|
Comparison of Data Classification Efficiency to Analyze Risk Factors that Affect the Occurrence of Hyperthyroid using Data Mining Techniques |
|---|---|
| รหัสดีโอไอ | |
| Creator | Nattavadee Hongboonmee |
| Title | Comparison of Data Classification Efficiency to Analyze Risk Factors that Affect the Occurrence of Hyperthyroid using Data Mining Techniques |
| Contributor | Praphasiri Trepanichkul |
| Publisher | Faculty of Information Science and Technology, Mahanakorn University of Technology |
| Publication Year | 2562 |
| Journal Title | Journal of Information Science and Technology |
| Journal Vol. | 9 |
| Journal No. | 1 |
| Page no. | 41-51 |
| Keyword | Hyperthyroid, Data Mining, Artificial Neural networks, Naive Bayes, Decision Tree |
| URL Website | https://tci-thaijo.org/index.php/JIST |
| Website title | Journal of Information Science and Technology |
| ISSN | 2651-1053 |
| Abstract | This research aims to compare the efficiency of data classification by 3 types of data mining algorithms, artificial neural networks, naive bayes and decision tree in order to obtain the most efficient model that will be analyzed for factors affecting the risk of hyperthyroid by reducing inputs individually. The data used in the experiment are data from hospitals in Phitsanulok, there are 323 datasets. The data for analysis are 12 factors. The comparison results showed that the classification of data using artificial neural networks gave the highest efficiency with 82.97% accuracy, which is more than a decision trees and naive bayes with efficiency values of 79.87% and 68.11%, respectively. Effect on the risk of hyperthyroid, it was found that the important symptoms were mood swings and fatigue. The personal factors that are important are gender. In addition to finding factors, this research can also use the data classification model developed to predict the risk of hyperthyroid on smart phone. To help support decision-making in the analysis of hyperthyroid disease risk, can be self-screening, and can continue to guide the treatment of doctors and patients. |
