朴素贝叶斯分类器
算法
计算机科学
机器学习
支持向量机
人工智能
贝叶斯定理
领域(数学)
统计分类
样品(材料)
数据挖掘
贝叶斯概率
数学
色谱法
化学
纯数学
作者
Dominikus Boli Watomakin,Andi Wahju Rahardjo Emanuel
标识
DOI:10.1109/icsitech46713.2019.8987464
摘要
Handling in the health sector has now developed a lot in terms of Information Technology. Many studies in the field of Information Technology that helps in accelerating the performance of management of a health agency, and also health workers who require fast and good decision making. In this study, a comparison of algorithms was used to diagnose diabetes, which had been used in many previous studies. Support vector machines and Naive Bayes become comparison algorithms carried out in this study. The purpose of this study was to look at the performance of the two algorithms and help health workers in better decision making. The level of accuracy, precision, sensitivity and specificity of the two algorithms will be the main focus of this research. Comparisons were made using a diabetes dataset taken from the National Institute of Diabetes and Digestive and Kidney Diseases with a total sample data of 768 sample data. From the results of calculations and comparisons of support vector machine algorithms have a better average value compared to the Naive Bayes algorithm.
科研通智能强力驱动
Strongly Powered by AbleSci AI