LIAM, EWEN (2021) Machine Learning to Predict the onset of Diabetes Disease based on Diagnostic Measures using Two Different Libraries and Algorithms. Other thesis, Universitas Katholik Soegijapranata Semarang.
![[img]](http://repository.unika.ac.id/style/images/fileicons/text.png) |
Text
17.K1.0052-EWEN LIAM-COVER_a.pdf Download (894kB) |
|
Text
17.K1.0052-EWEN LIAM-BAB I_a.pdf Download (229kB) |
|
Text
17.K1.0052-EWEN LIAM-BAB II_a.pdf Restricted to Registered users only Download (245kB) |
|
Text
17.K1.0052-EWEN LIAM-BAB III_a.pdf Download (405kB) |
|
Text
17.K1.0052-EWEN LIAM-BAB IV_a.pdf Download (595kB) |
|
Text
17.K1.0052-EWEN LIAM-BAB V_a.pdf Download (895kB) |
|
Text
17.K1.0052-EWEN LIAM-BAB VI_a.pdf Download (223kB) |
|
Text
17.K1.0052-EWEN LIAM-DAPUS_a.pdf Download (332kB) |
|
Text
17.K1.0052-EWEN LIAM-LAMP_a.pdf Download (497kB) |
Abstract
Diabetes is a very serious problem that needs to be solved, the cure has not been found yet, but we still could prevent it by diagnosing people who have diabetes disease. If people positively have a diabetes disease, they can quickly prevent it from a young age by watching their diet. So, it is an important thing to predict the patient who has diabetes disease.This study will show about how technology could help the medic as a milestone in medical study The technology that used in this project is machine learning based, using logistic regression to predict the onset of diabetes. This project will also be using two methods, the first method is using Naïve Bayes from Sci-Kit learn library and the second method is Logistic Regression without using library at all. The final result is the Naïve Bayes with Sci-Kit library performs better compare to the logistic regression without library. It could happen because, the more complex the algorithm the more the algorithm has higher accuracy. Although the model of the logistic regression without library does not have good accuracy as the Naïve Bayes with library, the logistic regression also high value which means it can be trusted code.
| Item Type: | Thesis (Other) |
|---|---|
| Subjects: | 000 Computer Science, Information and General Works > 004 Data processing & computer science |
| Divisions: | Faculty of Computer Science > Department of Informatics Engineering |
| Depositing User: | mr AM. Pudja Adjie Sudoso |
| Date Deposited: | 15 Oct 2021 03:03 |
| Last Modified: | 15 Oct 2021 03:03 |
| URI: | http://repository.unika.ac.id/id/eprint/27132 |
Actions (login required)
 |
View Item |
