Open AccessUtilization of Rough Sets Method with Optimization Genetic Algorithms in Heart Failure Cases
Author(s) -
Silfia Andini,
Rianto Sitanggang,
Anjar Wanto,
Harly Okprana,
GS Achmad Daengs,
Solly Aryza
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1933/1/012038
Subject(s) - rough set , computer science , data mining , genetic algorithm , set (abstract data type) , object (grammar) , data set , machine learning , algorithm , artificial intelligence , pattern recognition (psychology) , programming language
Rough Set is a machine learning method capable of analyzing dataset uncertainty to determine essential object attributes. At the same time, genetic algorithms can solve estimates for optimization and search problems. Therefore, this study aims to extract information from the rough set method with genetic algorithm parameters using the Rosetta application in heart failure cases. The research dataset was a collection of Clinical Heart Failure Record Data obtained from the UCI machine learning repository. There are 13 attributes contained in the dataset. Still, two features are removed, namely sex and time. It becomes 11 to reduce the amount of time and memory needed and make data easier to visualize, and help reduce irrelevant features. This research produces eight reducts and 77 rules based on the 20 sample data used. This study concludes that the use of genetic algorithm parameters can optimize the standard rough set method in generating rules.