis less accurate and time consuming. Dimension reduction algorithm combined with machine learning can solve these problems well. This paper proposes the single parameter decision theoretic rough set (SPDTRS) combined with the probability neural network (PNN) model for breast cancer diagnosis. We find that when the parameter value of SPDTRS is 2.5 and the SPREAD value is 0.75, the number of 30 attributes of the original breast cancer data dropped to 12, the accuracy of the SPDTRS-PNN model training set is 99.25%, the accuracy of the test set is 97.04%, and the test time is 0.093 s. The experimental results show that the SPDTRS-PNN model can improve the ac-curacy of breast cancer recognition, reduce the time required for diagnosis.
Funder
major science and technology program of Anhui province
the New Generation of Information Technology Innovation Project
Demonstration project of science popularization innovation and scientific research education for College Students
University-level Key Projects of Anhui University of Science and Technology
the National Key Research and Development Program of China
Publisher
Springer Science and Business Media LLC