PERBANDINGAN PARTICLE SWARM OPTIMIZATION DAN NGUYEN WIDROW PADA IMPLEMENTASI BACKPROPAGATION UNTUK PREDIKSI JUMLAH KASUS DEMAM BERDARAH DENGUE (Studi Kasus: DKI Jakarta)

Audrey Era Goldenia, . (2022) PERBANDINGAN PARTICLE SWARM OPTIMIZATION DAN NGUYEN WIDROW PADA IMPLEMENTASI BACKPROPAGATION UNTUK PREDIKSI JUMLAH KASUS DEMAM BERDARAH DENGUE (Studi Kasus: DKI Jakarta). Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ABSTRAK.pdf
Download (153kB)
[img] Text
AWAL.pdf
Download (975kB)
[img] Text
BAB I.pdf
Download (175kB)
[img] Text
BAB II.pdf
Restricted to Repository UPNVJ Only
Download (382kB)
[img] Text
BAB III.pdf
Restricted to Repository UPNVJ Only
Download (227kB)
[img] Text
BAB IV.pdf
Restricted to Repository UPNVJ Only
Download (464kB)
[img] Text
BAB V.pdf
Download (74kB)
[img] Text
DAFTAR PUSTAKA.pdf
Download (14kB)
[img] Text
DAFTAR RIWAYAT HIDUP.pdf
Restricted to Repository UPNVJ Only
Download (22kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository UPNVJ Only
Download (1MB)
[img] Text
HASIL PLAGIARISME.pdf
Restricted to Repository staff only
Download (8MB)
[img] Text
ARTIKEL KI.pdf
Restricted to Repository staff only
Download (453kB)

Abstract

Dengue hemorrhagic fever is one of the dangerous diseases and fatal consequences if not treated quickly and appropriately. The disease caused by the dengue virus has become endemic in more than 100 countries. The case of dengue fever in Indonesia itself is still a matter that needs to be considered because many cases occur every year which touch the hundreds of thousands. The number of cases that occur every year continues to increase and decrease. To anticipate a sudden spike in cases, machine learning technology can be used to predict the number of cases in the future. In terms of prediction, one of the methods that can be used is Backpropagation. To optimize the initial weight value to be used in the Backpropagation network, Backpropagation can be combined with Particle Swarm Optimization and Nguyen Widrow methods. From optimizing the value of the network weight, it is intended to obtain minimal error results. The results of the application of the three models show that the model can work well to predict cases of dengue fever with MSE training values for BP, PSO-BP, and NW-BP, respectively, namely 2,02 x 10-2 , 2,03 x 10-2 , and 1,972 x 10-2 . In addition, the MSE testing results obtained for BP, PSO-BP, and NW-BP were 4.76 x 10-2 , 4.44 x 10- 2 , and 5.70 x 10-2 . From the three models, the best performance results were obtained by PSO-Backpropagation with MSE and MAPE values, namely 4.44 x 10- 2 and 18.43%.

Item Type: Thesis (Skripsi)
Additional Information: [No. Panggil: 1810511084] [Pembimbing 1 : Didit Widyanto] [Pembimbing 2 : Mayanda Mega Santoni] [Penguji 1 : Yuni Widiastiwi] [Penguji 2 : Nurul Chamidah]
Uncontrolled Keywords: Backpropagation, particle swarm optimization, Nguyen widrow, dbd, Dengue hemorrhagic fever
Subjects: T Technology > T Technology (General)
Divisions: Fakultas Ilmu Komputer > Program Studi Informatika (S1)
Depositing User: Audrey Era Goldenia
Date Deposited: 10 Aug 2022 06:40
Last Modified: 10 Aug 2022 06:40
URI: http://repository.upnvj.ac.id/id/eprint/19837

Actions (login required)

View Item View Item