PREDIKSI DATA HILANG PADA DATASET SERANGAN JANTUNG MENGGUNAKAN JARINGAN SARAF TIRUAN MULTI LAYER PERCEPTRON (MLP) UNTUK MENINGKATKAN AKURASI PREDIKSI PENYAKIT JANTUNG

WILIYANTI, WILIYANTI and Desiani, Anita and Dewi, Novi Rustiana (2019) PREDIKSI DATA HILANG PADA DATASET SERANGAN JANTUNG MENGGUNAKAN JARINGAN SARAF TIRUAN MULTI LAYER PERCEPTRON (MLP) UNTUK MENINGKATKAN AKURASI PREDIKSI PENYAKIT JANTUNG. Undergraduate thesis, Sriwijaya University.

[img] Text
RAMA_44201_08011381520072.PDF - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (1MB) | Request a copy
[img] Text
RAMA_44201_08011381520072_TURNITIN.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (13MB) | Request a copy
[img] Text
RAMA_44201_08011381520072_0011127702_0013117004_01_front_ref.PDF - Accepted Version
Available under License Creative Commons Public Domain Dedication.

Download (1MB)
[img] Text
RAMA_44201_08011381520072_0011127702_0013117004_02.PDF - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (409kB) | Request a copy
[img] Text
RAMA_44201_08011381520072_0011127702_0013117004_03.PDF - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (231kB) | Request a copy
[img] Text
RAMA_44201_08011381520072_0011127702_0013117004_04.PDF - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (562kB) | Request a copy
[img] Text
RAMA_44201_08011381520072_0011127702_0013117004_05.PDF - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (6kB) | Request a copy
[img] Text
RAMA_44201_08011381520072_0011127702_0013117004_06_ref.PDF - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (178kB) | Request a copy
[img] Text
RAMA_44201_08011381520072_0011127702_0013117004_07_lamp.PDF - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (76kB) | Request a copy

Abstract

The University of California Irvine (UCI) heart attack dataset has the disadvantage of having missing values in some attributes. Missing values will result in the loss of important information, so that missing values in data cannot be erased. To overcome the missing data can completed by several ways including: data cleansing, imputation of mean values, modes, and predictions. In this study, missing values will be treated by imputation and prediction using artificial neural network MLP. The existing prediction results are used to complete the dataset and predict heart disease. From the test results, it is known that the prediction of missing values can increase the accuracy value of 84,74% with the artificial neural network MLP method and 80,50% using the Naive Bayes method, whereas for accuracy before prediction of missing data obtained by 75,42% by using the artificial neural network MLP method and 77,11% using the Naive Bayes method. It can be concluded, that predictions of missing data with MLP artificial neural networks can improve the accuracy of predictions of heart disease.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Missing Value, Artificial Neural Networks, MLP, and Accuracy
Subjects: Q Science > QA Mathematics > QA1-939 Mathematics
Q Science > QA Mathematics > QA75-76.95 Calculating machines > QA75 Electronic computers. Computer science
Divisions: 08-Faculty of Mathematics and Natural Science > 44201-Mathematics (S1)
Depositing User: Users 943 not found.
Date Deposited: 06 Aug 2019 04:26
Last Modified: 06 Aug 2019 04:26
URI: http://repository.unsri.ac.id/id/eprint/2465

Actions (login required)

View Item View Item