Ovarian Cancer Prediction Research Based On Microarray Mass Spectrometry Data

As one of the major threats to human life and health,cancer has been appraised as the deadliest disease in the world.Recently,the cancer prediction by microarray mass spectrometry data has become the research focus,which has realized the early cancer detection and increased the survival rate of cancer patients.First of all,the background and significance of cancer prediction are clarified,the current status and methods are reviewed,and the prediction methods based on machine learning are analyzed and summarized.Accordingly,the ovarian cancer prediction research based on microarray data is carried out.And the PCA-ABC-SVR ovarian cancer prediction model is proposed,which is based on principal component analysis,artificial bee colony optimization and support vector regression machine in the thesis.For the training data of the model,aiming at the characteristics of microarray data set,the PCA principal component analysis method is used to reduce the dimensionality of the data,and the ABC artificial bee colony optimization algorithm is adopted to select the parameters of the support vector regression machine SVR to construct the PCA-ABC-SVR ovarian cancer prediction model.Finally,in the given experimental platform environment of hardware and software,three simulation experiments of k value selection,model comparison and optimization comparison are implemented.And the learning and training of the proposed model are realized by the data set.Through the analysis of the experimental results,the feasibility and superiority of the PCA-ABC-SVR ovarian cancer prediction model are verified.