Method for realizing breast cancer classification based on novel quantum framework

Abstract

The invention discloses a method for realizing breast cancer classification based on a novel quantum framework, and the method comprises the steps: carrying out quantum coding according to breast cancer data features, and coding sample features to a quantum line; performing quantum kernel entropy principal component analysis on the breast cancer data by combining a quantum kernel estimation method to achieve the aim of preprocessing the breast cancer data; quantum coding is carried out successively according to the obtained preprocessed breast cancer data, and the processed breast cancer data enter a variable component sub-line, namely a quantum variation classifier; performing parameter optimization on parameters of the quantum variation classifier by using a quantum gradient descent algorithm; judging whether the loss function of the quantum variation classifier meets the actual requirement or not, and if yes, ending the quantum variation classification process; and if the actual requirement is not met, quantum coding is carried out on the next piece of preprocessed breast cancer data. Under the conditions of few data set feature values and low classification accuracy, the breast cancer classification accuracy can be effectively improved.

Description

technical field [0001] The invention belongs to the technical field of breast cancer classification and identification, and in particular relates to a method for realizing breast cancer classification based on a novel quantum framework. Background technique [0002] The existing main techniques for breast cancer classification based on quantum machine learning include methods based on quantum kernel estimation and methods based on quantum variational classification. [0003] The main disadvantages of these techniques are: [0004] 1. Data preprocessing is mainly realized by traditional methods, especially in data dimensionality reduction, SVD (singular value decomposition) and PCA (principal component analysis) are mainly used. These two methods have obvious defects. One is the difference between actual data. It is not a complex nonlinear relationship. Second, there is a certain amount of redundant information between the data, which is very likely to over-enforce the infor...

AI Technical Summary

Problems solved by technology

[0007] The present invention aims at the data preprocessing of the existing breast cancer classification method based on quantum machine learning, which is mainly realized by traditional methods, which cannot ensure that the useful features of the original information are maintained while reducing the dimension; the traditional gradient descent is mainly used in the model optimization link Algorithm, the time-consuming problem of reaching convergence is a problem, and a method for breast cancer classification based on a new quantum framework is proposed, and the relevant parameters of the cost function that need to be solved by the traditional method are transformed and encoded into the relative superposition state in the Hilbert space. In terms of phase, quantum optimization algorithm is used to find the optimal parameters of certain tasks, hoping to alleviate the barren plateau problem; at the same time, quantum kernel estimation method is used to realize the optimization and acceleration of kernel principal component analysis (KPCA), so as to achieve rapid The purpose of principal component analysis; in the case of few eigenvalues ​​in the data set and low classification accuracy, it can effectively improve the classification accuracy of breast cancer

Images