Skripsi
OPTIMASI ALGORITMA RANDOM FOREST MENGGUNAKAN ALGORITMA GENETIKA UNTUK KLASIFIKASI DATA PENDERITA PENYAKIT STROKE
Stroke is the second leading cause of death globally. A lack of knowledge regarding stroke risk factors results in high incidence and mortality rates. Using a classification approach can effectively address this issue. Classification involves grouping categories or classes based on patterns or characteristics found in the data. By classifying stroke patient data, we can identify patterns of stroke risk factors. The Random Forest algorithm was chosen for its high accuracy, but it has a drawback in that it requires a long processing time due to the large number of decision trees that need to be combined to determine the class. To overcome this weakness, a Genetic Algorithm is used for feature selection to identify the most relevant attributes, making the decision tree construction process more efficient and accurate. The study results show that the Random Forest method without optimization achieves an accuracy of 96.4%, while the method optimized with the Genetic Algorithm achieves an accuracy of 97.88%. With resampling, the accuracy of Random Forest reaches 80%, and with Genetic Algorithm optimization, it increases to 84%.
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2407003901 | T148538 | T1485382024 | Central Library (REFERENCES) | Available but not for loan - Not for Loan |
No other version available