TUBERCULOSIS CLASSIFICATION USING RANDOM FOREST WITH K-PROTOTYPE AS A METHOD TO OVERCOME MISSING VALUE

Keyphrases

• Tuberculosis 100%
• Random Forest 100%
• Tuberculosis Classification 100%
• K-prototypes 100%
• Lung 75%
• Classification Methods 50%
• Indonesia 25%
• Tuberculosis Data 25%
• Patient Data 25%
• Order of Accuracy 25%
• Mortality Cases 25%
• Parenchymal Tissue 25%
• Medical Record Data 25%
• Laboratory Results 25%
• Back Propagation Algorithm 25%
• High Mortality 25%
• Data Classification 25%
• Human Error 25%
• Patient Diagnosis 25%
• Anatomical Location 25%
• Support Vector Machine Model 25%
• TB Disease 25%
• Random Forest Method 25%
• Respiratory Organs 25%

Mathematics

• Classification Method 100%
• Missing Value 100%
• Support Vector Machine 50%
• Patient Data 50%
• Input Process 50%
• Method Performs 50%
• File Format 50%