A Survival Status Classification Model for Osteosarcoma Patients Based on E-CNN-SVM and Multisource Data Fusion

Table 2

The steps of the E-CNN-SVM and multisource algorithm.

Step 1	The copy number variation data, DNA methylation data, RNA gene sequencing data, and RNA homologue sequencing data are each reduced in dimension using the random forest algorithm
Step 2	Equal weighted fusion of these four types of data
Step 3	Combine the SMOTE algorithm with the TomekLink algorithm to clean and equalize the data
Step 4	Pretrain the E-CNN model and save the optimal model
Step 5	Feature extraction of data using the input layer to the fully connected layer of the E-CNN model
Step 6	Use the processed data to train the SVM model and use the trained model for classification