#Cancer dataset in matlab 2012 software#
Their data was sourced by using Matlab software to pre-process. The metrics used where: Accuracy, Sensitivity and Specificity. de 2012 PCANet : Matlab codes of PCANet, PCA filters (MultiPIE). It is expected that annual cancer cases will rise from 14 million in 2012 to 22 within. We then perform KNN, SVM, Naive Bayes and Decision Tree achieving a max of 97% accuracy with correctly parametrised Naive Bayes (kfold cross validation with k = 10). We normalise the values of our data on the range.
The first one has our data (10xnumbOfRows) and the second one our expected labels (1xnumbOfRows). We get rid of the first column which has the id and we create two matrixes. The aim of the project was to have a first touch with solving classification problems on Matlab, so I have not spent much time optimizing the parameters or in general taking a lot of metrics into account. The methodology followed in this example is to select a reduced set of measurements or 'features' that can be used to distinguish between cancer and control patients using a classifier. Info about where this dataset has been used and which are the characteristics can be found in dataSetInfo.txt. The goal is to build a classifier that can distinguish between cancer and control patients from the mass spectrometry data. The dataset used is the breast-cancer-dataset-wisconsin ( (Original)) Breast Cancer Classification IntroductionĪ small and compact Matlab script that solves a breast cancer classification with KNN, SVM, Naive Bayes and Decision Tree.
0 kommentar(er)
