Provide a method to diagnose and optimize diabetes using data mining methods and firefly algorithm
Diabetes is one of the most common, dangerous and costly diseases in the world today, which is increasing at an alarming rate. The use of data mining methods can help in the early diagnosis of diabetes, which prevents the progression of this disease and many of its complications such as cardiovascul...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | fas |
| Published: |
University of Qom
2023-09-01
|
| Series: | مدیریت مهندسی و رایانش نرم |
| Subjects: | |
| Online Access: | https://jemsc.qom.ac.ir/article_2020_19d2033b69a54d884e36d62d1c4e5edf.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Diabetes is one of the most common, dangerous and costly diseases in the world today, which is increasing at an alarming rate. The use of data mining methods can help in the early diagnosis of diabetes, which prevents the progression of this disease and many of its complications such as cardiovascular disease, vision problems and kidney disease. Providing care and health services to people with diabetes provides useful information that can be used to identify, treat, follow-up care and even prevent diabetes. In this study, a new method is presented to improve the diagnosis and prevention of diabetes using data mining methods. In this research, the DBSCAN clustering algorithm is used to cluster the data. Then, using SVM, we classify the data to identify useful data, and finally, with the firefly algorithm, we increase the obtained data to increase we optimize performance with this algorithm. The results of this study indicate that the DBSCAN algorithm is more efficient than other clustering algorithms. Also, the SVM algorithm can achieve 98% accuracy, which compared to other data mining algorithms could achieve a higher accuracy percentage. |
|---|---|
| ISSN: | 2538-6239 2538-2675 |