Inertia Weights-based Whale Optimization Algorithm and Its Application to Diagnostic Analysis of Diabetic Disease

• Main Authors: Wei-Chen Huang, 黃湋宸
• Other Authors: Jenn-Long Liu
• Format: Others
• Language: zh-TW
• Published: 2019
• Online Access: http://ndltd.ncl.edu.tw/handle/zq9n85

碩士 === 義守大學 === 資訊管理學系 === 107 === As the lifestyle and eating habits of people nowadays changed, diabetes has not only caused great damage to people’s health, but also been the top five among the top ten leading causes of death for a long time. Because there is still no radical cure for diabetes, nor significant symptoms in prediabetes status. In addition, gestational diabetes mellitus has even been the third among the top ten leading cause of death of middle-aged women. If we can diagnose someone as prediabetes, and provide proper health education and cure, we may prevent it from becoming areal diabetes. This study uses the 768 gestational diabetes mellitus sample of the UC Irvine Machine Learning Repository, and the Whale Optimization Algorithm to analyze diabetes cases. After checking calculations and analysis, we compare the data to the Whale Optimization Algorithm, and then use Weka to conduct cross-validation. The results reveal that IWOA with inertia weight is better than minimum benchmark functions of WOA. In comparison with WOA, the prediction result is very competitive. The result of this study will offer a better way to WOA.