RAHARDJO, RIO RIZKI (2023) HEART ATTACK PREDICTION USING NEURAL NETWORK AND RANDOM FOREST. Other thesis, Universitas Katholik Soegijapranata Semarang.
![[img]](http://repository.unika.ac.id/style/images/fileicons/text.png) |
Text
16.K1.0054-RIO RIZKI RAHARDJO-COVER_a.pdf Download (835kB) |
|
Text
16.K1.0054-RIO RIZKI RAHARDJO-BAB I_a.pdf Download (117kB) |
|
Text
16.K1.0054-RIO RIZKI RAHARDJO-BAB II_a.pdf Restricted to Registered users only Download (122kB) |
|
Text
16.K1.0054-RIO RIZKI RAHARDJO-BAB III_a.pdf Download (116kB) |
|
Text
16.K1.0054-RIO RIZKI RAHARDJO-BAB IV_a.pdf Download (312kB) |
|
Text
16.K1.0054-RIO RIZKI RAHARDJO-BAB V_a.pdf Download (570kB) |
|
Text
16.K1.0054-RIO RIZKI RAHARDJO-BAB VI_a.pdf Download (112kB) |
|
Text
16.K1.0054-RIO RIZKI RAHARDJO-DAPUS_a.pdf Download (180kB) |
|
Text
16.K1.0054-RIO RIZKI RAHARDJO-LAMP_a.pdf Download (905kB) |
Abstract
In this project, I raise the issue of predicting someone will have a heart attack disease. Based on the 2014-2019 Global Burden of Disease and Institute for Health Metrics and Evaluation (IHME), heart disease is the highest cause of death in Indonesia. The 2013 and 2018 Basic Health Research (Riskesdas) data show an increasing trend of heart disease from 0.5% in 2013 to 1.5% in 2018. In fact, heart disease is the biggest cost burden. Based on BPJS Health data, in 2021 the largest health financing will be for heart disease of IDR 7.7 trillion. Heart disease is caused by unhealthy lifestyles, such as smoking and lack of physical activity, obesity, hypertension and diabetes mellitus. With this project, it is hoped that the detection of heart attacks in suspects/people in general can be known early. The process that will be carried out in this project to predict the presence of a heart attack is to use two classification algorithm methods, namely Neural Network and Random Forest. By using an existing dataset downloaded on the Kaggle site and implemented in the Orange Data mining program. I trained both algorithms with the downloaded dataset to test the accuracy of the prediction results. The final results of the training data for the two algorithms will be used to see the level of accuracy in the two algorithms with varying training data parameters. So that it can be concluded which algorithm is right to use for a lot or a little available data.
| Item Type: | Thesis (Other) |
|---|---|
| Subjects: | 000 Computer Science, Information and General Works |
| Divisions: | Faculty of Computer Science > Department of Informatics Engineering |
| Depositing User: | mr AM. Pudja Adjie Sudoso |
| Date Deposited: | 04 Apr 2023 05:59 |
| Last Modified: | 04 Apr 2023 05:59 |
| URI: | http://repository.unika.ac.id/id/eprint/31391 |
Actions (login required)
 |
View Item |
